Commentary

Primary care practitioners (PCPs) in the US Department of Veterans Affairs (VA) provide care for patients with higher rates of many diseases—diabetes, heart disease, cancer, chronic obstructive pulmonary disease (COPD), and stroke—compared to the nonveteran population. ¹ Due to the medical complexities of these diseases, they are often misdiagnosed or not diagnosed at all.

COPD is hiding in plain sight, impacting quality of life and burdening US health care systems.² Research has yielded new treatments and evidence-based guidelines; however, COPD remains underdiagnosed. Only 13 million of the estimated 79 million US adults with COPD aged 20 to 79 years have been formally diagnosed.³ By the time patients are diagnosed, the disease is often advanced, and therapies are less effective. In 2 large studies of patients with COPD symptoms, later diagnosis was associated with worse outcomes.^4,5

Veterans have a higher prevalence of COPD (8%-19%) than nonveterans (6%), likely due to higher rates of smoking and service-related exposures, especially among veterans of post-9/11 conflicts.^6,7 Veterans do not always report symptoms and PCPs may not ask about symptoms, leading to underdiagnosis.⁸ The combination of high likelihood and underdetection of COPD presents a challenge and a target for VA quality improvement (QI).

The US Preventive Services Task Force (USPSTF) recommends against screening asymptomatic patients for COPD. However, both the USPSTF and the Global Initiative for Chronic Obstructive Lung Disease Report advocate for active case finding in primary care clinics to determine whether high-risk patients, such as smokers, experience COPD symptoms and warrant spirometry. ^9,10 To make early COPD diagnoses, clinicians may use questionnaires alone or in combination with handheld peak expiratory flow rate measurements.^11,12 Formal spirometry, considered the gold standard for COPD diagnosis, is ordered for patients who report COPD symptoms (ie, shortness of breath with exertion) or who have both COPD symptoms and reduced peak flow rates.

A systematic review and meta-analysis found that while the combination of questionnaires and peak flows was the more effective strategy overall, questionnaires alone were also valuable for identifying patients with possible COPD.¹³ Implementation of either screening method in primary care practices would be challenging. In a simulation study that applied chronic disease and preventive care guidelines to hypothetical patient panels, the time required for PCPs to provide guideline-recommended chronic and preventive care in addition to acute care far exceeded 8 hours per day, even in team-based settings.¹⁴ Overburdened PCPs are therefore unlikely to accept additional tasks like COPD case finding.

Why don’t patients report their pulmonary symptoms? Patients may not recognize the symptoms as evidence of COPD. Others may be afraid of a COPD diagnosis or the stigma that is associated with it.¹⁵ Perhaps they believe COPD treatment is ineffective because of lung damage from smoking. Some patients may not want to know if they have COPD, while others reduce activity levels to avoid symptoms.¹⁶

QUALITY IMPROVEMENT PROJECT

Given the high prevalence of COPD among veterans and the potential for underdiagnosis, VA Northeast Ohio Healthcare System (VANEOHS) internal medicine residents and faculty assessed the state of COPD diagnosis in its primary care clinic with a QI project in 2022. Patients in the clinic between August 1, 2015, and November 30, 2022, with an International Classification of Diseases-10 (ICD-10) COPD diagnosis code (J44) in the electronic health record were included. Of 157 included patients, 105 patients who had prior spirometry testing were excluded. Of the 52 patients with diagnosed COPD and no spirometry testing, 30 patients had computed tomography (CT) findings consistent with COPD (ie, airway thickening, emphysema, air trapping) that was performed for CT lung cancer screening (LCS).¹⁷ Twenty-three of these 30 patients were contacted by phone. All 23 were ever smokers and 13 reported COPD symptoms. The PCPs of the symptomatic patients were then contacted. Spirometry was ordered for all 13 patients and completed by 7. Three spirometry tests confirmed the COPD diagnosis. One PCP initiated inhaler therapy for a patient with newly diagnosed COPD.

All 11 PCPs of symptomatic patients were interviewed (many had > 1 symptomatic patient). They reported being unaware of patients’ COPD symptoms because the patients did not mention them, noting that screening for COPD was not a priority.

Role of Lung Cancer Screening

VA PCPs use electronic health record clinical reminders to track tests, consults, chronic disease education, cancer screenings, and routine health maintenance. A clinical reminder already exists (based on USPSTF recommendations) for LCS for patients aged 50 to 80 years who have a smoking history of 20 pack years. Patients who meet these criteria would also be considered high risk for COPD.

The VANEOHS QI project suggests that previously undiagnosed patients with findings of COPD on LCS may also have symptoms of COPD. Therefore, we wondered whether the LCS clinical reminder could serve a second purpose by prompting PCPs to ask veterans who meet LCS criteria about their COPD symptoms.

In 2022, about 13 million patients were eligible for LCS.¹⁸ Patients who qualify for LCS are at high risk for other cardiopulmonary disorders, such as COPD and coronary artery disease. Lung cancer is detected in only 1% of patients screened with CT at baseline. However, more often LCS yields evidence of additional cardiopulmonary disorders, such as emphysema or coronary artery calcifications. The International Early Lung Cancer Program (I-ELCAP) and the National Lung Cancer Screening Trial (NLST), which included > 79,000 patients, found evidence of emphysema on CT imaging in 24% and 31% of cases, respectively.^19,20 In both cohorts, > 80% of patients with emphysema on CT imaging had no prior history of COPD.

In a 2022 article summarizing the potential impact of CT LCS on COPD diagnosis, Mulshine et al suggest that detection of emphysema on CT LCS provides “earlier recognition for PCPs to identify patients who would benefit from detailed symptom screening to prompt spirometry for COPD detection” and additional motivation for tobacco cessation.²¹ The VANEOHS QI project was developed and implemented prior to I-ELCAP or NLST reporting results but reinforces the value of CT LCS for COPD diagnosis.

Early diagnosis of COPD remains challenging because PCPs do not ask, patients do not tell, and symptoms can easily be dismissed. However, earlier diagnosis of COPD in symptomatic patients improves outcomes.^3,4 To bridge this gap, VA PCPs and primary care patient aligned care teams (PACTs) need to commit to probing high-risk patients for COPD symptoms and ordering spirometry for those who are symptomatic. To accomplish this task, primary care teams need help.

The VANEOHS QI project confirmed that some patients with evidence of COPD on CT have symptoms of COPD that they did not share with their PCPs and suggests that LCS can be used as a dual action case finding method to screen both for lung cancer and COPD. We propose that patients who are eligible for LCS should also be probed for COPD symptoms at their clinic visits; for symptomatic patients, spirometry should be ordered, and COPD evidence-based management should be initiated when spirometry results are consistent with COPD. Annual probing for COPD symptoms could be considered in asymptomatic patients with ongoing tobacco use or emphysema on CT, since they may develop symptoms in the future. This new case-finding method bypasses the need for time-prohibitive questionnaires or peak flow measurements.

Future Opportunities

VA PCPs juggle many priorities and despite the simplicity of this new case finding COPD method, it may be unintentionally overlooked. PCPs often run out of time or may forget to ask patients about COPD symptoms when ordering LCS.

Future innovations to increase COPD diagnosis could include the creation of a yearly VA clinical reminder linked to the tobacco use reminder that has check boxes asking about symptoms of COPD in current and prior smokers. If patients have COPD symptoms, the reminder can prompt the ordering of spirometry. Similar reminders could be implemented to identify veterans with exposures to burn pits or other military environmental exposures who may have COPD symptoms. Another possible way to increase COPD diagnosis would be a partnership between primary care and the VA LCS program where patients receiving screening are asked about COPD symptoms during their LCS interviews and PACTs are alerted to order spirometry for symptomatic patients.

Elusive no longer! We can pull the veil back on COPD diagnosis and identify patients with possible COPD earlier in their course using their eligibility for LCS as a yearly reminder to probe them for symptoms. While not all patients who undergo LCS—even those with evidence of COPD on CT—will have COPD symptoms, symptoms may develop over time. LCS provides the possibility of 2 diagnoses from 1 test. This is an opportunity we cannot afford to miss.

Primary care practitioners (PCPs) in the US Department of Veterans Affairs (VA) provide care for patients with higher rates of many diseases—diabetes, heart disease, cancer, chronic obstructive pulmonary disease (COPD), and stroke—compared to the nonveteran population. ¹ Due to the medical complexities of these diseases, they are often misdiagnosed or not diagnosed at all.

COPD is hiding in plain sight, impacting quality of life and burdening US health care systems.² Research has yielded new treatments and evidence-based guidelines; however, COPD remains underdiagnosed. Only 13 million of the estimated 79 million US adults with COPD aged 20 to 79 years have been formally diagnosed.³ By the time patients are diagnosed, the disease is often advanced, and therapies are less effective. In 2 large studies of patients with COPD symptoms, later diagnosis was associated with worse outcomes.^4,5

Veterans have a higher prevalence of COPD (8%-19%) than nonveterans (6%), likely due to higher rates of smoking and service-related exposures, especially among veterans of post-9/11 conflicts.^6,7 Veterans do not always report symptoms and PCPs may not ask about symptoms, leading to underdiagnosis.⁸ The combination of high likelihood and underdetection of COPD presents a challenge and a target for VA quality improvement (QI).

The US Preventive Services Task Force (USPSTF) recommends against screening asymptomatic patients for COPD. However, both the USPSTF and the Global Initiative for Chronic Obstructive Lung Disease Report advocate for active case finding in primary care clinics to determine whether high-risk patients, such as smokers, experience COPD symptoms and warrant spirometry. ^9,10 To make early COPD diagnoses, clinicians may use questionnaires alone or in combination with handheld peak expiratory flow rate measurements.^11,12 Formal spirometry, considered the gold standard for COPD diagnosis, is ordered for patients who report COPD symptoms (ie, shortness of breath with exertion) or who have both COPD symptoms and reduced peak flow rates.

A systematic review and meta-analysis found that while the combination of questionnaires and peak flows was the more effective strategy overall, questionnaires alone were also valuable for identifying patients with possible COPD.¹³ Implementation of either screening method in primary care practices would be challenging. In a simulation study that applied chronic disease and preventive care guidelines to hypothetical patient panels, the time required for PCPs to provide guideline-recommended chronic and preventive care in addition to acute care far exceeded 8 hours per day, even in team-based settings.¹⁴ Overburdened PCPs are therefore unlikely to accept additional tasks like COPD case finding.

Why don’t patients report their pulmonary symptoms? Patients may not recognize the symptoms as evidence of COPD. Others may be afraid of a COPD diagnosis or the stigma that is associated with it.¹⁵ Perhaps they believe COPD treatment is ineffective because of lung damage from smoking. Some patients may not want to know if they have COPD, while others reduce activity levels to avoid symptoms.¹⁶

QUALITY IMPROVEMENT PROJECT

Given the high prevalence of COPD among veterans and the potential for underdiagnosis, VA Northeast Ohio Healthcare System (VANEOHS) internal medicine residents and faculty assessed the state of COPD diagnosis in its primary care clinic with a QI project in 2022. Patients in the clinic between August 1, 2015, and November 30, 2022, with an International Classification of Diseases-10 (ICD-10) COPD diagnosis code (J44) in the electronic health record were included. Of 157 included patients, 105 patients who had prior spirometry testing were excluded. Of the 52 patients with diagnosed COPD and no spirometry testing, 30 patients had computed tomography (CT) findings consistent with COPD (ie, airway thickening, emphysema, air trapping) that was performed for CT lung cancer screening (LCS).¹⁷ Twenty-three of these 30 patients were contacted by phone. All 23 were ever smokers and 13 reported COPD symptoms. The PCPs of the symptomatic patients were then contacted. Spirometry was ordered for all 13 patients and completed by 7. Three spirometry tests confirmed the COPD diagnosis. One PCP initiated inhaler therapy for a patient with newly diagnosed COPD.

All 11 PCPs of symptomatic patients were interviewed (many had > 1 symptomatic patient). They reported being unaware of patients’ COPD symptoms because the patients did not mention them, noting that screening for COPD was not a priority.

Role of Lung Cancer Screening

VA PCPs use electronic health record clinical reminders to track tests, consults, chronic disease education, cancer screenings, and routine health maintenance. A clinical reminder already exists (based on USPSTF recommendations) for LCS for patients aged 50 to 80 years who have a smoking history of 20 pack years. Patients who meet these criteria would also be considered high risk for COPD.

The VANEOHS QI project suggests that previously undiagnosed patients with findings of COPD on LCS may also have symptoms of COPD. Therefore, we wondered whether the LCS clinical reminder could serve a second purpose by prompting PCPs to ask veterans who meet LCS criteria about their COPD symptoms.

In 2022, about 13 million patients were eligible for LCS.¹⁸ Patients who qualify for LCS are at high risk for other cardiopulmonary disorders, such as COPD and coronary artery disease. Lung cancer is detected in only 1% of patients screened with CT at baseline. However, more often LCS yields evidence of additional cardiopulmonary disorders, such as emphysema or coronary artery calcifications. The International Early Lung Cancer Program (I-ELCAP) and the National Lung Cancer Screening Trial (NLST), which included > 79,000 patients, found evidence of emphysema on CT imaging in 24% and 31% of cases, respectively.^19,20 In both cohorts, > 80% of patients with emphysema on CT imaging had no prior history of COPD.

In a 2022 article summarizing the potential impact of CT LCS on COPD diagnosis, Mulshine et al suggest that detection of emphysema on CT LCS provides “earlier recognition for PCPs to identify patients who would benefit from detailed symptom screening to prompt spirometry for COPD detection” and additional motivation for tobacco cessation.²¹ The VANEOHS QI project was developed and implemented prior to I-ELCAP or NLST reporting results but reinforces the value of CT LCS for COPD diagnosis.

Early diagnosis of COPD remains challenging because PCPs do not ask, patients do not tell, and symptoms can easily be dismissed. However, earlier diagnosis of COPD in symptomatic patients improves outcomes.^3,4 To bridge this gap, VA PCPs and primary care patient aligned care teams (PACTs) need to commit to probing high-risk patients for COPD symptoms and ordering spirometry for those who are symptomatic. To accomplish this task, primary care teams need help.

The VANEOHS QI project confirmed that some patients with evidence of COPD on CT have symptoms of COPD that they did not share with their PCPs and suggests that LCS can be used as a dual action case finding method to screen both for lung cancer and COPD. We propose that patients who are eligible for LCS should also be probed for COPD symptoms at their clinic visits; for symptomatic patients, spirometry should be ordered, and COPD evidence-based management should be initiated when spirometry results are consistent with COPD. Annual probing for COPD symptoms could be considered in asymptomatic patients with ongoing tobacco use or emphysema on CT, since they may develop symptoms in the future. This new case-finding method bypasses the need for time-prohibitive questionnaires or peak flow measurements.

Future Opportunities

VA PCPs juggle many priorities and despite the simplicity of this new case finding COPD method, it may be unintentionally overlooked. PCPs often run out of time or may forget to ask patients about COPD symptoms when ordering LCS.

Future innovations to increase COPD diagnosis could include the creation of a yearly VA clinical reminder linked to the tobacco use reminder that has check boxes asking about symptoms of COPD in current and prior smokers. If patients have COPD symptoms, the reminder can prompt the ordering of spirometry. Similar reminders could be implemented to identify veterans with exposures to burn pits or other military environmental exposures who may have COPD symptoms. Another possible way to increase COPD diagnosis would be a partnership between primary care and the VA LCS program where patients receiving screening are asked about COPD symptoms during their LCS interviews and PACTs are alerted to order spirometry for symptomatic patients.

Elusive no longer! We can pull the veil back on COPD diagnosis and identify patients with possible COPD earlier in their course using their eligibility for LCS as a yearly reminder to probe them for symptoms. While not all patients who undergo LCS—even those with evidence of COPD on CT—will have COPD symptoms, symptoms may develop over time. LCS provides the possibility of 2 diagnoses from 1 test. This is an opportunity we cannot afford to miss.

Primary care practitioners (PCPs) in the US Department of Veterans Affairs (VA) provide care for patients with higher rates of many diseases—diabetes, heart disease, cancer, chronic obstructive pulmonary disease (COPD), and stroke—compared to the nonveteran population. ¹ Due to the medical complexities of these diseases, they are often misdiagnosed or not diagnosed at all.

COPD is hiding in plain sight, impacting quality of life and burdening US health care systems.² Research has yielded new treatments and evidence-based guidelines; however, COPD remains underdiagnosed. Only 13 million of the estimated 79 million US adults with COPD aged 20 to 79 years have been formally diagnosed.³ By the time patients are diagnosed, the disease is often advanced, and therapies are less effective. In 2 large studies of patients with COPD symptoms, later diagnosis was associated with worse outcomes.^4,5

Veterans have a higher prevalence of COPD (8%-19%) than nonveterans (6%), likely due to higher rates of smoking and service-related exposures, especially among veterans of post-9/11 conflicts.^6,7 Veterans do not always report symptoms and PCPs may not ask about symptoms, leading to underdiagnosis.⁸ The combination of high likelihood and underdetection of COPD presents a challenge and a target for VA quality improvement (QI).

The US Preventive Services Task Force (USPSTF) recommends against screening asymptomatic patients for COPD. However, both the USPSTF and the Global Initiative for Chronic Obstructive Lung Disease Report advocate for active case finding in primary care clinics to determine whether high-risk patients, such as smokers, experience COPD symptoms and warrant spirometry. ^9,10 To make early COPD diagnoses, clinicians may use questionnaires alone or in combination with handheld peak expiratory flow rate measurements.^11,12 Formal spirometry, considered the gold standard for COPD diagnosis, is ordered for patients who report COPD symptoms (ie, shortness of breath with exertion) or who have both COPD symptoms and reduced peak flow rates.

A systematic review and meta-analysis found that while the combination of questionnaires and peak flows was the more effective strategy overall, questionnaires alone were also valuable for identifying patients with possible COPD.¹³ Implementation of either screening method in primary care practices would be challenging. In a simulation study that applied chronic disease and preventive care guidelines to hypothetical patient panels, the time required for PCPs to provide guideline-recommended chronic and preventive care in addition to acute care far exceeded 8 hours per day, even in team-based settings.¹⁴ Overburdened PCPs are therefore unlikely to accept additional tasks like COPD case finding.

Why don’t patients report their pulmonary symptoms? Patients may not recognize the symptoms as evidence of COPD. Others may be afraid of a COPD diagnosis or the stigma that is associated with it.¹⁵ Perhaps they believe COPD treatment is ineffective because of lung damage from smoking. Some patients may not want to know if they have COPD, while others reduce activity levels to avoid symptoms.¹⁶

QUALITY IMPROVEMENT PROJECT

Given the high prevalence of COPD among veterans and the potential for underdiagnosis, VA Northeast Ohio Healthcare System (VANEOHS) internal medicine residents and faculty assessed the state of COPD diagnosis in its primary care clinic with a QI project in 2022. Patients in the clinic between August 1, 2015, and November 30, 2022, with an International Classification of Diseases-10 (ICD-10) COPD diagnosis code (J44) in the electronic health record were included. Of 157 included patients, 105 patients who had prior spirometry testing were excluded. Of the 52 patients with diagnosed COPD and no spirometry testing, 30 patients had computed tomography (CT) findings consistent with COPD (ie, airway thickening, emphysema, air trapping) that was performed for CT lung cancer screening (LCS).¹⁷ Twenty-three of these 30 patients were contacted by phone. All 23 were ever smokers and 13 reported COPD symptoms. The PCPs of the symptomatic patients were then contacted. Spirometry was ordered for all 13 patients and completed by 7. Three spirometry tests confirmed the COPD diagnosis. One PCP initiated inhaler therapy for a patient with newly diagnosed COPD.

All 11 PCPs of symptomatic patients were interviewed (many had > 1 symptomatic patient). They reported being unaware of patients’ COPD symptoms because the patients did not mention them, noting that screening for COPD was not a priority.

Role of Lung Cancer Screening

VA PCPs use electronic health record clinical reminders to track tests, consults, chronic disease education, cancer screenings, and routine health maintenance. A clinical reminder already exists (based on USPSTF recommendations) for LCS for patients aged 50 to 80 years who have a smoking history of 20 pack years. Patients who meet these criteria would also be considered high risk for COPD.

The VANEOHS QI project suggests that previously undiagnosed patients with findings of COPD on LCS may also have symptoms of COPD. Therefore, we wondered whether the LCS clinical reminder could serve a second purpose by prompting PCPs to ask veterans who meet LCS criteria about their COPD symptoms.

In 2022, about 13 million patients were eligible for LCS.¹⁸ Patients who qualify for LCS are at high risk for other cardiopulmonary disorders, such as COPD and coronary artery disease. Lung cancer is detected in only 1% of patients screened with CT at baseline. However, more often LCS yields evidence of additional cardiopulmonary disorders, such as emphysema or coronary artery calcifications. The International Early Lung Cancer Program (I-ELCAP) and the National Lung Cancer Screening Trial (NLST), which included > 79,000 patients, found evidence of emphysema on CT imaging in 24% and 31% of cases, respectively.^19,20 In both cohorts, > 80% of patients with emphysema on CT imaging had no prior history of COPD.

In a 2022 article summarizing the potential impact of CT LCS on COPD diagnosis, Mulshine et al suggest that detection of emphysema on CT LCS provides “earlier recognition for PCPs to identify patients who would benefit from detailed symptom screening to prompt spirometry for COPD detection” and additional motivation for tobacco cessation.²¹ The VANEOHS QI project was developed and implemented prior to I-ELCAP or NLST reporting results but reinforces the value of CT LCS for COPD diagnosis.

Early diagnosis of COPD remains challenging because PCPs do not ask, patients do not tell, and symptoms can easily be dismissed. However, earlier diagnosis of COPD in symptomatic patients improves outcomes.^3,4 To bridge this gap, VA PCPs and primary care patient aligned care teams (PACTs) need to commit to probing high-risk patients for COPD symptoms and ordering spirometry for those who are symptomatic. To accomplish this task, primary care teams need help.

The VANEOHS QI project confirmed that some patients with evidence of COPD on CT have symptoms of COPD that they did not share with their PCPs and suggests that LCS can be used as a dual action case finding method to screen both for lung cancer and COPD. We propose that patients who are eligible for LCS should also be probed for COPD symptoms at their clinic visits; for symptomatic patients, spirometry should be ordered, and COPD evidence-based management should be initiated when spirometry results are consistent with COPD. Annual probing for COPD symptoms could be considered in asymptomatic patients with ongoing tobacco use or emphysema on CT, since they may develop symptoms in the future. This new case-finding method bypasses the need for time-prohibitive questionnaires or peak flow measurements.

Future Opportunities

VA PCPs juggle many priorities and despite the simplicity of this new case finding COPD method, it may be unintentionally overlooked. PCPs often run out of time or may forget to ask patients about COPD symptoms when ordering LCS.

Future innovations to increase COPD diagnosis could include the creation of a yearly VA clinical reminder linked to the tobacco use reminder that has check boxes asking about symptoms of COPD in current and prior smokers. If patients have COPD symptoms, the reminder can prompt the ordering of spirometry. Similar reminders could be implemented to identify veterans with exposures to burn pits or other military environmental exposures who may have COPD symptoms. Another possible way to increase COPD diagnosis would be a partnership between primary care and the VA LCS program where patients receiving screening are asked about COPD symptoms during their LCS interviews and PACTs are alerted to order spirometry for symptomatic patients.

Elusive no longer! We can pull the veil back on COPD diagnosis and identify patients with possible COPD earlier in their course using their eligibility for LCS as a yearly reminder to probe them for symptoms. While not all patients who undergo LCS—even those with evidence of COPD on CT—will have COPD symptoms, symptoms may develop over time. LCS provides the possibility of 2 diagnoses from 1 test. This is an opportunity we cannot afford to miss.

The landmark Crossing the Quality Chasm report from the National Academy of Medicine identified patient- centered care as essential to health care quality. The report defines patientcentered care as “respectful of and responsive to individual patient preferences, needs, and values.”¹ Many health care systems, including the Veterans Health Administration, are transforming to a patient-centered model of care.² The US Department of Veterans Affairs (VA) Whole Health System of Care initiative is a system-wide, cultural transformation. Within whole health, what matters most to the patient—including their preferences, needs, and values—is foundational to health care and meant to be essential in every clinical encounter. Whole health implementation includes a progressive rollout with health care practitioner (HCP) trainings across the VA.²

Shared decision-making (SDM) is a different but aligned patient-centered care concept. SDM is a process through which a decision or care plan, based on patients’ preferences, needs, and values, is made or developed.^3-5 SDM is ideal in situations with equipoise (decisions with equivalent choices), individualized risks, and/or greater uncertainty of the net benefit, such as with lung cancer screening (LCS).³ SDM for LCS is required by the US Centers for Medicare and Medicaid Services and has been adopted by many US health care systems, including the VA.^6,7 Early detection of lung cancer can reduce death by 20% at the population level.⁸ However, at the patient level there is wide variation in the risk of developing lung cancer and a range of potential harms.⁸ LCS follow-up procedures may be more invasive than with other cancer screenings. Thus, there is concern about the risk of false-positive results leading to unnecessary care or complications.⁸ Given this balance between benefit and harm and the differing patient value on the trade-offs of LCS, an individualized, patient-centered approach is essential when deciding whether LCS is the right choice for a specific patient.

Despite the importance of LCS SDM, observational studies have shown poor implementation in clinical encounters.^9,10 HCP barriers include competing demands, limited time, lack of familiarity with and training in SDM, and beliefs biasing screening over no screening.^11-13 Additionally, HCPs may assume that patients want them to make the decision. However, research has shown that patients actually want to be more involved in their health care decisions.¹⁴ One suggested strategy to overcome these barriers is aligning SDM for LCS within an organization’s broader patient-centered initiatives.¹⁵

This project sought to align the need for SDM for LCS and the broader VA whole health initiative as part of a multilevel strategy to implement SDM for LCS across Veterans Integrated Service Network (VISN) 1.¹⁶

This article addresses HCP-level barriers. HCPs targeted are those typically involved in LCS. The VA utilizes LCS coordinators (LCSCs) in both centralized or consult models (in which LCSCs are involved in all aspects of screening) and hybrid models (in which primary care practitioners and LCSCs are both engaged in LCS tasks). The goal of this program was to generate areas of conceptual alignment between SDM and whole health as a first step in integrating these VA initiatives. This work was conducted as a foundation for an SDM for lung cancer HCP training and consultation initiative.

ALIGNMENT PROCESS

We reviewed relevant literature and resources for SDM and whole health. In reviewing the SDM literature, we included a sample of the most widely cited literature on the topic, and focused primarily on the systematic review by Bomhof-Roordink et al.^4,5,17,18 This review provided a synthesis of SDM elements across SDM models and identified 53 different elements clustered into 24 components.⁴ The most common components were present in at least half of all SDM published models, including: make the decision, patient preferences, tailor information, deliberate, create choice awareness, and learn about the patient. Bomhof-Roordink et al provided the guiding framework for this conceptualization of SDM because that study included the available recent published SDM models.⁴

Second, published literature on VA whole health along with supplemental promotional and training materials were reviewed. The whole health materials included 2 sets of training slides developed for VA HCPs (available to VA employees): Implementing Whole Health in Clinical Care, which is focused on HCPs’ work with patients, and Whole Health for You and Me, which is about HCPs’ personal well-being.¹⁹ We also reviewed a publication describing the history of whole health and patient-facing online whole health tools.^2,19

Each document was reviewed for key elements related to SDM, patient-centered care, and whole health. Using the 53 elements identified by Bomhof-Roordink et al, we reviewed and compared each element to the whole health materials to create the integrated model of SDM and whole health. We iteratively discussed and organized the elements until we reached consensus.

SDM and Whole Health Alignment

We created an integrated model of SDM for LCS within the context of the VA whole health initiative. This integrated model is directed at HCPs who would likely engage patients in discussions of LCS, including primary care practitioners and nurse coordinators. The model includes 3 steps for HCPs to follow that align SDM within whole health: (1) frame the conversation and partner with the patient; (2) share clinical perspective and elicit patient values; and (3) deliberate and decide together. For each step, the SDM elements, whole health elements, and integration of SDM and whole health are provided. Table 1 provides an overview of the similarities and differences between SDM and whole health. Example phrases that merge SDM and whole health for HCPs to use in patient conversations about LCS are included in Table 2.

STEP 1. FRAME THE CONVERSATION AND PARTNER WITH THE PATIENT

Shared decision-making. Traditional SDM literature includes an initial step of letting patients know that there is a choice to be made between ≥ 2 clinical options.⁴ Ancillary elements of this first step include asking patients their preferences about the degree to which they want to be involved in SDM and about how they like to receive information (eg, verbal, written, video). These steps open the SDM conversation and ensure the patient and HCP are on the same page before moving forward. For example, the US Agency for Healthcare Research and Quality SHARE model’s first step is for HCPs to communicate that choices exist and to invite the patient to be involved in decisions.²⁰ Similarly, Elwyn’s 3-step SDM model begins with establishing that a choice exists and inviting patient input on making that choice.¹⁷

Whole health. Patients are encouraged to play an active role in their health care. Through whole health programs such as Taking Charge of My Life and Health, patients explore their values and set self-care goals.²¹ HCP whole health trainings teach and reinforce communication skills, including SDM, listening skills, and motivational interviewing.¹⁹

Shared decision-making/whole health integration. SDM and whole health both prioritize respect, compassion, and patients’ expertise. They focus on the patient-HCP relationship with an emphasis on fostering egalitarian interactions. HCPs frame the SDM conversation and partner with the patient so they know what to expect and who will be involved. This conversation is framed from the outset as a collaborative discussion. HCPs empower the patient to play an active role in decision-making and help them understand why their engagement is critical.

STEP 2. SHARE CLINICAL PERSPECTIVE AND ELICIT PATIENT VALUES

Shared decision-making. HCPs share clinical perspective on LCS tailored to individual patients while explicitly inviting the patient to share their preferences and values when thinking about whether to undergo LCS. HCPs give a balanced description of LCS, including the benefits and harms, tailored to the patient’s unique information needs and questions. Sharing clinical perspective also includes describing treatment options, the most common element across SDM models.⁴ Decision aids, which provide unbiased information and include a values clarification exercise, may be helpful in sharing clinical perspectives and clarifying patient values related to the trade-offs of LCS.²² For example, the VA National Center for Health Promotion and Disease Prevention developed a LCS decision aid to be used for SDM for LCS.

Whole health. The conversation shifts from “What is the matter with you?” to “What matters to you?” starting with the patient’s goals and priorities rather than disease prevention, diagnosis, and treatment.² Several whole health tools exist, including the Personal Health Inventory, used to identify what matters most to patients and understand their current well-being and self-care.²³ Using the inventory, the patient and their health care team develop the patient’s personal health plan.²⁴ Additionally, whole health trains HCPs to reflect on their own attitudes and biases when providing clinical care.

Shared decision-making/whole health integration. The LCS conversation can build on other whole health-related conversations with a HCP or other team members. HCPs can reference the patient’s personal health plan for documentation of the patient’s preferences, values, and goals in the electronic medical record. During this process, HCPs can give space for patients to discuss factors in their life and experiences that impact their perspective and decision-making. For example, patient concerns could be explored here, including fear of a cancer diagnosis, stigma around smoking, and fears around the screening and/or treatment process. HCPs may ask, “What matters most to you when making this decision?” Finally, by sharing clinical information, HCPs will focus on patient values to help overcome their own biases toward a desire for LCS. HCPs, similar to the rest of the US public, tend to hold highly favorable attitudes toward cancer screening as well as misconceptions about the magnitude of benefits from screening.¹³

STEP 3. DELIBERATE AND DECIDE TOGETHER

Shared decision-making. Decision-making is almost always considered the last SDM step.⁴ In the final step, the patient and HCP discuss the options (ie, to screen or not to screen) considering the patient’s values and preferences, and patients decide with their HCP whether they will undergo LCS. Patients may decide they need more time to think about these options. As part of deliberation, HCPs assess what other information patients may need to arrive at a decision. Family members, friends, or peers may be included in making the final decision.

Whole health. In Whole health, decisions also may include the entire health care team and other individuals important to the patient (eg, family, friends). Integration across different health care settings is also considered a key whole health element. Finally, whole health focuses on long-term relationships with patients; thus, the LCS SDM process is situated within longer term relationship building and patient empowerment, both of which will facilitate partnering with the patient in future conversations about other decisions.

Shared decision-making/whole health integration. Both SDM and whole health emphasize partnership with the patient in making a final decision. There is also focus on decision-making as an ongoing process. Deciding whether LCS is the best choice might include naming and addressing emotions, voicing questions not raised, and exploring whether screening fits the patient’s goals, values, and life context. HCPs may give guidance, but patients retain the authority to make decisions. The goal is to empower patients to know that the only right decision is the one right for them and they will be supported.

Limitations

This article describes a VA practice program and was not a formal research study. Further work is needed to evaluate the presented strategies. Additionally, we did not conduct a systematic literature review and thus elements of SDM and whole health may not be exhaustive.

CONCLUSIONS

This article describes the alignment of 2 distinct VA initiatives, whole health and SDM for LCS. The goal was to reduce known barriers to SDM, such as competing demands, limited time, and lack of familiarity with and training in SDM.^11-13 These concepts are well aligned. This integrated model is the first step in informing the development of a HCP training program and materials as part of a multilevel strategy that our team is using to implement SDM for LCS in VISN 1.16 The final training and materials resulting from this work were delivered to LCSCs in 3 ways: (1) a series of 3 interactive group training sessions, including didactic elements, role play, and time for open discussion; (2) 1-on-1 academic detailing; and (3) educational handouts. In academic detailing, a member of the research team trained in academic detailing met virtually with each nurse coordinator, identified that individual’s barriers to SDM, and used the training materials to highlight messages to overcome those barriers; follow-up calls provided a forum for discussing progress and overcoming additional challenges. Although this article focused specifically on whole health and SDM, the conceptual alignment process strategy can be applied to other implementations of multiple initiatives.

The landmark Crossing the Quality Chasm report from the National Academy of Medicine identified patient- centered care as essential to health care quality. The report defines patientcentered care as “respectful of and responsive to individual patient preferences, needs, and values.”¹ Many health care systems, including the Veterans Health Administration, are transforming to a patient-centered model of care.² The US Department of Veterans Affairs (VA) Whole Health System of Care initiative is a system-wide, cultural transformation. Within whole health, what matters most to the patient—including their preferences, needs, and values—is foundational to health care and meant to be essential in every clinical encounter. Whole health implementation includes a progressive rollout with health care practitioner (HCP) trainings across the VA.²

Shared decision-making (SDM) is a different but aligned patient-centered care concept. SDM is a process through which a decision or care plan, based on patients’ preferences, needs, and values, is made or developed.^3-5 SDM is ideal in situations with equipoise (decisions with equivalent choices), individualized risks, and/or greater uncertainty of the net benefit, such as with lung cancer screening (LCS).³ SDM for LCS is required by the US Centers for Medicare and Medicaid Services and has been adopted by many US health care systems, including the VA.^6,7 Early detection of lung cancer can reduce death by 20% at the population level.⁸ However, at the patient level there is wide variation in the risk of developing lung cancer and a range of potential harms.⁸ LCS follow-up procedures may be more invasive than with other cancer screenings. Thus, there is concern about the risk of false-positive results leading to unnecessary care or complications.⁸ Given this balance between benefit and harm and the differing patient value on the trade-offs of LCS, an individualized, patient-centered approach is essential when deciding whether LCS is the right choice for a specific patient.

Despite the importance of LCS SDM, observational studies have shown poor implementation in clinical encounters.^9,10 HCP barriers include competing demands, limited time, lack of familiarity with and training in SDM, and beliefs biasing screening over no screening.^11-13 Additionally, HCPs may assume that patients want them to make the decision. However, research has shown that patients actually want to be more involved in their health care decisions.¹⁴ One suggested strategy to overcome these barriers is aligning SDM for LCS within an organization’s broader patient-centered initiatives.¹⁵

This project sought to align the need for SDM for LCS and the broader VA whole health initiative as part of a multilevel strategy to implement SDM for LCS across Veterans Integrated Service Network (VISN) 1.¹⁶

This article addresses HCP-level barriers. HCPs targeted are those typically involved in LCS. The VA utilizes LCS coordinators (LCSCs) in both centralized or consult models (in which LCSCs are involved in all aspects of screening) and hybrid models (in which primary care practitioners and LCSCs are both engaged in LCS tasks). The goal of this program was to generate areas of conceptual alignment between SDM and whole health as a first step in integrating these VA initiatives. This work was conducted as a foundation for an SDM for lung cancer HCP training and consultation initiative.

ALIGNMENT PROCESS

We reviewed relevant literature and resources for SDM and whole health. In reviewing the SDM literature, we included a sample of the most widely cited literature on the topic, and focused primarily on the systematic review by Bomhof-Roordink et al.^4,5,17,18 This review provided a synthesis of SDM elements across SDM models and identified 53 different elements clustered into 24 components.⁴ The most common components were present in at least half of all SDM published models, including: make the decision, patient preferences, tailor information, deliberate, create choice awareness, and learn about the patient. Bomhof-Roordink et al provided the guiding framework for this conceptualization of SDM because that study included the available recent published SDM models.⁴

Second, published literature on VA whole health along with supplemental promotional and training materials were reviewed. The whole health materials included 2 sets of training slides developed for VA HCPs (available to VA employees): Implementing Whole Health in Clinical Care, which is focused on HCPs’ work with patients, and Whole Health for You and Me, which is about HCPs’ personal well-being.¹⁹ We also reviewed a publication describing the history of whole health and patient-facing online whole health tools.^2,19

Each document was reviewed for key elements related to SDM, patient-centered care, and whole health. Using the 53 elements identified by Bomhof-Roordink et al, we reviewed and compared each element to the whole health materials to create the integrated model of SDM and whole health. We iteratively discussed and organized the elements until we reached consensus.

SDM and Whole Health Alignment

We created an integrated model of SDM for LCS within the context of the VA whole health initiative. This integrated model is directed at HCPs who would likely engage patients in discussions of LCS, including primary care practitioners and nurse coordinators. The model includes 3 steps for HCPs to follow that align SDM within whole health: (1) frame the conversation and partner with the patient; (2) share clinical perspective and elicit patient values; and (3) deliberate and decide together. For each step, the SDM elements, whole health elements, and integration of SDM and whole health are provided. Table 1 provides an overview of the similarities and differences between SDM and whole health. Example phrases that merge SDM and whole health for HCPs to use in patient conversations about LCS are included in Table 2.

STEP 1. FRAME THE CONVERSATION AND PARTNER WITH THE PATIENT

Shared decision-making. Traditional SDM literature includes an initial step of letting patients know that there is a choice to be made between ≥ 2 clinical options.⁴ Ancillary elements of this first step include asking patients their preferences about the degree to which they want to be involved in SDM and about how they like to receive information (eg, verbal, written, video). These steps open the SDM conversation and ensure the patient and HCP are on the same page before moving forward. For example, the US Agency for Healthcare Research and Quality SHARE model’s first step is for HCPs to communicate that choices exist and to invite the patient to be involved in decisions.²⁰ Similarly, Elwyn’s 3-step SDM model begins with establishing that a choice exists and inviting patient input on making that choice.¹⁷

Whole health. Patients are encouraged to play an active role in their health care. Through whole health programs such as Taking Charge of My Life and Health, patients explore their values and set self-care goals.²¹ HCP whole health trainings teach and reinforce communication skills, including SDM, listening skills, and motivational interviewing.¹⁹

Shared decision-making/whole health integration. SDM and whole health both prioritize respect, compassion, and patients’ expertise. They focus on the patient-HCP relationship with an emphasis on fostering egalitarian interactions. HCPs frame the SDM conversation and partner with the patient so they know what to expect and who will be involved. This conversation is framed from the outset as a collaborative discussion. HCPs empower the patient to play an active role in decision-making and help them understand why their engagement is critical.

STEP 2. SHARE CLINICAL PERSPECTIVE AND ELICIT PATIENT VALUES

Shared decision-making. HCPs share clinical perspective on LCS tailored to individual patients while explicitly inviting the patient to share their preferences and values when thinking about whether to undergo LCS. HCPs give a balanced description of LCS, including the benefits and harms, tailored to the patient’s unique information needs and questions. Sharing clinical perspective also includes describing treatment options, the most common element across SDM models.⁴ Decision aids, which provide unbiased information and include a values clarification exercise, may be helpful in sharing clinical perspectives and clarifying patient values related to the trade-offs of LCS.²² For example, the VA National Center for Health Promotion and Disease Prevention developed a LCS decision aid to be used for SDM for LCS.

Whole health. The conversation shifts from “What is the matter with you?” to “What matters to you?” starting with the patient’s goals and priorities rather than disease prevention, diagnosis, and treatment.² Several whole health tools exist, including the Personal Health Inventory, used to identify what matters most to patients and understand their current well-being and self-care.²³ Using the inventory, the patient and their health care team develop the patient’s personal health plan.²⁴ Additionally, whole health trains HCPs to reflect on their own attitudes and biases when providing clinical care.

Shared decision-making/whole health integration. The LCS conversation can build on other whole health-related conversations with a HCP or other team members. HCPs can reference the patient’s personal health plan for documentation of the patient’s preferences, values, and goals in the electronic medical record. During this process, HCPs can give space for patients to discuss factors in their life and experiences that impact their perspective and decision-making. For example, patient concerns could be explored here, including fear of a cancer diagnosis, stigma around smoking, and fears around the screening and/or treatment process. HCPs may ask, “What matters most to you when making this decision?” Finally, by sharing clinical information, HCPs will focus on patient values to help overcome their own biases toward a desire for LCS. HCPs, similar to the rest of the US public, tend to hold highly favorable attitudes toward cancer screening as well as misconceptions about the magnitude of benefits from screening.¹³

STEP 3. DELIBERATE AND DECIDE TOGETHER

Shared decision-making. Decision-making is almost always considered the last SDM step.⁴ In the final step, the patient and HCP discuss the options (ie, to screen or not to screen) considering the patient’s values and preferences, and patients decide with their HCP whether they will undergo LCS. Patients may decide they need more time to think about these options. As part of deliberation, HCPs assess what other information patients may need to arrive at a decision. Family members, friends, or peers may be included in making the final decision.

Whole health. In Whole health, decisions also may include the entire health care team and other individuals important to the patient (eg, family, friends). Integration across different health care settings is also considered a key whole health element. Finally, whole health focuses on long-term relationships with patients; thus, the LCS SDM process is situated within longer term relationship building and patient empowerment, both of which will facilitate partnering with the patient in future conversations about other decisions.

Shared decision-making/whole health integration. Both SDM and whole health emphasize partnership with the patient in making a final decision. There is also focus on decision-making as an ongoing process. Deciding whether LCS is the best choice might include naming and addressing emotions, voicing questions not raised, and exploring whether screening fits the patient’s goals, values, and life context. HCPs may give guidance, but patients retain the authority to make decisions. The goal is to empower patients to know that the only right decision is the one right for them and they will be supported.

Limitations

This article describes a VA practice program and was not a formal research study. Further work is needed to evaluate the presented strategies. Additionally, we did not conduct a systematic literature review and thus elements of SDM and whole health may not be exhaustive.

CONCLUSIONS

This article describes the alignment of 2 distinct VA initiatives, whole health and SDM for LCS. The goal was to reduce known barriers to SDM, such as competing demands, limited time, and lack of familiarity with and training in SDM.^11-13 These concepts are well aligned. This integrated model is the first step in informing the development of a HCP training program and materials as part of a multilevel strategy that our team is using to implement SDM for LCS in VISN 1.16 The final training and materials resulting from this work were delivered to LCSCs in 3 ways: (1) a series of 3 interactive group training sessions, including didactic elements, role play, and time for open discussion; (2) 1-on-1 academic detailing; and (3) educational handouts. In academic detailing, a member of the research team trained in academic detailing met virtually with each nurse coordinator, identified that individual’s barriers to SDM, and used the training materials to highlight messages to overcome those barriers; follow-up calls provided a forum for discussing progress and overcoming additional challenges. Although this article focused specifically on whole health and SDM, the conceptual alignment process strategy can be applied to other implementations of multiple initiatives.

The landmark Crossing the Quality Chasm report from the National Academy of Medicine identified patient- centered care as essential to health care quality. The report defines patientcentered care as “respectful of and responsive to individual patient preferences, needs, and values.”¹ Many health care systems, including the Veterans Health Administration, are transforming to a patient-centered model of care.² The US Department of Veterans Affairs (VA) Whole Health System of Care initiative is a system-wide, cultural transformation. Within whole health, what matters most to the patient—including their preferences, needs, and values—is foundational to health care and meant to be essential in every clinical encounter. Whole health implementation includes a progressive rollout with health care practitioner (HCP) trainings across the VA.²

Shared decision-making (SDM) is a different but aligned patient-centered care concept. SDM is a process through which a decision or care plan, based on patients’ preferences, needs, and values, is made or developed.^3-5 SDM is ideal in situations with equipoise (decisions with equivalent choices), individualized risks, and/or greater uncertainty of the net benefit, such as with lung cancer screening (LCS).³ SDM for LCS is required by the US Centers for Medicare and Medicaid Services and has been adopted by many US health care systems, including the VA.^6,7 Early detection of lung cancer can reduce death by 20% at the population level.⁸ However, at the patient level there is wide variation in the risk of developing lung cancer and a range of potential harms.⁸ LCS follow-up procedures may be more invasive than with other cancer screenings. Thus, there is concern about the risk of false-positive results leading to unnecessary care or complications.⁸ Given this balance between benefit and harm and the differing patient value on the trade-offs of LCS, an individualized, patient-centered approach is essential when deciding whether LCS is the right choice for a specific patient.

Despite the importance of LCS SDM, observational studies have shown poor implementation in clinical encounters.^9,10 HCP barriers include competing demands, limited time, lack of familiarity with and training in SDM, and beliefs biasing screening over no screening.^11-13 Additionally, HCPs may assume that patients want them to make the decision. However, research has shown that patients actually want to be more involved in their health care decisions.¹⁴ One suggested strategy to overcome these barriers is aligning SDM for LCS within an organization’s broader patient-centered initiatives.¹⁵

This project sought to align the need for SDM for LCS and the broader VA whole health initiative as part of a multilevel strategy to implement SDM for LCS across Veterans Integrated Service Network (VISN) 1.¹⁶

This article addresses HCP-level barriers. HCPs targeted are those typically involved in LCS. The VA utilizes LCS coordinators (LCSCs) in both centralized or consult models (in which LCSCs are involved in all aspects of screening) and hybrid models (in which primary care practitioners and LCSCs are both engaged in LCS tasks). The goal of this program was to generate areas of conceptual alignment between SDM and whole health as a first step in integrating these VA initiatives. This work was conducted as a foundation for an SDM for lung cancer HCP training and consultation initiative.

ALIGNMENT PROCESS

We reviewed relevant literature and resources for SDM and whole health. In reviewing the SDM literature, we included a sample of the most widely cited literature on the topic, and focused primarily on the systematic review by Bomhof-Roordink et al.^4,5,17,18 This review provided a synthesis of SDM elements across SDM models and identified 53 different elements clustered into 24 components.⁴ The most common components were present in at least half of all SDM published models, including: make the decision, patient preferences, tailor information, deliberate, create choice awareness, and learn about the patient. Bomhof-Roordink et al provided the guiding framework for this conceptualization of SDM because that study included the available recent published SDM models.⁴

Second, published literature on VA whole health along with supplemental promotional and training materials were reviewed. The whole health materials included 2 sets of training slides developed for VA HCPs (available to VA employees): Implementing Whole Health in Clinical Care, which is focused on HCPs’ work with patients, and Whole Health for You and Me, which is about HCPs’ personal well-being.¹⁹ We also reviewed a publication describing the history of whole health and patient-facing online whole health tools.^2,19

Each document was reviewed for key elements related to SDM, patient-centered care, and whole health. Using the 53 elements identified by Bomhof-Roordink et al, we reviewed and compared each element to the whole health materials to create the integrated model of SDM and whole health. We iteratively discussed and organized the elements until we reached consensus.

SDM and Whole Health Alignment

We created an integrated model of SDM for LCS within the context of the VA whole health initiative. This integrated model is directed at HCPs who would likely engage patients in discussions of LCS, including primary care practitioners and nurse coordinators. The model includes 3 steps for HCPs to follow that align SDM within whole health: (1) frame the conversation and partner with the patient; (2) share clinical perspective and elicit patient values; and (3) deliberate and decide together. For each step, the SDM elements, whole health elements, and integration of SDM and whole health are provided. Table 1 provides an overview of the similarities and differences between SDM and whole health. Example phrases that merge SDM and whole health for HCPs to use in patient conversations about LCS are included in Table 2.

STEP 1. FRAME THE CONVERSATION AND PARTNER WITH THE PATIENT

Shared decision-making. Traditional SDM literature includes an initial step of letting patients know that there is a choice to be made between ≥ 2 clinical options.⁴ Ancillary elements of this first step include asking patients their preferences about the degree to which they want to be involved in SDM and about how they like to receive information (eg, verbal, written, video). These steps open the SDM conversation and ensure the patient and HCP are on the same page before moving forward. For example, the US Agency for Healthcare Research and Quality SHARE model’s first step is for HCPs to communicate that choices exist and to invite the patient to be involved in decisions.²⁰ Similarly, Elwyn’s 3-step SDM model begins with establishing that a choice exists and inviting patient input on making that choice.¹⁷

Whole health. Patients are encouraged to play an active role in their health care. Through whole health programs such as Taking Charge of My Life and Health, patients explore their values and set self-care goals.²¹ HCP whole health trainings teach and reinforce communication skills, including SDM, listening skills, and motivational interviewing.¹⁹

Shared decision-making/whole health integration. SDM and whole health both prioritize respect, compassion, and patients’ expertise. They focus on the patient-HCP relationship with an emphasis on fostering egalitarian interactions. HCPs frame the SDM conversation and partner with the patient so they know what to expect and who will be involved. This conversation is framed from the outset as a collaborative discussion. HCPs empower the patient to play an active role in decision-making and help them understand why their engagement is critical.

STEP 2. SHARE CLINICAL PERSPECTIVE AND ELICIT PATIENT VALUES

Shared decision-making. HCPs share clinical perspective on LCS tailored to individual patients while explicitly inviting the patient to share their preferences and values when thinking about whether to undergo LCS. HCPs give a balanced description of LCS, including the benefits and harms, tailored to the patient’s unique information needs and questions. Sharing clinical perspective also includes describing treatment options, the most common element across SDM models.⁴ Decision aids, which provide unbiased information and include a values clarification exercise, may be helpful in sharing clinical perspectives and clarifying patient values related to the trade-offs of LCS.²² For example, the VA National Center for Health Promotion and Disease Prevention developed a LCS decision aid to be used for SDM for LCS.

Whole health. The conversation shifts from “What is the matter with you?” to “What matters to you?” starting with the patient’s goals and priorities rather than disease prevention, diagnosis, and treatment.² Several whole health tools exist, including the Personal Health Inventory, used to identify what matters most to patients and understand their current well-being and self-care.²³ Using the inventory, the patient and their health care team develop the patient’s personal health plan.²⁴ Additionally, whole health trains HCPs to reflect on their own attitudes and biases when providing clinical care.

Shared decision-making/whole health integration. The LCS conversation can build on other whole health-related conversations with a HCP or other team members. HCPs can reference the patient’s personal health plan for documentation of the patient’s preferences, values, and goals in the electronic medical record. During this process, HCPs can give space for patients to discuss factors in their life and experiences that impact their perspective and decision-making. For example, patient concerns could be explored here, including fear of a cancer diagnosis, stigma around smoking, and fears around the screening and/or treatment process. HCPs may ask, “What matters most to you when making this decision?” Finally, by sharing clinical information, HCPs will focus on patient values to help overcome their own biases toward a desire for LCS. HCPs, similar to the rest of the US public, tend to hold highly favorable attitudes toward cancer screening as well as misconceptions about the magnitude of benefits from screening.¹³

STEP 3. DELIBERATE AND DECIDE TOGETHER

Shared decision-making. Decision-making is almost always considered the last SDM step.⁴ In the final step, the patient and HCP discuss the options (ie, to screen or not to screen) considering the patient’s values and preferences, and patients decide with their HCP whether they will undergo LCS. Patients may decide they need more time to think about these options. As part of deliberation, HCPs assess what other information patients may need to arrive at a decision. Family members, friends, or peers may be included in making the final decision.

Whole health. In Whole health, decisions also may include the entire health care team and other individuals important to the patient (eg, family, friends). Integration across different health care settings is also considered a key whole health element. Finally, whole health focuses on long-term relationships with patients; thus, the LCS SDM process is situated within longer term relationship building and patient empowerment, both of which will facilitate partnering with the patient in future conversations about other decisions.

Shared decision-making/whole health integration. Both SDM and whole health emphasize partnership with the patient in making a final decision. There is also focus on decision-making as an ongoing process. Deciding whether LCS is the best choice might include naming and addressing emotions, voicing questions not raised, and exploring whether screening fits the patient’s goals, values, and life context. HCPs may give guidance, but patients retain the authority to make decisions. The goal is to empower patients to know that the only right decision is the one right for them and they will be supported.

Limitations

This article describes a VA practice program and was not a formal research study. Further work is needed to evaluate the presented strategies. Additionally, we did not conduct a systematic literature review and thus elements of SDM and whole health may not be exhaustive.

CONCLUSIONS

This article describes the alignment of 2 distinct VA initiatives, whole health and SDM for LCS. The goal was to reduce known barriers to SDM, such as competing demands, limited time, and lack of familiarity with and training in SDM.^11-13 These concepts are well aligned. This integrated model is the first step in informing the development of a HCP training program and materials as part of a multilevel strategy that our team is using to implement SDM for LCS in VISN 1.16 The final training and materials resulting from this work were delivered to LCSCs in 3 ways: (1) a series of 3 interactive group training sessions, including didactic elements, role play, and time for open discussion; (2) 1-on-1 academic detailing; and (3) educational handouts. In academic detailing, a member of the research team trained in academic detailing met virtually with each nurse coordinator, identified that individual’s barriers to SDM, and used the training materials to highlight messages to overcome those barriers; follow-up calls provided a forum for discussing progress and overcoming additional challenges. Although this article focused specifically on whole health and SDM, the conceptual alignment process strategy can be applied to other implementations of multiple initiatives.

Measles, also known as rubeola, is a highly contagious paramyxovirus that has neared elimination in the United States since 2000 due to widespread adoption of the measles vaccine; however, measles recently has made a comeback, with outbreaks reported in more than 60 countries. In the United States, vaccine hesitancy coupled with decreasing vaccination rates, international travel to endemic areas, and decreased funding and resources for monitoring and immunization programs likely led to a re-emergence of measles cases.^1,2 The resurgence of measles is troubling given its infectiousness and potential severity in at-risk populations. Since measles has a basic reproduction number of 12 to 18 (ie, 1 infected individual will on average infect 12 to 18 others³), it has the capacity to spread quickly. This is why, prior to the development of the measles vaccine in the 1960s, it was responsible for millions of deaths across the globe.

Prior to the introduction of the measles vaccine, both physicians and the public generally were aware of the signs and symptoms of measles due to its prevalence; however, since there have been so few cases in recent decades, images and descriptions of patients presenting with measles can be found only in textbooks, and many physicians are ill-prepared to diagnose the disease.⁴ In response to the recent surge in measles cases, dermatologists—who often are among the first medical professionals to encounter febrile patients with rashes—must be prepared to bridge this divide. Herein, we review the clinical signs, diagnostic approach, operational precautions, and public health responsibilities that dermatologists must relearn amid the current measles outbreak.

Background

Measles is primarily transmitted via respiratory droplets and may remain airborne for up to 2 hours.⁵ It also can be transmitted through direct contact with secretions such as mucus. Indirect transmission via fomites, while certainly plausible, is thought to be the least effective mechanism of transmission.⁶ Following exposure, the incubation period ranges from 7 to 21 days, during which the virus replicates asymptomatically before causing clinical disease.⁷ Herd immunity for measles requires 93% immunity in the population; public health agencies typically target greater than 95% immunity.⁸ Humans are the only reservoir for the measles virus, making eradication possible.

The road to eradication began with the introduction of the measles vaccine in 1963 and subsequent development of the combined measles-mumps-rubella (MMR) vaccine in 1971. As MMR is a live vaccine, 2 doses confer approximately 97% protection.⁹ The first dose is given at 12 to 15 months of age, and the second dose is given at 4 to 6 years of age. Immunity is considered lifelong, and the Centers for Disease Control and Prevention and the World Health Organization do not recommend routine measles boosters for individuals who have completed the primary 2-dose series.^10,11

Widespread vaccination led to a dramatic reduction in incidence, with many countries eliminating measles infections.⁷ The United States declared measles eliminated in 2000, with confirmed cases between 2000 and 2020 ranging from 37 to 1282.¹² Vaccination progress stalled in the late 1990s due to vaccine hesitancy resulting from (subsequently debunked) reports of an association between the MMR vaccine and autism.¹³ Despite efforts to correct this misinformation, many patients continue to espouse these concerns.

Recognizing Measles: Clinical Presentation

Measles, which most often manifests in childhood but also can occur in adults, follows a distinctive clinical course. The prodromal phase is characterized by high fever, cough, coryza (nasal congestion), and conjunctivitis— conjunctivitis—the 3 “Cs” that serve as early warning signs of the disease. Patients may develop small white macules on the buccal mucosa known as Koplik spots (phonetically the fourth “C”), which appear just before the rash. Three to 5 days after the onset of systemic symptoms, patients will develop a classic morbilliform exanthem. In some cases, the exanthem manifests on the head and neck (Figure 1)—first behind the ears and along the hairline, then spreading caudally to the trunk and extremities. The lesions may become confluent, with patients presenting with diffuse erythema. The exanthem fades over several days to weeks, often accompanied by superficial desquamation.¹⁴

Given the nonspecificity of the early symptoms of measles, a high index of suspicion is needed for patients presenting with a febrile illness and a morbilliform eruption (Figure 2). Consideration of MMR vaccination status, exposure history, and local outbreak patterns can help guide risk stratification and the need for testing. Immunocompromised individuals, including those receiving immunosuppressive therapies for dermatologic conditions, may present atypically, lacking the prototypical exanthem or displaying milder signs and further complicating the diagnosis.¹⁵ The differential diagnosis for measles includes a drug reaction or other viral exanthem, and a detailed history may help elucidate the culprit.

Evaluation and Diagnosis

Definitive diagnosis of measles relies on both molecular and serologic testing. Nasopharyngeal swabs for measles polymerase chain reaction testing are obtained using synthetic (noncotton) swabs placed in a viral transport medium. Serum samples also should be collected for measles IgM and IgG antibody testing. Importantly, measles is a reportable illness, and testing may be coordinated with local departments of health.

Determining a patient’s immune status may be important for certain populations. Patients with documented 2-dose MMR vaccination, positive measles IgG serology, or a prior confirmed measles infection are considered immune. While a positive measles IgG indicates immunity, a negative result in an exposed patient should prompt consideration of postexposure prophylaxis with intravenous immunoglobulin.

Many patients, specifically those presenting to dermatology, are taking immunomodulatory or immunosuppressive medications—a contraindication for vaccination with the live MMR vaccine. At the time of publication, there was a single reported case of a patient taking a tumor necrosis factor α inhibitor for rheumatoid arthritis who had acquired measles.¹⁶ While the benefits of titer assessment in patients who are starting or continuing immunomodulatory therapy are not known and currently it is not recommended by the Centers for Disease Control and Prevention, dermatologists might consider checking MMR titers and vaccinating (or referring for vaccination) nonimmune patients.¹⁷

Infection Control

Early identification of a suspected measles case is paramount. Patients in whom measles is a possibility should be isolated as quickly as possible, and the patient and accompanying caregivers should be masked. Clinical staff should don appropriate personal protective equipment, including an N95 mask. Coordination with the local department of health must occur as soon as measles is suspected.

If testing is an option in the outpatient setting, a nasopharyngeal viral swab and serologic titers can be obtained. If testing is not available on site, patients should be sent to appropriate care facilities; prenotification is critical to prevent nosocomial outbreaks. Patients should be encouraged to isolate and avoid public spaces and/or public transport for 4 days following development of an exanthem.¹⁸ Offices should develop clinical protocols for suspected measles cases with training for clinical and office staff.

Final Thoughts

As measles outbreaks become more prevalent, it is incumbent upon physicians to remind ourselves of the signs and symptoms of this largely eliminated disease so that we may pursue early detection and intervention strategies. The primary cutaneous manifestations of measles make dermatologists critical to early recognition and containment efforts. Dermatologists should prepare for the arrival of patients with measles by maintaining vigilance for the classic signs of the disease, implementing stringent isolation protocols, verifying patient immunity when appropriate, and partnering closely with public health authorities.

More broadly, efforts to contain and re-establish a paradigm for eliminating measles outbreaks must be pursued. Encouraging vaccination and developing programs to help combat misinformation surrounding vaccines are critical to this effort. In an era of vaccine hesitancy, measles is a multidisciplinary public health emergency. Dermatologists must remain ready.

Measles, also known as rubeola, is a highly contagious paramyxovirus that has neared elimination in the United States since 2000 due to widespread adoption of the measles vaccine; however, measles recently has made a comeback, with outbreaks reported in more than 60 countries. In the United States, vaccine hesitancy coupled with decreasing vaccination rates, international travel to endemic areas, and decreased funding and resources for monitoring and immunization programs likely led to a re-emergence of measles cases.^1,2 The resurgence of measles is troubling given its infectiousness and potential severity in at-risk populations. Since measles has a basic reproduction number of 12 to 18 (ie, 1 infected individual will on average infect 12 to 18 others³), it has the capacity to spread quickly. This is why, prior to the development of the measles vaccine in the 1960s, it was responsible for millions of deaths across the globe.

Prior to the introduction of the measles vaccine, both physicians and the public generally were aware of the signs and symptoms of measles due to its prevalence; however, since there have been so few cases in recent decades, images and descriptions of patients presenting with measles can be found only in textbooks, and many physicians are ill-prepared to diagnose the disease.⁴ In response to the recent surge in measles cases, dermatologists—who often are among the first medical professionals to encounter febrile patients with rashes—must be prepared to bridge this divide. Herein, we review the clinical signs, diagnostic approach, operational precautions, and public health responsibilities that dermatologists must relearn amid the current measles outbreak.

Background

Measles is primarily transmitted via respiratory droplets and may remain airborne for up to 2 hours.⁵ It also can be transmitted through direct contact with secretions such as mucus. Indirect transmission via fomites, while certainly plausible, is thought to be the least effective mechanism of transmission.⁶ Following exposure, the incubation period ranges from 7 to 21 days, during which the virus replicates asymptomatically before causing clinical disease.⁷ Herd immunity for measles requires 93% immunity in the population; public health agencies typically target greater than 95% immunity.⁸ Humans are the only reservoir for the measles virus, making eradication possible.

The road to eradication began with the introduction of the measles vaccine in 1963 and subsequent development of the combined measles-mumps-rubella (MMR) vaccine in 1971. As MMR is a live vaccine, 2 doses confer approximately 97% protection.⁹ The first dose is given at 12 to 15 months of age, and the second dose is given at 4 to 6 years of age. Immunity is considered lifelong, and the Centers for Disease Control and Prevention and the World Health Organization do not recommend routine measles boosters for individuals who have completed the primary 2-dose series.^10,11

Widespread vaccination led to a dramatic reduction in incidence, with many countries eliminating measles infections.⁷ The United States declared measles eliminated in 2000, with confirmed cases between 2000 and 2020 ranging from 37 to 1282.¹² Vaccination progress stalled in the late 1990s due to vaccine hesitancy resulting from (subsequently debunked) reports of an association between the MMR vaccine and autism.¹³ Despite efforts to correct this misinformation, many patients continue to espouse these concerns.

Recognizing Measles: Clinical Presentation

Measles, which most often manifests in childhood but also can occur in adults, follows a distinctive clinical course. The prodromal phase is characterized by high fever, cough, coryza (nasal congestion), and conjunctivitis— conjunctivitis—the 3 “Cs” that serve as early warning signs of the disease. Patients may develop small white macules on the buccal mucosa known as Koplik spots (phonetically the fourth “C”), which appear just before the rash. Three to 5 days after the onset of systemic symptoms, patients will develop a classic morbilliform exanthem. In some cases, the exanthem manifests on the head and neck (Figure 1)—first behind the ears and along the hairline, then spreading caudally to the trunk and extremities. The lesions may become confluent, with patients presenting with diffuse erythema. The exanthem fades over several days to weeks, often accompanied by superficial desquamation.¹⁴

Given the nonspecificity of the early symptoms of measles, a high index of suspicion is needed for patients presenting with a febrile illness and a morbilliform eruption (Figure 2). Consideration of MMR vaccination status, exposure history, and local outbreak patterns can help guide risk stratification and the need for testing. Immunocompromised individuals, including those receiving immunosuppressive therapies for dermatologic conditions, may present atypically, lacking the prototypical exanthem or displaying milder signs and further complicating the diagnosis.¹⁵ The differential diagnosis for measles includes a drug reaction or other viral exanthem, and a detailed history may help elucidate the culprit.

Evaluation and Diagnosis

Definitive diagnosis of measles relies on both molecular and serologic testing. Nasopharyngeal swabs for measles polymerase chain reaction testing are obtained using synthetic (noncotton) swabs placed in a viral transport medium. Serum samples also should be collected for measles IgM and IgG antibody testing. Importantly, measles is a reportable illness, and testing may be coordinated with local departments of health.

Determining a patient’s immune status may be important for certain populations. Patients with documented 2-dose MMR vaccination, positive measles IgG serology, or a prior confirmed measles infection are considered immune. While a positive measles IgG indicates immunity, a negative result in an exposed patient should prompt consideration of postexposure prophylaxis with intravenous immunoglobulin.

Many patients, specifically those presenting to dermatology, are taking immunomodulatory or immunosuppressive medications—a contraindication for vaccination with the live MMR vaccine. At the time of publication, there was a single reported case of a patient taking a tumor necrosis factor α inhibitor for rheumatoid arthritis who had acquired measles.¹⁶ While the benefits of titer assessment in patients who are starting or continuing immunomodulatory therapy are not known and currently it is not recommended by the Centers for Disease Control and Prevention, dermatologists might consider checking MMR titers and vaccinating (or referring for vaccination) nonimmune patients.¹⁷

Infection Control

Early identification of a suspected measles case is paramount. Patients in whom measles is a possibility should be isolated as quickly as possible, and the patient and accompanying caregivers should be masked. Clinical staff should don appropriate personal protective equipment, including an N95 mask. Coordination with the local department of health must occur as soon as measles is suspected.

If testing is an option in the outpatient setting, a nasopharyngeal viral swab and serologic titers can be obtained. If testing is not available on site, patients should be sent to appropriate care facilities; prenotification is critical to prevent nosocomial outbreaks. Patients should be encouraged to isolate and avoid public spaces and/or public transport for 4 days following development of an exanthem.¹⁸ Offices should develop clinical protocols for suspected measles cases with training for clinical and office staff.

Final Thoughts

As measles outbreaks become more prevalent, it is incumbent upon physicians to remind ourselves of the signs and symptoms of this largely eliminated disease so that we may pursue early detection and intervention strategies. The primary cutaneous manifestations of measles make dermatologists critical to early recognition and containment efforts. Dermatologists should prepare for the arrival of patients with measles by maintaining vigilance for the classic signs of the disease, implementing stringent isolation protocols, verifying patient immunity when appropriate, and partnering closely with public health authorities.

More broadly, efforts to contain and re-establish a paradigm for eliminating measles outbreaks must be pursued. Encouraging vaccination and developing programs to help combat misinformation surrounding vaccines are critical to this effort. In an era of vaccine hesitancy, measles is a multidisciplinary public health emergency. Dermatologists must remain ready.

Measles, also known as rubeola, is a highly contagious paramyxovirus that has neared elimination in the United States since 2000 due to widespread adoption of the measles vaccine; however, measles recently has made a comeback, with outbreaks reported in more than 60 countries. In the United States, vaccine hesitancy coupled with decreasing vaccination rates, international travel to endemic areas, and decreased funding and resources for monitoring and immunization programs likely led to a re-emergence of measles cases.^1,2 The resurgence of measles is troubling given its infectiousness and potential severity in at-risk populations. Since measles has a basic reproduction number of 12 to 18 (ie, 1 infected individual will on average infect 12 to 18 others³), it has the capacity to spread quickly. This is why, prior to the development of the measles vaccine in the 1960s, it was responsible for millions of deaths across the globe.

Prior to the introduction of the measles vaccine, both physicians and the public generally were aware of the signs and symptoms of measles due to its prevalence; however, since there have been so few cases in recent decades, images and descriptions of patients presenting with measles can be found only in textbooks, and many physicians are ill-prepared to diagnose the disease.⁴ In response to the recent surge in measles cases, dermatologists—who often are among the first medical professionals to encounter febrile patients with rashes—must be prepared to bridge this divide. Herein, we review the clinical signs, diagnostic approach, operational precautions, and public health responsibilities that dermatologists must relearn amid the current measles outbreak.

Background

Measles is primarily transmitted via respiratory droplets and may remain airborne for up to 2 hours.⁵ It also can be transmitted through direct contact with secretions such as mucus. Indirect transmission via fomites, while certainly plausible, is thought to be the least effective mechanism of transmission.⁶ Following exposure, the incubation period ranges from 7 to 21 days, during which the virus replicates asymptomatically before causing clinical disease.⁷ Herd immunity for measles requires 93% immunity in the population; public health agencies typically target greater than 95% immunity.⁸ Humans are the only reservoir for the measles virus, making eradication possible.

The road to eradication began with the introduction of the measles vaccine in 1963 and subsequent development of the combined measles-mumps-rubella (MMR) vaccine in 1971. As MMR is a live vaccine, 2 doses confer approximately 97% protection.⁹ The first dose is given at 12 to 15 months of age, and the second dose is given at 4 to 6 years of age. Immunity is considered lifelong, and the Centers for Disease Control and Prevention and the World Health Organization do not recommend routine measles boosters for individuals who have completed the primary 2-dose series.^10,11

Widespread vaccination led to a dramatic reduction in incidence, with many countries eliminating measles infections.⁷ The United States declared measles eliminated in 2000, with confirmed cases between 2000 and 2020 ranging from 37 to 1282.¹² Vaccination progress stalled in the late 1990s due to vaccine hesitancy resulting from (subsequently debunked) reports of an association between the MMR vaccine and autism.¹³ Despite efforts to correct this misinformation, many patients continue to espouse these concerns.

Recognizing Measles: Clinical Presentation

Measles, which most often manifests in childhood but also can occur in adults, follows a distinctive clinical course. The prodromal phase is characterized by high fever, cough, coryza (nasal congestion), and conjunctivitis— conjunctivitis—the 3 “Cs” that serve as early warning signs of the disease. Patients may develop small white macules on the buccal mucosa known as Koplik spots (phonetically the fourth “C”), which appear just before the rash. Three to 5 days after the onset of systemic symptoms, patients will develop a classic morbilliform exanthem. In some cases, the exanthem manifests on the head and neck (Figure 1)—first behind the ears and along the hairline, then spreading caudally to the trunk and extremities. The lesions may become confluent, with patients presenting with diffuse erythema. The exanthem fades over several days to weeks, often accompanied by superficial desquamation.¹⁴

Given the nonspecificity of the early symptoms of measles, a high index of suspicion is needed for patients presenting with a febrile illness and a morbilliform eruption (Figure 2). Consideration of MMR vaccination status, exposure history, and local outbreak patterns can help guide risk stratification and the need for testing. Immunocompromised individuals, including those receiving immunosuppressive therapies for dermatologic conditions, may present atypically, lacking the prototypical exanthem or displaying milder signs and further complicating the diagnosis.¹⁵ The differential diagnosis for measles includes a drug reaction or other viral exanthem, and a detailed history may help elucidate the culprit.

Evaluation and Diagnosis

Definitive diagnosis of measles relies on both molecular and serologic testing. Nasopharyngeal swabs for measles polymerase chain reaction testing are obtained using synthetic (noncotton) swabs placed in a viral transport medium. Serum samples also should be collected for measles IgM and IgG antibody testing. Importantly, measles is a reportable illness, and testing may be coordinated with local departments of health.

Determining a patient’s immune status may be important for certain populations. Patients with documented 2-dose MMR vaccination, positive measles IgG serology, or a prior confirmed measles infection are considered immune. While a positive measles IgG indicates immunity, a negative result in an exposed patient should prompt consideration of postexposure prophylaxis with intravenous immunoglobulin.

Many patients, specifically those presenting to dermatology, are taking immunomodulatory or immunosuppressive medications—a contraindication for vaccination with the live MMR vaccine. At the time of publication, there was a single reported case of a patient taking a tumor necrosis factor α inhibitor for rheumatoid arthritis who had acquired measles.¹⁶ While the benefits of titer assessment in patients who are starting or continuing immunomodulatory therapy are not known and currently it is not recommended by the Centers for Disease Control and Prevention, dermatologists might consider checking MMR titers and vaccinating (or referring for vaccination) nonimmune patients.¹⁷

Infection Control

Early identification of a suspected measles case is paramount. Patients in whom measles is a possibility should be isolated as quickly as possible, and the patient and accompanying caregivers should be masked. Clinical staff should don appropriate personal protective equipment, including an N95 mask. Coordination with the local department of health must occur as soon as measles is suspected.

If testing is an option in the outpatient setting, a nasopharyngeal viral swab and serologic titers can be obtained. If testing is not available on site, patients should be sent to appropriate care facilities; prenotification is critical to prevent nosocomial outbreaks. Patients should be encouraged to isolate and avoid public spaces and/or public transport for 4 days following development of an exanthem.¹⁸ Offices should develop clinical protocols for suspected measles cases with training for clinical and office staff.

Final Thoughts

As measles outbreaks become more prevalent, it is incumbent upon physicians to remind ourselves of the signs and symptoms of this largely eliminated disease so that we may pursue early detection and intervention strategies. The primary cutaneous manifestations of measles make dermatologists critical to early recognition and containment efforts. Dermatologists should prepare for the arrival of patients with measles by maintaining vigilance for the classic signs of the disease, implementing stringent isolation protocols, verifying patient immunity when appropriate, and partnering closely with public health authorities.

More broadly, efforts to contain and re-establish a paradigm for eliminating measles outbreaks must be pursued. Encouraging vaccination and developing programs to help combat misinformation surrounding vaccines are critical to this effort. In an era of vaccine hesitancy, measles is a multidisciplinary public health emergency. Dermatologists must remain ready.

Later this month, the U.S. Supreme Court is anticipated to announce its decision in Kennedy vs. Braidwood Management, a case that could significantly impact the no-cost coverage of preventive healthcare services under the Patient Protection and Affordable Care Act (ACA). At the center of the case is whether the structure of the U.S. Preventive Services Task Force (USPSTF) – an independent body convened by the federal government that makes recommendations for preventive services that nearly all private insurances must cover without cost sharing under provisions of the ACA (specifically, Grade A and B recommendations) – violates the Appointments Clause of the U.S. Constitution. This clause states that “officers of the United States” may only be appointed by the president with the Senate’s approval.

The case, initiated in 2022 by a self-insured, Christian-owned business, specifically targeted the coverage of pre-exposure prophylaxis (PrEP) for preventing HIV in high-risk individuals. However, the decision could broadly affect the coverage of other preventive services, including colorectal cancer screening tests. In June 2024, the 5th Circuit Court of Appeals upheld a district court’s ruling that the ACA’s requirement to cover without cost-sharing services recommended by USPSTF is unconstitutional, paving the way for the current Supreme Court showdown.

The consequences of this ruling could be significant. If the Court rules in favor of Braidwood, private health insurers would no longer be required to cover, without cost-sharing, preventive services recommended by USPSTF after March 2010 when the ACA was enacted. This would likely reverse the progress we have made in increasing colorectal cancer screening rates by reducing financial barriers to care. Interestingly, despite a new administration, the federal government continues to advocate for upholding the law, asserting that USPSTF members are “inferior officers” such that the Secretary of Health and Human Services can dismiss individual members and oversee or veto the Task Force’s recommendations at will, potentially threatening scientific independence. Though it’s often challenging to predict the Supreme Court’s final decision, the tone of questioning during oral arguments in April hinted at a possible win for the ACA and preventive care. Stay tuned, as the decision to be released later this month has seismic clinical implications.

Megan A. Adams, MD, JD, MSc

Editor in Chief

Later this month, the U.S. Supreme Court is anticipated to announce its decision in Kennedy vs. Braidwood Management, a case that could significantly impact the no-cost coverage of preventive healthcare services under the Patient Protection and Affordable Care Act (ACA). At the center of the case is whether the structure of the U.S. Preventive Services Task Force (USPSTF) – an independent body convened by the federal government that makes recommendations for preventive services that nearly all private insurances must cover without cost sharing under provisions of the ACA (specifically, Grade A and B recommendations) – violates the Appointments Clause of the U.S. Constitution. This clause states that “officers of the United States” may only be appointed by the president with the Senate’s approval.

The case, initiated in 2022 by a self-insured, Christian-owned business, specifically targeted the coverage of pre-exposure prophylaxis (PrEP) for preventing HIV in high-risk individuals. However, the decision could broadly affect the coverage of other preventive services, including colorectal cancer screening tests. In June 2024, the 5th Circuit Court of Appeals upheld a district court’s ruling that the ACA’s requirement to cover without cost-sharing services recommended by USPSTF is unconstitutional, paving the way for the current Supreme Court showdown.

The consequences of this ruling could be significant. If the Court rules in favor of Braidwood, private health insurers would no longer be required to cover, without cost-sharing, preventive services recommended by USPSTF after March 2010 when the ACA was enacted. This would likely reverse the progress we have made in increasing colorectal cancer screening rates by reducing financial barriers to care. Interestingly, despite a new administration, the federal government continues to advocate for upholding the law, asserting that USPSTF members are “inferior officers” such that the Secretary of Health and Human Services can dismiss individual members and oversee or veto the Task Force’s recommendations at will, potentially threatening scientific independence. Though it’s often challenging to predict the Supreme Court’s final decision, the tone of questioning during oral arguments in April hinted at a possible win for the ACA and preventive care. Stay tuned, as the decision to be released later this month has seismic clinical implications.

Megan A. Adams, MD, JD, MSc

Editor in Chief

Later this month, the U.S. Supreme Court is anticipated to announce its decision in Kennedy vs. Braidwood Management, a case that could significantly impact the no-cost coverage of preventive healthcare services under the Patient Protection and Affordable Care Act (ACA). At the center of the case is whether the structure of the U.S. Preventive Services Task Force (USPSTF) – an independent body convened by the federal government that makes recommendations for preventive services that nearly all private insurances must cover without cost sharing under provisions of the ACA (specifically, Grade A and B recommendations) – violates the Appointments Clause of the U.S. Constitution. This clause states that “officers of the United States” may only be appointed by the president with the Senate’s approval.

The case, initiated in 2022 by a self-insured, Christian-owned business, specifically targeted the coverage of pre-exposure prophylaxis (PrEP) for preventing HIV in high-risk individuals. However, the decision could broadly affect the coverage of other preventive services, including colorectal cancer screening tests. In June 2024, the 5th Circuit Court of Appeals upheld a district court’s ruling that the ACA’s requirement to cover without cost-sharing services recommended by USPSTF is unconstitutional, paving the way for the current Supreme Court showdown.

The consequences of this ruling could be significant. If the Court rules in favor of Braidwood, private health insurers would no longer be required to cover, without cost-sharing, preventive services recommended by USPSTF after March 2010 when the ACA was enacted. This would likely reverse the progress we have made in increasing colorectal cancer screening rates by reducing financial barriers to care. Interestingly, despite a new administration, the federal government continues to advocate for upholding the law, asserting that USPSTF members are “inferior officers” such that the Secretary of Health and Human Services can dismiss individual members and oversee or veto the Task Force’s recommendations at will, potentially threatening scientific independence. Though it’s often challenging to predict the Supreme Court’s final decision, the tone of questioning during oral arguments in April hinted at a possible win for the ACA and preventive care. Stay tuned, as the decision to be released later this month has seismic clinical implications.

Megan A. Adams, MD, JD, MSc

Editor in Chief

Artificial intelligence (AI) is rapidly evolving, with large language models (LLMs) marking a significant milestone in processing and generating human-like responses to natural language prompts. However, this advancement only signals the beginning of a more profound transformation in AI capabilities. The development of AI agents represents a new paradigm at the forefront of this evolution.

BACKGROUND

AI agents represent a leap forward from traditional LLM applications. While definitions may vary slightly among technology developers, the core concept remains: these agents are autonomous software entities designed to interact with their environment, make independent decisions, and execute tasks based on predefined goals.^1-3 What sets AI agents apart is their combination of sophisticated components within structured architectures. At their core, AI agents incorporate an LLM for response generation, which is augmented by a suite of tools to optimize workflow and complete tasks, memory capabilities for personalized interactions, and autonomous reasoning. This combination allows AI agents to plan, create subtasks, gather information, and learn iteratively from their own experiences or other AI agents.

The true potential of this technology becomes apparent when multiple AI agents collaborate within multiagent AI systems. This concept introduces a new level of flexibility and capability in tackling complex tasks. Autogen, CrewAI, and LangChain offer various agent network configurations, including hierarchical, sequential, conditional, or even parallel task execution.^4-6 This adaptability opens up a world of possibilities across various industries, but perhaps nowhere is the potential impact more exciting and profound than in health care.

AI agents in health care present an opportunity to revolutionize patient care, streamline administrative processes, and support complex clinical decision-making. This review examines 3 scenarios that illustrate the impact of AI agents in health care: a hypothetical sepsis management system, chronic disease management, and hospital patient flow optimization. This article will provide a detailed look at the technical implementation challenges, including the integration with existing health care IT systems, data privacy considerations, and the crucial role of explainable AI in maintaining trust and transparency.

It is challenging to implement AI agents in health care. Concerns include ensuring data quality and mitigating bias, seamlessly integrating these systems into existing clinical workflows, and navigating the complex ethical considerations that arise when deploying autonomous systems in health care. The integration with Internet of Things (IoT) devices for real-time patient data monitoring and the development of more sophisticated natural language interfaces to enhance future human-AI collaboration.

The adoption of AI agents in health care is only beginning, and it promises to be transformative. As AI continues to evolve, a comprehensive understanding of its applications, limitations, and ethical considerations is essential. This report provides a comprehensive overview of the current state, potential applications, and future directions of AI agents in health care, offering insights valuable to researchers, clinicians, and policymakers.

MultiAgent AI architecture

Sepsis Management

Despite advancements in broad-spectrum antibiotics, imaging, and life support systems, mortality rates associated with sepsis remain high. The complexity of optimizing care in clinical settings has hindered progress in managing sepsis. Previous attempts to develop predictive sepsis models have proven challenging.⁷ This report proposes a multiagent AI system designed to enhance comprehensive patient monitoring and care through coordinated AI-driven interventions.

Data Collection and Integration Agent. Powered by a controlled vocabulary to specify all data, the primary function for the data collection and integration agent is to clean, transform, and organize patient data from structured and unstructured sources. This agent prepares succinct summaries of consultant notes and formats data for human and machine consumption. All numerical data are presented graphically, including relevant historical data trends. The agent also digitally captures all orders in a structured format using a specified controlled vocabulary. This structured data feed supports the output of other agents, including documentation, treatment planning, and risk stratification, while also supplying the data structures for future training.

Diagnostic Agent. Critical illness is characterized by multiple abnormalities across a wide array of tests, ranging from plain chest X-ray, computed tomography (CT), blood cell composition, plasma chemistry, and microscopic evaluation of specimens. Additionally, life support parameters provide insights into disease severity and can inform management recommendations. These data offer a wide array of visual and numerical data to be used as input for computation, recommendation, and further training. For example, to evaluate fluid overload on chest X-rays or tissue histopathology slides, an AI agent can leverage deep learning models such as convolutional neural networks and vision transformers to analyze images like radiographs and histopathology slides.^8,9 Recurrent neural networks or transformer models process sequential data like time-series vital signs. The agent also implements ensemble methods that combine multiple machine learning algorithms to enhance diagnostic accuracy.

Risk Stratification Agent. This assesses severity and predicts potential outcomes. Morbidity and mortality risks are calculated using an established scoring system and individualized based on the history of other agents’ conditional patients. These are presented graphically, with major risk factors highlighted for explainability. 

Treatment Recommendation Agent. Using a reinforcement learning framework supplemented by up-to-date clinical guidelines, this system leverages historical data structured with standardized vocabulary to analyze patients with similar clinical features. Training is also conducted on the patient’s physiological data. All recommendations are presented via a dedicated user interface in a readable format, along with recommendations for editable, orderable items, references, and full-text snippets from previous research. Stop rules end computing if confidence in recommendations is too broad or no clear pathway can be computed with certainty, prompting human mitigation.

Resource Management Agent. This agent coordinates hospital resources using constraint programming techniques for optimal resource allocation, uses queueing theory models to predict and manage patient flow, and implements genetic algorithms for complex scheduling problems.^10,11

Monitoring and Alert Agent. By tracking patients’ progress and alerting staff to changes, this agent uses anomaly detection algorithms to identify unusual patterns in patient data and implement time-series forecasting models, such as autoregressive integrated moving average and prophet, to predict future patient states. The agent also uses stream-processing techniques for real-time data analysis.^12,13

Documentation and Reporting Agent. This agent maintains comprehensive medical records and generates reports. It employs advanced natural language processing techniques for automated report generation, uses advanced LLMs fine-tuned on medical corpora for narrative creation, and implements information-retrieval techniques to efficiently query patient records.

CLINICAL CASE STUDIES

To illustrate the functionality of a multiagent system, this report examines its application for managing sepsis. The data collection and integration agent continuously aggregates patient data from various sources, normalizing and timestamping it for consistent processing. The diagnostic agent analyzes this integrated data in real time, applying sepsis criteria and utilizing a deep learning model trained on a large sepsis dataset to detect subtle patterns.

The risk stratification agent calculates severity scores, such as the Sepsis-related Organ Failure Assessment (SOFA), quick SOFA (qSOFA), and Acute Physiology and Chronic Health Evaluation II, upon detecting a possible sepsis case.¹⁴ It predicts the likelihood of specific outcomes and estimates the potential trajectory of the patient’s condition for the next 24 to 48 hours. Based on this assessment, the treatment recommendation agent suggests an initial treatment plan, including appropriate antibiotics, fluid resuscitation protocols, and vasopressor recommendations, recommendations when indicated.

Concurrently, the resource management agent checks the availability of necessary resources and prioritizes allocation based on the severity. The monitoring agent tracks the patient’s response to interventions in real time, alerting the care team to any concerning changes or lack of expected improvement. Throughout this process, the documentation agent ensures that all actions, responses, and outcomes are meticulously recorded in a structured format and generates real-time updates for the patient’s electronic health record (EHR) and preparing summary reports for handoffs between care teams.

Administrative Workflow Support

Modern health care operations are resource-intensive, requiring coordination of advanced imaging, procedures, laboratory testing, and professional consultations.¹⁵ AI-powered health care administrative workflow systems are revolutionizing how medical facilities coordinate patient care. For patients with chronic cough, these systems seamlessly integrate scheduling, imaging, diagnostics, and follow-up care into a cohesive process that reduces administrative burden while improving patient outcomes. Through an intuitive interface and automated assistance, health care practitioners (HCPs) can track patient progress from initial consultation through diagnosis and treatment.

The process begins when an HCP enters a patient into the system, which triggers an automated CT scan scheduling system. The system considers factors like urgency, facility availability, and patient preferences to suggest optimal appointment times. Once imaging is complete, AI agents analyze the radiology reports, extract key findings, and generate structured summaries that highlight critical information such as “mild bronchial wall thickening with patchy ground-glass opacities” or “findings consistent with chronic bronchitis.”

Based on these findings, the system automatically generates evidence-based recommendations for follow-up care, such as pulmonology consultations or follow-up imaging in 3 months. These recommendations are presented to the ordering clinician, along with suggested appointment slots for specialist consultations. The system then manages the coordination of multiple appointments, ensuring each step in the patient’s care plan is properly sequenced and scheduled.

The entire process is monitored through a comprehensive dashboard that provides real-time updates on patient status, appointment schedules, and clinical recommendations. HCPs can track which patients require immediate attention, view upcoming appointments, and monitor the progress of ongoing care plans.

Multiagent AI Operation Optimization

Hospitals are complex entities that must function at different scales and respond in an agile, timely manner at all hours, deploying staff at various positions.¹⁶ A system of AI agents can receive signals from sensors monitoring foot traffic in the emergency department and trauma unit, as well as the availability of operating room staff, equipment, and intensive care unit beds. Smart sensors enable this monitoring through IoT networks. These networks benefit from advances in adaptive and consensus networking algorithms, along with recent advances in bioengineering and biocomputing.¹⁷

For example, in the case of imaging for suspected abdominal obstruction, an AI agent tasked with scheduling CTs could time the patient’s arrival based on acuity. Another AI agent could alert staff transporting the patient to the CT appointment, with the next location contingent on a clinical decision to proceed to the operating room. Yet another AI agent could summarize radiology interpretations and alert the surgery and anesthesia teams to a potential case, while others could notify operating room staff of equipment needs or reserve a bed. In this paradigm, AI agents facilitate more precise and timely communication between multiple staff members.

TECHNICAL IMPLEMENTATION

Large Language Models

Each agent uses a different LLM optimized for its specific task. For example, the diagnostic agent uses an LLM pretrained on a large corpus of biomedical literature and fine-tuned on a dataset of confirmed sepsis cases and their presentations.¹⁸ It implements few-shot learning techniques to adapt to rare or atypical presentations. The treatment recommendation agent also uses an LLM, employing a retrieval-augmented generation approach to access the latest clinical guidelines during inference. The documentation agent uses another advanced language model, fine-tuned on a large corpus of high-quality medical documentation, implementing controlled text generation techniques and utilizing a separate smaller model for real-time error checking and correction.

Interagent Quality Control

Agents learn from their own experience and the experience of other agents. They are equipped with user-defined rule-based and model-based systems for quality assurance, with clear stopping rules for human involvement and mitigation.

Sophisticated quality control measures bolster the system’s reliability, including ensemble techniques for result comparison, redundancy for critical tasks, and automatic human review for disagreements above a certain threshold. Each agent provides a calibrated confidence score with its output, used to weigh inputs in downstream tasks and trigger additional checks for low-confidence outputs.

A dedicated quality control agent monitors output from all agents, employing both supervised and unsupervised anomaly detection techniques. Feedback loops allow agents to evaluate the quality and utility of information received from other agents. The system implements a multiarmed bandit approach to dynamically adjust the influence of different agents based on their performance and periodically retrains agent models using federated learning techniques.¹⁹

Electronic Health Record Integration

Seamless EHR integration is crucial for practical implementation. The system has secure application programming interface access to various EHR platforms, implements OAuth 2.0 for authentication, and use HTTPS with perfect forward secrecy for all communications.²⁰ It works with HL7 FHIR to ensure interoperability and uses SNOMED CT for clinical terminology to ensure semantic interoperability across different EHRs.^21,22

The system implements a multilevel approval system for write-backs to EHRs, with different thresholds based on the information’s criticality. It uses digital signatures to ensure the integrity and nonrepudiation of AI-generated entries and implements blockchain technology to create an immutable and distributed ledger of all AI system actions.²³

Decision Transparency

To ensure transparency in decision-making processes, the system applies techniques (eg, local interpretable model-agnostic explanations and Shapley additive explanations) to provide insights into agent decision-making processes.^24-26 It provides customized visualizations for different stakeholders and allows users to explore alternative decision paths through what-if scenario modeling.²⁷

The system provides calibrated confidence indicators for each recommendation or decision, implementing a novel confidence calibration agent that continuously monitors and adjusts confidence scores based on observed outcomes.

Continuous Learning and Adaptation

The system employs several techniques to remain current with evolving medical knowledge. Federated learning includes information from diverse datasets across multiple institutions without compromising patient privacy.²⁸ A/B testing is used to safely deploy and compare new agent versions in controlled settings, implementing multiarmed bandit algorithms to efficiently explore new models while minimizing potential negative impacts. Human-in-the-loop learning and active learning techniques are used to incorporate feedback from HCPs and efficiently solicit expert input on the most informative data.²⁹

CLINICAL IMPLICATIONS

The implementation of multiagent AI systems in health care has several potential benefits: enhanced diagnostic accuracy, personalized treatment, improved efficiency, continuous monitoring, and resource optimization. A recent review of AI sepsis predictive models exhibited superior results to standard clinical scoring methods like qSOFA.³⁰ In oncology, such systems can result in more tailored treatments, enhancing outcomes.³¹ The implementation of an ambient dictation system can improve workflow and prevent HCP burnout.³²

ETHICAL CONSIDERATIONS AND AI OVERSIGHT

Integrating AI agents into health care raises significant ethical considerations that must be carefully addressed to ensure equitable and effective care delivery. One primary concern involves cultural and linguistic competency, as AI systems may struggle with cultural nuances, idioms, and context-specific communication patterns. This becomes particularly challenging in regions with diverse ethnic populations or immigrant communities, where medical terminology may not have direct translations and cultural beliefs significantly influence health care decisions. AI systems also may inherit and amplify existing biases in health care delivery, whether through HCP bias reflected in training data, patient bias affecting acceptance of AI-assisted care, or demographic underrepresentation during system development.

AI agents present unique opportunities for improving health care access and outcomes through community engagement, though such initiatives require thoughtful implementation. Predictive analytics can identify high-risk individuals within communities who may benefit from preventive care, while analysis of social determinants of health can enable more targeted interventions. However, these capabilities must be balanced with privacy concerns and the risk of surveillance, particularly in communities that distrust health care institutions. The potential for AI to bridge health care gaps must be weighed against the need to maintain cultural sensitivity and community trust.

The governance and oversight of health care AI systems requires a multistakeholder approach with clear lines of responsibility and accountability. This includes involvement from government health care agencies, professional medical associations, ethics boards, and independent auditors, all working together to establish and enforce standards while monitoring system performance and addressing potential biases. Health care organizations must maintain transparent policies about AI use, implement regular monitoring and evaluation protocols, and establish precise mechanisms for patient feedback and grievance resolution. Ongoing assessment and adjustment of these systems, informed by community feedback and outcomes data, will be crucial for their ethical implementation, ensuring that AI agents complement, rather than replace, human judgment and cultural sensitivity.

FUTURE DIRECTIONS

Despite the potential benefits, implementing multiagent AI systems in health care faces significant challenges that require careful consideration. Beyond the fundamental issues such as data quality and bias mitigation, health care organizations struggle with fragmented systems, inconsistent data formats, and varying quality. Technical infrastructure requirements are substantial, particularly in rural or underserved areas that lack robust networks and cybersecurity. HCPs already face significant cognitive load and time pressures, making integrating AI agents into existing workflows particularly challenging. There is also the critical issue of transparency and interpretability, as health care decisions require clear reasoning and accountability that many black-box AI systems struggle to provide.

The legal landscape introduces another layer of complexity, particularly regarding liability, consent, and privacy questions. When AI agents contribute to medical decisions, establishing clear lines of responsibility becomes crucial. There are also serious concerns about algorithmic fairness and the potential for AI systems to perpetuate or amplify existing inequities. The cost of implementation remains a significant barrier, requiring substantial investment in technology, training, and ongoing maintenance while ensuring resources are not diverted from direct patient care. Moreover, HCPs may resist adoption due to concerns about job security, loss of autonomy, or skepticism about AI capabilities while paradoxically facing risks of overreliance on AI systems that could lead to the degradation of human clinical skills.

Addressing these challenges requires a multifaceted approach that combines technical solutions with organizational and policy changes. Health care organizations must implement rigorous data validation processes and interoperability standards while developing hybrid models that balance sophisticated AI capabilities with interpretable techniques. Extensive research and iterative design processes, with direct input from HCPs, are essential for successful integration. Establishing independent ethics boards to oversee system development and deployment, conducting multicenter randomized controlled trials, and creating clear regulatory frameworks will ensure safe and effective implementation. Success will ultimately depend on ongoing collaboration between technology developers, HCPs, policymakers, and patients, maintaining a steady focus on improving patient care and outcomes while carefully navigating the complex challenges of AI integration in health care.^33-35

As multiagent AI systems in health care evolve, several exciting directions emerge. These include the integration of IoT and wearable devices, the development of more sophisticated natural language interfaces, and applying these systems to predictive maintenance of medical equipment.

CONCLUSIONS

The advent of multiagent AI systems in health care represents a paradigm shift in the approach to patient care, clinical decision making, and health care management. While these systems offer immense potential to transform health care delivery, their development and implementation must be guided by rigorous scientific validation, ethical considerations, and a patient-centered approach. The ultimate goal remains clear: harnessing the power of AI to improve patient outcomes, enhance the efficiency of health care delivery, and ultimately advance the health and well-being of patients.

Artificial intelligence (AI) is rapidly evolving, with large language models (LLMs) marking a significant milestone in processing and generating human-like responses to natural language prompts. However, this advancement only signals the beginning of a more profound transformation in AI capabilities. The development of AI agents represents a new paradigm at the forefront of this evolution.

BACKGROUND

AI agents represent a leap forward from traditional LLM applications. While definitions may vary slightly among technology developers, the core concept remains: these agents are autonomous software entities designed to interact with their environment, make independent decisions, and execute tasks based on predefined goals.^1-3 What sets AI agents apart is their combination of sophisticated components within structured architectures. At their core, AI agents incorporate an LLM for response generation, which is augmented by a suite of tools to optimize workflow and complete tasks, memory capabilities for personalized interactions, and autonomous reasoning. This combination allows AI agents to plan, create subtasks, gather information, and learn iteratively from their own experiences or other AI agents.

The true potential of this technology becomes apparent when multiple AI agents collaborate within multiagent AI systems. This concept introduces a new level of flexibility and capability in tackling complex tasks. Autogen, CrewAI, and LangChain offer various agent network configurations, including hierarchical, sequential, conditional, or even parallel task execution.^4-6 This adaptability opens up a world of possibilities across various industries, but perhaps nowhere is the potential impact more exciting and profound than in health care.

AI agents in health care present an opportunity to revolutionize patient care, streamline administrative processes, and support complex clinical decision-making. This review examines 3 scenarios that illustrate the impact of AI agents in health care: a hypothetical sepsis management system, chronic disease management, and hospital patient flow optimization. This article will provide a detailed look at the technical implementation challenges, including the integration with existing health care IT systems, data privacy considerations, and the crucial role of explainable AI in maintaining trust and transparency.

It is challenging to implement AI agents in health care. Concerns include ensuring data quality and mitigating bias, seamlessly integrating these systems into existing clinical workflows, and navigating the complex ethical considerations that arise when deploying autonomous systems in health care. The integration with Internet of Things (IoT) devices for real-time patient data monitoring and the development of more sophisticated natural language interfaces to enhance future human-AI collaboration.

The adoption of AI agents in health care is only beginning, and it promises to be transformative. As AI continues to evolve, a comprehensive understanding of its applications, limitations, and ethical considerations is essential. This report provides a comprehensive overview of the current state, potential applications, and future directions of AI agents in health care, offering insights valuable to researchers, clinicians, and policymakers.

MultiAgent AI architecture

Sepsis Management

Despite advancements in broad-spectrum antibiotics, imaging, and life support systems, mortality rates associated with sepsis remain high. The complexity of optimizing care in clinical settings has hindered progress in managing sepsis. Previous attempts to develop predictive sepsis models have proven challenging.⁷ This report proposes a multiagent AI system designed to enhance comprehensive patient monitoring and care through coordinated AI-driven interventions.

Data Collection and Integration Agent. Powered by a controlled vocabulary to specify all data, the primary function for the data collection and integration agent is to clean, transform, and organize patient data from structured and unstructured sources. This agent prepares succinct summaries of consultant notes and formats data for human and machine consumption. All numerical data are presented graphically, including relevant historical data trends. The agent also digitally captures all orders in a structured format using a specified controlled vocabulary. This structured data feed supports the output of other agents, including documentation, treatment planning, and risk stratification, while also supplying the data structures for future training.

Diagnostic Agent. Critical illness is characterized by multiple abnormalities across a wide array of tests, ranging from plain chest X-ray, computed tomography (CT), blood cell composition, plasma chemistry, and microscopic evaluation of specimens. Additionally, life support parameters provide insights into disease severity and can inform management recommendations. These data offer a wide array of visual and numerical data to be used as input for computation, recommendation, and further training. For example, to evaluate fluid overload on chest X-rays or tissue histopathology slides, an AI agent can leverage deep learning models such as convolutional neural networks and vision transformers to analyze images like radiographs and histopathology slides.^8,9 Recurrent neural networks or transformer models process sequential data like time-series vital signs. The agent also implements ensemble methods that combine multiple machine learning algorithms to enhance diagnostic accuracy.

Risk Stratification Agent. This assesses severity and predicts potential outcomes. Morbidity and mortality risks are calculated using an established scoring system and individualized based on the history of other agents’ conditional patients. These are presented graphically, with major risk factors highlighted for explainability. 

Treatment Recommendation Agent. Using a reinforcement learning framework supplemented by up-to-date clinical guidelines, this system leverages historical data structured with standardized vocabulary to analyze patients with similar clinical features. Training is also conducted on the patient’s physiological data. All recommendations are presented via a dedicated user interface in a readable format, along with recommendations for editable, orderable items, references, and full-text snippets from previous research. Stop rules end computing if confidence in recommendations is too broad or no clear pathway can be computed with certainty, prompting human mitigation.

Resource Management Agent. This agent coordinates hospital resources using constraint programming techniques for optimal resource allocation, uses queueing theory models to predict and manage patient flow, and implements genetic algorithms for complex scheduling problems.^10,11

Monitoring and Alert Agent. By tracking patients’ progress and alerting staff to changes, this agent uses anomaly detection algorithms to identify unusual patterns in patient data and implement time-series forecasting models, such as autoregressive integrated moving average and prophet, to predict future patient states. The agent also uses stream-processing techniques for real-time data analysis.^12,13

Documentation and Reporting Agent. This agent maintains comprehensive medical records and generates reports. It employs advanced natural language processing techniques for automated report generation, uses advanced LLMs fine-tuned on medical corpora for narrative creation, and implements information-retrieval techniques to efficiently query patient records.

CLINICAL CASE STUDIES

To illustrate the functionality of a multiagent system, this report examines its application for managing sepsis. The data collection and integration agent continuously aggregates patient data from various sources, normalizing and timestamping it for consistent processing. The diagnostic agent analyzes this integrated data in real time, applying sepsis criteria and utilizing a deep learning model trained on a large sepsis dataset to detect subtle patterns.

The risk stratification agent calculates severity scores, such as the Sepsis-related Organ Failure Assessment (SOFA), quick SOFA (qSOFA), and Acute Physiology and Chronic Health Evaluation II, upon detecting a possible sepsis case.¹⁴ It predicts the likelihood of specific outcomes and estimates the potential trajectory of the patient’s condition for the next 24 to 48 hours. Based on this assessment, the treatment recommendation agent suggests an initial treatment plan, including appropriate antibiotics, fluid resuscitation protocols, and vasopressor recommendations, recommendations when indicated.

Concurrently, the resource management agent checks the availability of necessary resources and prioritizes allocation based on the severity. The monitoring agent tracks the patient’s response to interventions in real time, alerting the care team to any concerning changes or lack of expected improvement. Throughout this process, the documentation agent ensures that all actions, responses, and outcomes are meticulously recorded in a structured format and generates real-time updates for the patient’s electronic health record (EHR) and preparing summary reports for handoffs between care teams.

Administrative Workflow Support

Modern health care operations are resource-intensive, requiring coordination of advanced imaging, procedures, laboratory testing, and professional consultations.¹⁵ AI-powered health care administrative workflow systems are revolutionizing how medical facilities coordinate patient care. For patients with chronic cough, these systems seamlessly integrate scheduling, imaging, diagnostics, and follow-up care into a cohesive process that reduces administrative burden while improving patient outcomes. Through an intuitive interface and automated assistance, health care practitioners (HCPs) can track patient progress from initial consultation through diagnosis and treatment.

The process begins when an HCP enters a patient into the system, which triggers an automated CT scan scheduling system. The system considers factors like urgency, facility availability, and patient preferences to suggest optimal appointment times. Once imaging is complete, AI agents analyze the radiology reports, extract key findings, and generate structured summaries that highlight critical information such as “mild bronchial wall thickening with patchy ground-glass opacities” or “findings consistent with chronic bronchitis.”

Based on these findings, the system automatically generates evidence-based recommendations for follow-up care, such as pulmonology consultations or follow-up imaging in 3 months. These recommendations are presented to the ordering clinician, along with suggested appointment slots for specialist consultations. The system then manages the coordination of multiple appointments, ensuring each step in the patient’s care plan is properly sequenced and scheduled.

The entire process is monitored through a comprehensive dashboard that provides real-time updates on patient status, appointment schedules, and clinical recommendations. HCPs can track which patients require immediate attention, view upcoming appointments, and monitor the progress of ongoing care plans.

Multiagent AI Operation Optimization

Hospitals are complex entities that must function at different scales and respond in an agile, timely manner at all hours, deploying staff at various positions.¹⁶ A system of AI agents can receive signals from sensors monitoring foot traffic in the emergency department and trauma unit, as well as the availability of operating room staff, equipment, and intensive care unit beds. Smart sensors enable this monitoring through IoT networks. These networks benefit from advances in adaptive and consensus networking algorithms, along with recent advances in bioengineering and biocomputing.¹⁷

For example, in the case of imaging for suspected abdominal obstruction, an AI agent tasked with scheduling CTs could time the patient’s arrival based on acuity. Another AI agent could alert staff transporting the patient to the CT appointment, with the next location contingent on a clinical decision to proceed to the operating room. Yet another AI agent could summarize radiology interpretations and alert the surgery and anesthesia teams to a potential case, while others could notify operating room staff of equipment needs or reserve a bed. In this paradigm, AI agents facilitate more precise and timely communication between multiple staff members.

TECHNICAL IMPLEMENTATION

Large Language Models

Each agent uses a different LLM optimized for its specific task. For example, the diagnostic agent uses an LLM pretrained on a large corpus of biomedical literature and fine-tuned on a dataset of confirmed sepsis cases and their presentations.¹⁸ It implements few-shot learning techniques to adapt to rare or atypical presentations. The treatment recommendation agent also uses an LLM, employing a retrieval-augmented generation approach to access the latest clinical guidelines during inference. The documentation agent uses another advanced language model, fine-tuned on a large corpus of high-quality medical documentation, implementing controlled text generation techniques and utilizing a separate smaller model for real-time error checking and correction.

Interagent Quality Control

Agents learn from their own experience and the experience of other agents. They are equipped with user-defined rule-based and model-based systems for quality assurance, with clear stopping rules for human involvement and mitigation.

Sophisticated quality control measures bolster the system’s reliability, including ensemble techniques for result comparison, redundancy for critical tasks, and automatic human review for disagreements above a certain threshold. Each agent provides a calibrated confidence score with its output, used to weigh inputs in downstream tasks and trigger additional checks for low-confidence outputs.

A dedicated quality control agent monitors output from all agents, employing both supervised and unsupervised anomaly detection techniques. Feedback loops allow agents to evaluate the quality and utility of information received from other agents. The system implements a multiarmed bandit approach to dynamically adjust the influence of different agents based on their performance and periodically retrains agent models using federated learning techniques.¹⁹

Electronic Health Record Integration

Seamless EHR integration is crucial for practical implementation. The system has secure application programming interface access to various EHR platforms, implements OAuth 2.0 for authentication, and use HTTPS with perfect forward secrecy for all communications.²⁰ It works with HL7 FHIR to ensure interoperability and uses SNOMED CT for clinical terminology to ensure semantic interoperability across different EHRs.^21,22

The system implements a multilevel approval system for write-backs to EHRs, with different thresholds based on the information’s criticality. It uses digital signatures to ensure the integrity and nonrepudiation of AI-generated entries and implements blockchain technology to create an immutable and distributed ledger of all AI system actions.²³

Decision Transparency

To ensure transparency in decision-making processes, the system applies techniques (eg, local interpretable model-agnostic explanations and Shapley additive explanations) to provide insights into agent decision-making processes.^24-26 It provides customized visualizations for different stakeholders and allows users to explore alternative decision paths through what-if scenario modeling.²⁷

The system provides calibrated confidence indicators for each recommendation or decision, implementing a novel confidence calibration agent that continuously monitors and adjusts confidence scores based on observed outcomes.

Continuous Learning and Adaptation

The system employs several techniques to remain current with evolving medical knowledge. Federated learning includes information from diverse datasets across multiple institutions without compromising patient privacy.²⁸ A/B testing is used to safely deploy and compare new agent versions in controlled settings, implementing multiarmed bandit algorithms to efficiently explore new models while minimizing potential negative impacts. Human-in-the-loop learning and active learning techniques are used to incorporate feedback from HCPs and efficiently solicit expert input on the most informative data.²⁹

CLINICAL IMPLICATIONS

The implementation of multiagent AI systems in health care has several potential benefits: enhanced diagnostic accuracy, personalized treatment, improved efficiency, continuous monitoring, and resource optimization. A recent review of AI sepsis predictive models exhibited superior results to standard clinical scoring methods like qSOFA.³⁰ In oncology, such systems can result in more tailored treatments, enhancing outcomes.³¹ The implementation of an ambient dictation system can improve workflow and prevent HCP burnout.³²

ETHICAL CONSIDERATIONS AND AI OVERSIGHT

Integrating AI agents into health care raises significant ethical considerations that must be carefully addressed to ensure equitable and effective care delivery. One primary concern involves cultural and linguistic competency, as AI systems may struggle with cultural nuances, idioms, and context-specific communication patterns. This becomes particularly challenging in regions with diverse ethnic populations or immigrant communities, where medical terminology may not have direct translations and cultural beliefs significantly influence health care decisions. AI systems also may inherit and amplify existing biases in health care delivery, whether through HCP bias reflected in training data, patient bias affecting acceptance of AI-assisted care, or demographic underrepresentation during system development.

AI agents present unique opportunities for improving health care access and outcomes through community engagement, though such initiatives require thoughtful implementation. Predictive analytics can identify high-risk individuals within communities who may benefit from preventive care, while analysis of social determinants of health can enable more targeted interventions. However, these capabilities must be balanced with privacy concerns and the risk of surveillance, particularly in communities that distrust health care institutions. The potential for AI to bridge health care gaps must be weighed against the need to maintain cultural sensitivity and community trust.

The governance and oversight of health care AI systems requires a multistakeholder approach with clear lines of responsibility and accountability. This includes involvement from government health care agencies, professional medical associations, ethics boards, and independent auditors, all working together to establish and enforce standards while monitoring system performance and addressing potential biases. Health care organizations must maintain transparent policies about AI use, implement regular monitoring and evaluation protocols, and establish precise mechanisms for patient feedback and grievance resolution. Ongoing assessment and adjustment of these systems, informed by community feedback and outcomes data, will be crucial for their ethical implementation, ensuring that AI agents complement, rather than replace, human judgment and cultural sensitivity.

FUTURE DIRECTIONS

Despite the potential benefits, implementing multiagent AI systems in health care faces significant challenges that require careful consideration. Beyond the fundamental issues such as data quality and bias mitigation, health care organizations struggle with fragmented systems, inconsistent data formats, and varying quality. Technical infrastructure requirements are substantial, particularly in rural or underserved areas that lack robust networks and cybersecurity. HCPs already face significant cognitive load and time pressures, making integrating AI agents into existing workflows particularly challenging. There is also the critical issue of transparency and interpretability, as health care decisions require clear reasoning and accountability that many black-box AI systems struggle to provide.

The legal landscape introduces another layer of complexity, particularly regarding liability, consent, and privacy questions. When AI agents contribute to medical decisions, establishing clear lines of responsibility becomes crucial. There are also serious concerns about algorithmic fairness and the potential for AI systems to perpetuate or amplify existing inequities. The cost of implementation remains a significant barrier, requiring substantial investment in technology, training, and ongoing maintenance while ensuring resources are not diverted from direct patient care. Moreover, HCPs may resist adoption due to concerns about job security, loss of autonomy, or skepticism about AI capabilities while paradoxically facing risks of overreliance on AI systems that could lead to the degradation of human clinical skills.

Addressing these challenges requires a multifaceted approach that combines technical solutions with organizational and policy changes. Health care organizations must implement rigorous data validation processes and interoperability standards while developing hybrid models that balance sophisticated AI capabilities with interpretable techniques. Extensive research and iterative design processes, with direct input from HCPs, are essential for successful integration. Establishing independent ethics boards to oversee system development and deployment, conducting multicenter randomized controlled trials, and creating clear regulatory frameworks will ensure safe and effective implementation. Success will ultimately depend on ongoing collaboration between technology developers, HCPs, policymakers, and patients, maintaining a steady focus on improving patient care and outcomes while carefully navigating the complex challenges of AI integration in health care.^33-35

As multiagent AI systems in health care evolve, several exciting directions emerge. These include the integration of IoT and wearable devices, the development of more sophisticated natural language interfaces, and applying these systems to predictive maintenance of medical equipment.

CONCLUSIONS

The advent of multiagent AI systems in health care represents a paradigm shift in the approach to patient care, clinical decision making, and health care management. While these systems offer immense potential to transform health care delivery, their development and implementation must be guided by rigorous scientific validation, ethical considerations, and a patient-centered approach. The ultimate goal remains clear: harnessing the power of AI to improve patient outcomes, enhance the efficiency of health care delivery, and ultimately advance the health and well-being of patients.

Artificial intelligence (AI) is rapidly evolving, with large language models (LLMs) marking a significant milestone in processing and generating human-like responses to natural language prompts. However, this advancement only signals the beginning of a more profound transformation in AI capabilities. The development of AI agents represents a new paradigm at the forefront of this evolution.

BACKGROUND

AI agents represent a leap forward from traditional LLM applications. While definitions may vary slightly among technology developers, the core concept remains: these agents are autonomous software entities designed to interact with their environment, make independent decisions, and execute tasks based on predefined goals.^1-3 What sets AI agents apart is their combination of sophisticated components within structured architectures. At their core, AI agents incorporate an LLM for response generation, which is augmented by a suite of tools to optimize workflow and complete tasks, memory capabilities for personalized interactions, and autonomous reasoning. This combination allows AI agents to plan, create subtasks, gather information, and learn iteratively from their own experiences or other AI agents.

The true potential of this technology becomes apparent when multiple AI agents collaborate within multiagent AI systems. This concept introduces a new level of flexibility and capability in tackling complex tasks. Autogen, CrewAI, and LangChain offer various agent network configurations, including hierarchical, sequential, conditional, or even parallel task execution.^4-6 This adaptability opens up a world of possibilities across various industries, but perhaps nowhere is the potential impact more exciting and profound than in health care.

AI agents in health care present an opportunity to revolutionize patient care, streamline administrative processes, and support complex clinical decision-making. This review examines 3 scenarios that illustrate the impact of AI agents in health care: a hypothetical sepsis management system, chronic disease management, and hospital patient flow optimization. This article will provide a detailed look at the technical implementation challenges, including the integration with existing health care IT systems, data privacy considerations, and the crucial role of explainable AI in maintaining trust and transparency.

It is challenging to implement AI agents in health care. Concerns include ensuring data quality and mitigating bias, seamlessly integrating these systems into existing clinical workflows, and navigating the complex ethical considerations that arise when deploying autonomous systems in health care. The integration with Internet of Things (IoT) devices for real-time patient data monitoring and the development of more sophisticated natural language interfaces to enhance future human-AI collaboration.

The adoption of AI agents in health care is only beginning, and it promises to be transformative. As AI continues to evolve, a comprehensive understanding of its applications, limitations, and ethical considerations is essential. This report provides a comprehensive overview of the current state, potential applications, and future directions of AI agents in health care, offering insights valuable to researchers, clinicians, and policymakers.

MultiAgent AI architecture

Sepsis Management

Despite advancements in broad-spectrum antibiotics, imaging, and life support systems, mortality rates associated with sepsis remain high. The complexity of optimizing care in clinical settings has hindered progress in managing sepsis. Previous attempts to develop predictive sepsis models have proven challenging.⁷ This report proposes a multiagent AI system designed to enhance comprehensive patient monitoring and care through coordinated AI-driven interventions.

Data Collection and Integration Agent. Powered by a controlled vocabulary to specify all data, the primary function for the data collection and integration agent is to clean, transform, and organize patient data from structured and unstructured sources. This agent prepares succinct summaries of consultant notes and formats data for human and machine consumption. All numerical data are presented graphically, including relevant historical data trends. The agent also digitally captures all orders in a structured format using a specified controlled vocabulary. This structured data feed supports the output of other agents, including documentation, treatment planning, and risk stratification, while also supplying the data structures for future training.

Diagnostic Agent. Critical illness is characterized by multiple abnormalities across a wide array of tests, ranging from plain chest X-ray, computed tomography (CT), blood cell composition, plasma chemistry, and microscopic evaluation of specimens. Additionally, life support parameters provide insights into disease severity and can inform management recommendations. These data offer a wide array of visual and numerical data to be used as input for computation, recommendation, and further training. For example, to evaluate fluid overload on chest X-rays or tissue histopathology slides, an AI agent can leverage deep learning models such as convolutional neural networks and vision transformers to analyze images like radiographs and histopathology slides.^8,9 Recurrent neural networks or transformer models process sequential data like time-series vital signs. The agent also implements ensemble methods that combine multiple machine learning algorithms to enhance diagnostic accuracy.

Risk Stratification Agent. This assesses severity and predicts potential outcomes. Morbidity and mortality risks are calculated using an established scoring system and individualized based on the history of other agents’ conditional patients. These are presented graphically, with major risk factors highlighted for explainability. 

Treatment Recommendation Agent. Using a reinforcement learning framework supplemented by up-to-date clinical guidelines, this system leverages historical data structured with standardized vocabulary to analyze patients with similar clinical features. Training is also conducted on the patient’s physiological data. All recommendations are presented via a dedicated user interface in a readable format, along with recommendations for editable, orderable items, references, and full-text snippets from previous research. Stop rules end computing if confidence in recommendations is too broad or no clear pathway can be computed with certainty, prompting human mitigation.

Resource Management Agent. This agent coordinates hospital resources using constraint programming techniques for optimal resource allocation, uses queueing theory models to predict and manage patient flow, and implements genetic algorithms for complex scheduling problems.^10,11

Monitoring and Alert Agent. By tracking patients’ progress and alerting staff to changes, this agent uses anomaly detection algorithms to identify unusual patterns in patient data and implement time-series forecasting models, such as autoregressive integrated moving average and prophet, to predict future patient states. The agent also uses stream-processing techniques for real-time data analysis.^12,13

Documentation and Reporting Agent. This agent maintains comprehensive medical records and generates reports. It employs advanced natural language processing techniques for automated report generation, uses advanced LLMs fine-tuned on medical corpora for narrative creation, and implements information-retrieval techniques to efficiently query patient records.

CLINICAL CASE STUDIES

To illustrate the functionality of a multiagent system, this report examines its application for managing sepsis. The data collection and integration agent continuously aggregates patient data from various sources, normalizing and timestamping it for consistent processing. The diagnostic agent analyzes this integrated data in real time, applying sepsis criteria and utilizing a deep learning model trained on a large sepsis dataset to detect subtle patterns.

The risk stratification agent calculates severity scores, such as the Sepsis-related Organ Failure Assessment (SOFA), quick SOFA (qSOFA), and Acute Physiology and Chronic Health Evaluation II, upon detecting a possible sepsis case.¹⁴ It predicts the likelihood of specific outcomes and estimates the potential trajectory of the patient’s condition for the next 24 to 48 hours. Based on this assessment, the treatment recommendation agent suggests an initial treatment plan, including appropriate antibiotics, fluid resuscitation protocols, and vasopressor recommendations, recommendations when indicated.

Concurrently, the resource management agent checks the availability of necessary resources and prioritizes allocation based on the severity. The monitoring agent tracks the patient’s response to interventions in real time, alerting the care team to any concerning changes or lack of expected improvement. Throughout this process, the documentation agent ensures that all actions, responses, and outcomes are meticulously recorded in a structured format and generates real-time updates for the patient’s electronic health record (EHR) and preparing summary reports for handoffs between care teams.

Administrative Workflow Support

Modern health care operations are resource-intensive, requiring coordination of advanced imaging, procedures, laboratory testing, and professional consultations.¹⁵ AI-powered health care administrative workflow systems are revolutionizing how medical facilities coordinate patient care. For patients with chronic cough, these systems seamlessly integrate scheduling, imaging, diagnostics, and follow-up care into a cohesive process that reduces administrative burden while improving patient outcomes. Through an intuitive interface and automated assistance, health care practitioners (HCPs) can track patient progress from initial consultation through diagnosis and treatment.

The process begins when an HCP enters a patient into the system, which triggers an automated CT scan scheduling system. The system considers factors like urgency, facility availability, and patient preferences to suggest optimal appointment times. Once imaging is complete, AI agents analyze the radiology reports, extract key findings, and generate structured summaries that highlight critical information such as “mild bronchial wall thickening with patchy ground-glass opacities” or “findings consistent with chronic bronchitis.”

Based on these findings, the system automatically generates evidence-based recommendations for follow-up care, such as pulmonology consultations or follow-up imaging in 3 months. These recommendations are presented to the ordering clinician, along with suggested appointment slots for specialist consultations. The system then manages the coordination of multiple appointments, ensuring each step in the patient’s care plan is properly sequenced and scheduled.

The entire process is monitored through a comprehensive dashboard that provides real-time updates on patient status, appointment schedules, and clinical recommendations. HCPs can track which patients require immediate attention, view upcoming appointments, and monitor the progress of ongoing care plans.

Multiagent AI Operation Optimization

Hospitals are complex entities that must function at different scales and respond in an agile, timely manner at all hours, deploying staff at various positions.¹⁶ A system of AI agents can receive signals from sensors monitoring foot traffic in the emergency department and trauma unit, as well as the availability of operating room staff, equipment, and intensive care unit beds. Smart sensors enable this monitoring through IoT networks. These networks benefit from advances in adaptive and consensus networking algorithms, along with recent advances in bioengineering and biocomputing.¹⁷

For example, in the case of imaging for suspected abdominal obstruction, an AI agent tasked with scheduling CTs could time the patient’s arrival based on acuity. Another AI agent could alert staff transporting the patient to the CT appointment, with the next location contingent on a clinical decision to proceed to the operating room. Yet another AI agent could summarize radiology interpretations and alert the surgery and anesthesia teams to a potential case, while others could notify operating room staff of equipment needs or reserve a bed. In this paradigm, AI agents facilitate more precise and timely communication between multiple staff members.

TECHNICAL IMPLEMENTATION

Large Language Models

Each agent uses a different LLM optimized for its specific task. For example, the diagnostic agent uses an LLM pretrained on a large corpus of biomedical literature and fine-tuned on a dataset of confirmed sepsis cases and their presentations.¹⁸ It implements few-shot learning techniques to adapt to rare or atypical presentations. The treatment recommendation agent also uses an LLM, employing a retrieval-augmented generation approach to access the latest clinical guidelines during inference. The documentation agent uses another advanced language model, fine-tuned on a large corpus of high-quality medical documentation, implementing controlled text generation techniques and utilizing a separate smaller model for real-time error checking and correction.

Interagent Quality Control

Agents learn from their own experience and the experience of other agents. They are equipped with user-defined rule-based and model-based systems for quality assurance, with clear stopping rules for human involvement and mitigation.

Sophisticated quality control measures bolster the system’s reliability, including ensemble techniques for result comparison, redundancy for critical tasks, and automatic human review for disagreements above a certain threshold. Each agent provides a calibrated confidence score with its output, used to weigh inputs in downstream tasks and trigger additional checks for low-confidence outputs.

A dedicated quality control agent monitors output from all agents, employing both supervised and unsupervised anomaly detection techniques. Feedback loops allow agents to evaluate the quality and utility of information received from other agents. The system implements a multiarmed bandit approach to dynamically adjust the influence of different agents based on their performance and periodically retrains agent models using federated learning techniques.¹⁹

Electronic Health Record Integration

Seamless EHR integration is crucial for practical implementation. The system has secure application programming interface access to various EHR platforms, implements OAuth 2.0 for authentication, and use HTTPS with perfect forward secrecy for all communications.²⁰ It works with HL7 FHIR to ensure interoperability and uses SNOMED CT for clinical terminology to ensure semantic interoperability across different EHRs.^21,22

The system implements a multilevel approval system for write-backs to EHRs, with different thresholds based on the information’s criticality. It uses digital signatures to ensure the integrity and nonrepudiation of AI-generated entries and implements blockchain technology to create an immutable and distributed ledger of all AI system actions.²³

Decision Transparency

To ensure transparency in decision-making processes, the system applies techniques (eg, local interpretable model-agnostic explanations and Shapley additive explanations) to provide insights into agent decision-making processes.^24-26 It provides customized visualizations for different stakeholders and allows users to explore alternative decision paths through what-if scenario modeling.²⁷

The system provides calibrated confidence indicators for each recommendation or decision, implementing a novel confidence calibration agent that continuously monitors and adjusts confidence scores based on observed outcomes.

Continuous Learning and Adaptation

The system employs several techniques to remain current with evolving medical knowledge. Federated learning includes information from diverse datasets across multiple institutions without compromising patient privacy.²⁸ A/B testing is used to safely deploy and compare new agent versions in controlled settings, implementing multiarmed bandit algorithms to efficiently explore new models while minimizing potential negative impacts. Human-in-the-loop learning and active learning techniques are used to incorporate feedback from HCPs and efficiently solicit expert input on the most informative data.²⁹

CLINICAL IMPLICATIONS

The implementation of multiagent AI systems in health care has several potential benefits: enhanced diagnostic accuracy, personalized treatment, improved efficiency, continuous monitoring, and resource optimization. A recent review of AI sepsis predictive models exhibited superior results to standard clinical scoring methods like qSOFA.³⁰ In oncology, such systems can result in more tailored treatments, enhancing outcomes.³¹ The implementation of an ambient dictation system can improve workflow and prevent HCP burnout.³²

ETHICAL CONSIDERATIONS AND AI OVERSIGHT

Integrating AI agents into health care raises significant ethical considerations that must be carefully addressed to ensure equitable and effective care delivery. One primary concern involves cultural and linguistic competency, as AI systems may struggle with cultural nuances, idioms, and context-specific communication patterns. This becomes particularly challenging in regions with diverse ethnic populations or immigrant communities, where medical terminology may not have direct translations and cultural beliefs significantly influence health care decisions. AI systems also may inherit and amplify existing biases in health care delivery, whether through HCP bias reflected in training data, patient bias affecting acceptance of AI-assisted care, or demographic underrepresentation during system development.

AI agents present unique opportunities for improving health care access and outcomes through community engagement, though such initiatives require thoughtful implementation. Predictive analytics can identify high-risk individuals within communities who may benefit from preventive care, while analysis of social determinants of health can enable more targeted interventions. However, these capabilities must be balanced with privacy concerns and the risk of surveillance, particularly in communities that distrust health care institutions. The potential for AI to bridge health care gaps must be weighed against the need to maintain cultural sensitivity and community trust.

The governance and oversight of health care AI systems requires a multistakeholder approach with clear lines of responsibility and accountability. This includes involvement from government health care agencies, professional medical associations, ethics boards, and independent auditors, all working together to establish and enforce standards while monitoring system performance and addressing potential biases. Health care organizations must maintain transparent policies about AI use, implement regular monitoring and evaluation protocols, and establish precise mechanisms for patient feedback and grievance resolution. Ongoing assessment and adjustment of these systems, informed by community feedback and outcomes data, will be crucial for their ethical implementation, ensuring that AI agents complement, rather than replace, human judgment and cultural sensitivity.

FUTURE DIRECTIONS

Despite the potential benefits, implementing multiagent AI systems in health care faces significant challenges that require careful consideration. Beyond the fundamental issues such as data quality and bias mitigation, health care organizations struggle with fragmented systems, inconsistent data formats, and varying quality. Technical infrastructure requirements are substantial, particularly in rural or underserved areas that lack robust networks and cybersecurity. HCPs already face significant cognitive load and time pressures, making integrating AI agents into existing workflows particularly challenging. There is also the critical issue of transparency and interpretability, as health care decisions require clear reasoning and accountability that many black-box AI systems struggle to provide.

The legal landscape introduces another layer of complexity, particularly regarding liability, consent, and privacy questions. When AI agents contribute to medical decisions, establishing clear lines of responsibility becomes crucial. There are also serious concerns about algorithmic fairness and the potential for AI systems to perpetuate or amplify existing inequities. The cost of implementation remains a significant barrier, requiring substantial investment in technology, training, and ongoing maintenance while ensuring resources are not diverted from direct patient care. Moreover, HCPs may resist adoption due to concerns about job security, loss of autonomy, or skepticism about AI capabilities while paradoxically facing risks of overreliance on AI systems that could lead to the degradation of human clinical skills.

Addressing these challenges requires a multifaceted approach that combines technical solutions with organizational and policy changes. Health care organizations must implement rigorous data validation processes and interoperability standards while developing hybrid models that balance sophisticated AI capabilities with interpretable techniques. Extensive research and iterative design processes, with direct input from HCPs, are essential for successful integration. Establishing independent ethics boards to oversee system development and deployment, conducting multicenter randomized controlled trials, and creating clear regulatory frameworks will ensure safe and effective implementation. Success will ultimately depend on ongoing collaboration between technology developers, HCPs, policymakers, and patients, maintaining a steady focus on improving patient care and outcomes while carefully navigating the complex challenges of AI integration in health care.^33-35

As multiagent AI systems in health care evolve, several exciting directions emerge. These include the integration of IoT and wearable devices, the development of more sophisticated natural language interfaces, and applying these systems to predictive maintenance of medical equipment.

CONCLUSIONS

The advent of multiagent AI systems in health care represents a paradigm shift in the approach to patient care, clinical decision making, and health care management. While these systems offer immense potential to transform health care delivery, their development and implementation must be guided by rigorous scientific validation, ethical considerations, and a patient-centered approach. The ultimate goal remains clear: harnessing the power of AI to improve patient outcomes, enhance the efficiency of health care delivery, and ultimately advance the health and well-being of patients.

Worldwide, it is estimated that up to 1 in 5 individuals will experience a dermatophyte infection (commonly called ringworm or tinea infection) in their lifetime.¹ Historically, dermatophyte infections have been considered relatively minor conditions usually treated with short courses of topical antifungals.² Oral antifungals historically were needed only for patients with nail or hair shaft infections or extensive cutaneous fungal infections, which typically occurred in immunosuppressed patients.² However, the landscape is changing rapidly due to the global emergence of severe dermatophyte infections that frequently are resistant to first-line antifungal medications.^3-5 In this article, we aimed to review the epidemiology of emerging dermatophyte infections and provide dermatologists with information needed for effective diagnosis and management.

Emergence of Trichophyton indotineae

In recent decades, public health officials and dermatologists have noted with concern the spread of the recently emerged dermatophyte species Trichophyton indotineae in South Asia.^3,6 This species (previously known as Trichophyton mentagrophytes genotype VIII) usually is transmitted from person to person, either through direct skin-to-skin contact or by fomites.^4,6 Potential sexual transmission of T indotineae infections also has been reported,⁷ and it is possible that animals may serve as reservoirs for this pathogen, although there are no known reports of direct spread from animals to humans.^8,9 Major outbreaks of T indotineae are ongoing in South Asia, and cases have been documented in 6 continents.^10-12 In the United States, most but not all cases have occurred in immigrants from or recently returned travelers to South Asia.^6,13 The emergence and spread of T indotineae is hypothesized to be promoted by the misuse and overuse of topical antifungal products, particularly those containing combinations of potent corticosteroids with other antimicrobial drugs.^14,15

Cutaneous manifestations of T indotineae infections tend to cover large body surface areas, recur frequently, and pose substantial treatment challenges.^6,13,16 Several clinical presentations have been documented, including erythematous, scaly concentric plaques; papulosquamous lesions; pustular forms; and corticosteroid-modified disease (Figure 1).^6,16 Affected patients seldom are immunocompromised and often have a history of multiple failed courses of topical or oral antifungals, including oral terbinafine.¹³ Many also have been prescribed topical corticosteroids or have used over-the-counter topical corticosteroids, which worsen the rash.¹⁷

Direct microscopy with potassium hydroxide could be used to confirm the diagnosis of dermatophyte infection, but it does not distinguish T indotineae from other dermatophyte species.^2,6 Importantly, culture-based testing usually will misidentify T indotineae as other Trichophyton species such as the more common T mentagrophytes or Trichophyton interdigitale. Definitive identification of T indotineae requires advanced molecular techniques that are available only at select laboratories.⁶ Unfortunately, availability of such testing is limited (Table), and results may take several weeks; therefore, it is suggested that dermatologists who suspect T indotineae infections based on the patient’s history and clinical presentation begin antifungal treatment after confirmation of dermatophyte infection but not wait for definitive confirmation of the causative organism.¹⁶

Itraconazole is considered the first-line therapy for T indotineae infection, as terbinafine usually is ineffective due to mutations in the squalene epoxidase gene.¹⁶ Dermatologists should be aware that itraconazole is available in different formulations that can affect absorption. The oral solution has greater bioavailability and should be taken on an empty stomach, whereas the capsules are required to be taken with food for effective absorption; the capsules also should be taken with an acidic beverage such as orange juice. Dermatologists should carefully assess for drug-drug interactions when prescribing itraconazole, given its extensive interaction profile with numerous other medications. Patients may require treatment with itraconazole (100 mg/d or 200 mg/d) for a minimum of 6 to 8 weeks until complete clearance has been achieved and ideally a negative potassium hydroxide preparation of skin scrapings has been obtained. A longer treatment period (eg, ≥3 months) frequently is needed, and relapses are common.^6,16,18 Regular follow-up is needed to monitor for infection clearance and recurrences. It is important to note that cases of itraconazole resistance have been reported, although this currently appears to be uncommon.^19,20

Other Emerging Dermatophytes to Watch

Trichophyton rubrum is the most common cause of dermatophyte infections among humans,²¹ and cases of terbinafine-resistant T rubrum infections have been reported increasingly in the United States and Canada.^5,22-24 Onychomycosis caused by terbinafine-resistant T rubrum has been documented, and patients may have infections that do not respond to terbinafine given at the standard dose and duration.^22,23 Case reports have indicated successful treatment using itraconazole 200 mg/d and posaconazole 300 mg/d.^5,23

Trichophyton mentagrophytes genotype VII (TMVII) is an emerging dermatophyte that recently has been reported as a cause of sexually transmitted dermatophyte infections in Europe and the United States primarily affecting men who have sex with men.^25-27 Patients may present with pruritic, annular, scaly patches and plaques involving the trunk, groin, genital region, or face (Figure 2). Although closely related to T indotineae, TMVII differs in that it more often affects the genital region, generally is susceptible to terbinafine, and in the United States and Europe usually is not related to travel or immigration involving South Asia.²⁶ Although TMVII has not been associated with antifungal resistance, awareness among dermatologists is important because patients may experience inflamed, painful, and persistent rashes that can lead to secondary bacterial infection or scarring, and physicians might mistake it for mimics including eczema or psoriasis.^25,26

Importance of Judicious Antifungal Use

Optimizing the use of antifungals is critical to improving patient outcomes and preserving available treatment options.^28,29 A retrospective analysis of commercial health insurance data estimated that topical antifungal prescriptions were potentially unnecessary for more than half of the more than 560,000 patients who were prescribed these medications in 2023. In this study, it also was observed that only 16% of patients prescribed a topical antifungal had received diagnostic testing, with low rates across specialties.³⁰ This is concerning because even among board-certified dermatologists, incorrect diagnosis of suspected fungal skin infections can occur; in one survey-based study of board-certified dermatologists who were presented with dermatomycosis images, respondents categorized cases with greater than 75% accuracy in only 31% (4/13) of instances.³¹ Clotrimazole-betamethasone is among the most commonly prescribed topical antifungals in the United States,^14,32 and 2 recent retrospective analyses highlighted that the majority of patients prescribed this medication did not receive any fungal diagnostic testing.^33,34

Final Thoughts

In an era of emerging antifungal-resistant dermatophyte infections, it is important for dermatologists to educate nondermatologists about the importance of using diagnostic testing for suspected dermatophyte infections.^14,28 Dermatologists also can educate nondermatologist colleagues on the importance of avoiding the use of topical combination antifungal/corticosteroid medications and referring for dermatologic evaluation when diagnoses are uncertain.^33,34 Strategies for education by dermatologists could include giving workshops, creating educational materials, and fostering open communication about optimal treatment practices and referral parameters for suspected dermatophyte infections.

Worldwide, it is estimated that up to 1 in 5 individuals will experience a dermatophyte infection (commonly called ringworm or tinea infection) in their lifetime.¹ Historically, dermatophyte infections have been considered relatively minor conditions usually treated with short courses of topical antifungals.² Oral antifungals historically were needed only for patients with nail or hair shaft infections or extensive cutaneous fungal infections, which typically occurred in immunosuppressed patients.² However, the landscape is changing rapidly due to the global emergence of severe dermatophyte infections that frequently are resistant to first-line antifungal medications.^3-5 In this article, we aimed to review the epidemiology of emerging dermatophyte infections and provide dermatologists with information needed for effective diagnosis and management.

Emergence of Trichophyton indotineae

In recent decades, public health officials and dermatologists have noted with concern the spread of the recently emerged dermatophyte species Trichophyton indotineae in South Asia.^3,6 This species (previously known as Trichophyton mentagrophytes genotype VIII) usually is transmitted from person to person, either through direct skin-to-skin contact or by fomites.^4,6 Potential sexual transmission of T indotineae infections also has been reported,⁷ and it is possible that animals may serve as reservoirs for this pathogen, although there are no known reports of direct spread from animals to humans.^8,9 Major outbreaks of T indotineae are ongoing in South Asia, and cases have been documented in 6 continents.^10-12 In the United States, most but not all cases have occurred in immigrants from or recently returned travelers to South Asia.^6,13 The emergence and spread of T indotineae is hypothesized to be promoted by the misuse and overuse of topical antifungal products, particularly those containing combinations of potent corticosteroids with other antimicrobial drugs.^14,15

Cutaneous manifestations of T indotineae infections tend to cover large body surface areas, recur frequently, and pose substantial treatment challenges.^6,13,16 Several clinical presentations have been documented, including erythematous, scaly concentric plaques; papulosquamous lesions; pustular forms; and corticosteroid-modified disease (Figure 1).^6,16 Affected patients seldom are immunocompromised and often have a history of multiple failed courses of topical or oral antifungals, including oral terbinafine.¹³ Many also have been prescribed topical corticosteroids or have used over-the-counter topical corticosteroids, which worsen the rash.¹⁷

Direct microscopy with potassium hydroxide could be used to confirm the diagnosis of dermatophyte infection, but it does not distinguish T indotineae from other dermatophyte species.^2,6 Importantly, culture-based testing usually will misidentify T indotineae as other Trichophyton species such as the more common T mentagrophytes or Trichophyton interdigitale. Definitive identification of T indotineae requires advanced molecular techniques that are available only at select laboratories.⁶ Unfortunately, availability of such testing is limited (Table), and results may take several weeks; therefore, it is suggested that dermatologists who suspect T indotineae infections based on the patient’s history and clinical presentation begin antifungal treatment after confirmation of dermatophyte infection but not wait for definitive confirmation of the causative organism.¹⁶

Itraconazole is considered the first-line therapy for T indotineae infection, as terbinafine usually is ineffective due to mutations in the squalene epoxidase gene.¹⁶ Dermatologists should be aware that itraconazole is available in different formulations that can affect absorption. The oral solution has greater bioavailability and should be taken on an empty stomach, whereas the capsules are required to be taken with food for effective absorption; the capsules also should be taken with an acidic beverage such as orange juice. Dermatologists should carefully assess for drug-drug interactions when prescribing itraconazole, given its extensive interaction profile with numerous other medications. Patients may require treatment with itraconazole (100 mg/d or 200 mg/d) for a minimum of 6 to 8 weeks until complete clearance has been achieved and ideally a negative potassium hydroxide preparation of skin scrapings has been obtained. A longer treatment period (eg, ≥3 months) frequently is needed, and relapses are common.^6,16,18 Regular follow-up is needed to monitor for infection clearance and recurrences. It is important to note that cases of itraconazole resistance have been reported, although this currently appears to be uncommon.^19,20

Other Emerging Dermatophytes to Watch

Trichophyton rubrum is the most common cause of dermatophyte infections among humans,²¹ and cases of terbinafine-resistant T rubrum infections have been reported increasingly in the United States and Canada.^5,22-24 Onychomycosis caused by terbinafine-resistant T rubrum has been documented, and patients may have infections that do not respond to terbinafine given at the standard dose and duration.^22,23 Case reports have indicated successful treatment using itraconazole 200 mg/d and posaconazole 300 mg/d.^5,23

Trichophyton mentagrophytes genotype VII (TMVII) is an emerging dermatophyte that recently has been reported as a cause of sexually transmitted dermatophyte infections in Europe and the United States primarily affecting men who have sex with men.^25-27 Patients may present with pruritic, annular, scaly patches and plaques involving the trunk, groin, genital region, or face (Figure 2). Although closely related to T indotineae, TMVII differs in that it more often affects the genital region, generally is susceptible to terbinafine, and in the United States and Europe usually is not related to travel or immigration involving South Asia.²⁶ Although TMVII has not been associated with antifungal resistance, awareness among dermatologists is important because patients may experience inflamed, painful, and persistent rashes that can lead to secondary bacterial infection or scarring, and physicians might mistake it for mimics including eczema or psoriasis.^25,26

Importance of Judicious Antifungal Use

Optimizing the use of antifungals is critical to improving patient outcomes and preserving available treatment options.^28,29 A retrospective analysis of commercial health insurance data estimated that topical antifungal prescriptions were potentially unnecessary for more than half of the more than 560,000 patients who were prescribed these medications in 2023. In this study, it also was observed that only 16% of patients prescribed a topical antifungal had received diagnostic testing, with low rates across specialties.³⁰ This is concerning because even among board-certified dermatologists, incorrect diagnosis of suspected fungal skin infections can occur; in one survey-based study of board-certified dermatologists who were presented with dermatomycosis images, respondents categorized cases with greater than 75% accuracy in only 31% (4/13) of instances.³¹ Clotrimazole-betamethasone is among the most commonly prescribed topical antifungals in the United States,^14,32 and 2 recent retrospective analyses highlighted that the majority of patients prescribed this medication did not receive any fungal diagnostic testing.^33,34

Final Thoughts

In an era of emerging antifungal-resistant dermatophyte infections, it is important for dermatologists to educate nondermatologists about the importance of using diagnostic testing for suspected dermatophyte infections.^14,28 Dermatologists also can educate nondermatologist colleagues on the importance of avoiding the use of topical combination antifungal/corticosteroid medications and referring for dermatologic evaluation when diagnoses are uncertain.^33,34 Strategies for education by dermatologists could include giving workshops, creating educational materials, and fostering open communication about optimal treatment practices and referral parameters for suspected dermatophyte infections.

Worldwide, it is estimated that up to 1 in 5 individuals will experience a dermatophyte infection (commonly called ringworm or tinea infection) in their lifetime.¹ Historically, dermatophyte infections have been considered relatively minor conditions usually treated with short courses of topical antifungals.² Oral antifungals historically were needed only for patients with nail or hair shaft infections or extensive cutaneous fungal infections, which typically occurred in immunosuppressed patients.² However, the landscape is changing rapidly due to the global emergence of severe dermatophyte infections that frequently are resistant to first-line antifungal medications.^3-5 In this article, we aimed to review the epidemiology of emerging dermatophyte infections and provide dermatologists with information needed for effective diagnosis and management.

Emergence of Trichophyton indotineae

In recent decades, public health officials and dermatologists have noted with concern the spread of the recently emerged dermatophyte species Trichophyton indotineae in South Asia.^3,6 This species (previously known as Trichophyton mentagrophytes genotype VIII) usually is transmitted from person to person, either through direct skin-to-skin contact or by fomites.^4,6 Potential sexual transmission of T indotineae infections also has been reported,⁷ and it is possible that animals may serve as reservoirs for this pathogen, although there are no known reports of direct spread from animals to humans.^8,9 Major outbreaks of T indotineae are ongoing in South Asia, and cases have been documented in 6 continents.^10-12 In the United States, most but not all cases have occurred in immigrants from or recently returned travelers to South Asia.^6,13 The emergence and spread of T indotineae is hypothesized to be promoted by the misuse and overuse of topical antifungal products, particularly those containing combinations of potent corticosteroids with other antimicrobial drugs.^14,15

Cutaneous manifestations of T indotineae infections tend to cover large body surface areas, recur frequently, and pose substantial treatment challenges.^6,13,16 Several clinical presentations have been documented, including erythematous, scaly concentric plaques; papulosquamous lesions; pustular forms; and corticosteroid-modified disease (Figure 1).^6,16 Affected patients seldom are immunocompromised and often have a history of multiple failed courses of topical or oral antifungals, including oral terbinafine.¹³ Many also have been prescribed topical corticosteroids or have used over-the-counter topical corticosteroids, which worsen the rash.¹⁷

Direct microscopy with potassium hydroxide could be used to confirm the diagnosis of dermatophyte infection, but it does not distinguish T indotineae from other dermatophyte species.^2,6 Importantly, culture-based testing usually will misidentify T indotineae as other Trichophyton species such as the more common T mentagrophytes or Trichophyton interdigitale. Definitive identification of T indotineae requires advanced molecular techniques that are available only at select laboratories.⁶ Unfortunately, availability of such testing is limited (Table), and results may take several weeks; therefore, it is suggested that dermatologists who suspect T indotineae infections based on the patient’s history and clinical presentation begin antifungal treatment after confirmation of dermatophyte infection but not wait for definitive confirmation of the causative organism.¹⁶

Itraconazole is considered the first-line therapy for T indotineae infection, as terbinafine usually is ineffective due to mutations in the squalene epoxidase gene.¹⁶ Dermatologists should be aware that itraconazole is available in different formulations that can affect absorption. The oral solution has greater bioavailability and should be taken on an empty stomach, whereas the capsules are required to be taken with food for effective absorption; the capsules also should be taken with an acidic beverage such as orange juice. Dermatologists should carefully assess for drug-drug interactions when prescribing itraconazole, given its extensive interaction profile with numerous other medications. Patients may require treatment with itraconazole (100 mg/d or 200 mg/d) for a minimum of 6 to 8 weeks until complete clearance has been achieved and ideally a negative potassium hydroxide preparation of skin scrapings has been obtained. A longer treatment period (eg, ≥3 months) frequently is needed, and relapses are common.^6,16,18 Regular follow-up is needed to monitor for infection clearance and recurrences. It is important to note that cases of itraconazole resistance have been reported, although this currently appears to be uncommon.^19,20

Other Emerging Dermatophytes to Watch

Trichophyton rubrum is the most common cause of dermatophyte infections among humans,²¹ and cases of terbinafine-resistant T rubrum infections have been reported increasingly in the United States and Canada.^5,22-24 Onychomycosis caused by terbinafine-resistant T rubrum has been documented, and patients may have infections that do not respond to terbinafine given at the standard dose and duration.^22,23 Case reports have indicated successful treatment using itraconazole 200 mg/d and posaconazole 300 mg/d.^5,23

Trichophyton mentagrophytes genotype VII (TMVII) is an emerging dermatophyte that recently has been reported as a cause of sexually transmitted dermatophyte infections in Europe and the United States primarily affecting men who have sex with men.^25-27 Patients may present with pruritic, annular, scaly patches and plaques involving the trunk, groin, genital region, or face (Figure 2). Although closely related to T indotineae, TMVII differs in that it more often affects the genital region, generally is susceptible to terbinafine, and in the United States and Europe usually is not related to travel or immigration involving South Asia.²⁶ Although TMVII has not been associated with antifungal resistance, awareness among dermatologists is important because patients may experience inflamed, painful, and persistent rashes that can lead to secondary bacterial infection or scarring, and physicians might mistake it for mimics including eczema or psoriasis.^25,26

Importance of Judicious Antifungal Use

Optimizing the use of antifungals is critical to improving patient outcomes and preserving available treatment options.^28,29 A retrospective analysis of commercial health insurance data estimated that topical antifungal prescriptions were potentially unnecessary for more than half of the more than 560,000 patients who were prescribed these medications in 2023. In this study, it also was observed that only 16% of patients prescribed a topical antifungal had received diagnostic testing, with low rates across specialties.³⁰ This is concerning because even among board-certified dermatologists, incorrect diagnosis of suspected fungal skin infections can occur; in one survey-based study of board-certified dermatologists who were presented with dermatomycosis images, respondents categorized cases with greater than 75% accuracy in only 31% (4/13) of instances.³¹ Clotrimazole-betamethasone is among the most commonly prescribed topical antifungals in the United States,^14,32 and 2 recent retrospective analyses highlighted that the majority of patients prescribed this medication did not receive any fungal diagnostic testing.^33,34

Final Thoughts

In an era of emerging antifungal-resistant dermatophyte infections, it is important for dermatologists to educate nondermatologists about the importance of using diagnostic testing for suspected dermatophyte infections.^14,28 Dermatologists also can educate nondermatologist colleagues on the importance of avoiding the use of topical combination antifungal/corticosteroid medications and referring for dermatologic evaluation when diagnoses are uncertain.^33,34 Strategies for education by dermatologists could include giving workshops, creating educational materials, and fostering open communication about optimal treatment practices and referral parameters for suspected dermatophyte infections.

Lifeguards play a crucial role in ensuring water safety, but they also are uniquely positioned to promote skin cancer prevention and proper sunscreen use.^1,2 There are several benefits and challenges to offering skin cancer prevention training for lifeguards.³ We examine the advantages of training, highlight the role lifeguards can play in larger public skin cancer prevention efforts, and address practical techniques for developing lifeguardfocused skin cancer education programs. By providing this knowledge to lifeguards, we can improve community health outcomes and encourage sun-safe behaviors in high-risk outdoor locations.

Benefits of Skin Cancer Prevention Training for Lifeguards

Research has shown that lifeguards are at an elevated risk for basal cell carcinoma, squamous cell carcinoma, and melanoma due to frequent prolonged occupational sun exposure.^1,2,4-6 Therefore, comprehensive education on skin cancer prevention—including instruction on proper sunscreen application techniques and the importance of regular reapplication as well as how to recognize suspicious skin lesions—should be incorporated into lifeguard certification programs. One study evaluating the effectiveness of a skin cancer prevention program for lifeguards found that many of the participants lacked a thorough understanding of the different types of skin cancer.⁵ Another study found that lifeguards at pools in areas where societal norms supporting sun safety are stronger exhibited noticeably more sun protection practices, with regression estimates of 0.22 (95% CI, 0.17-0.26).⁷ Empowering lifeguards with valuable health knowledge during their regular training could potentially reduce their risk for skin cancer,⁴ as they may be more inclined to use sunscreen appropriately and reach out to a dermatologist for regular skin checks and evaluation of suspicious lesions.

Role of Lifeguards in Public Skin Cancer Prevention Efforts

Once trained on skin cancer prevention, lifeguards also can play a pivotal role in promoting sunscreen use among the public. Despite the widespread availability of high-quality sunscreens, many swimmers and beachgoers neglect to regularly apply or reapply sunscreen, especially on commonly exposed areas such as the back, shoulders, and face.⁸ Educating lifeguards on skin cancer prevention could enhance health outcomes by increasing early detection rates and promoting sun-safe behaviors among the general public.⁹ However, additional training requirements might increase the cost and time commitment for lifeguard certification, potentially leading to staffing shortages.^3,7 There also is a risk of lifeguards overstepping their role and providing inaccurate medical advice, which could cause distress or even lead to liability issues.⁷ Balancing these factors will be crucial in developing effective and sustainable skin cancer prevention programs for lifeguards.

Implementing Lifeguard Skin Cancer Training

Implementing skin cancer prevention training programs for lifeguards requires strategic collaboration between dermatologists, and lifeguard training organizations to ensure that the participants receive consistent and comprehensive training.¹⁰ Additionally, public health campaigns can support these efforts by raising awareness about the importance of sun safety and regular skin checks.⁶ Tailored training modules/materials, ongoing technical assistance, and active, multicomponent approaches that account for both individual and environmental factors can increase program implementation in a variety of community settings.

Final Thoughts

Through effective education, lifeguards can potentially have a substantial impact on skin cancer prevention, both among lifeguards themselves and the general public. By promoting proper sunscreen use, lifeguards can help reduce the incidence and mortality associated with skin cancers. Future studies should focus on developing and implementing targeted education initiatives for lifeguards, fostering collaboration between relevant stakeholders, and raising public awareness about the importance of sun safety and early skin cancer detection. These efforts ultimately could lead to improved public health outcomes and reduced skin cancer rates, particularly in high-risk populations that frequently are exposed to UV radiation.

Lifeguards play a crucial role in ensuring water safety, but they also are uniquely positioned to promote skin cancer prevention and proper sunscreen use.^1,2 There are several benefits and challenges to offering skin cancer prevention training for lifeguards.³ We examine the advantages of training, highlight the role lifeguards can play in larger public skin cancer prevention efforts, and address practical techniques for developing lifeguardfocused skin cancer education programs. By providing this knowledge to lifeguards, we can improve community health outcomes and encourage sun-safe behaviors in high-risk outdoor locations.

Benefits of Skin Cancer Prevention Training for Lifeguards

Research has shown that lifeguards are at an elevated risk for basal cell carcinoma, squamous cell carcinoma, and melanoma due to frequent prolonged occupational sun exposure.^1,2,4-6 Therefore, comprehensive education on skin cancer prevention—including instruction on proper sunscreen application techniques and the importance of regular reapplication as well as how to recognize suspicious skin lesions—should be incorporated into lifeguard certification programs. One study evaluating the effectiveness of a skin cancer prevention program for lifeguards found that many of the participants lacked a thorough understanding of the different types of skin cancer.⁵ Another study found that lifeguards at pools in areas where societal norms supporting sun safety are stronger exhibited noticeably more sun protection practices, with regression estimates of 0.22 (95% CI, 0.17-0.26).⁷ Empowering lifeguards with valuable health knowledge during their regular training could potentially reduce their risk for skin cancer,⁴ as they may be more inclined to use sunscreen appropriately and reach out to a dermatologist for regular skin checks and evaluation of suspicious lesions.

Role of Lifeguards in Public Skin Cancer Prevention Efforts

Once trained on skin cancer prevention, lifeguards also can play a pivotal role in promoting sunscreen use among the public. Despite the widespread availability of high-quality sunscreens, many swimmers and beachgoers neglect to regularly apply or reapply sunscreen, especially on commonly exposed areas such as the back, shoulders, and face.⁸ Educating lifeguards on skin cancer prevention could enhance health outcomes by increasing early detection rates and promoting sun-safe behaviors among the general public.⁹ However, additional training requirements might increase the cost and time commitment for lifeguard certification, potentially leading to staffing shortages.^3,7 There also is a risk of lifeguards overstepping their role and providing inaccurate medical advice, which could cause distress or even lead to liability issues.⁷ Balancing these factors will be crucial in developing effective and sustainable skin cancer prevention programs for lifeguards.

Implementing Lifeguard Skin Cancer Training

Implementing skin cancer prevention training programs for lifeguards requires strategic collaboration between dermatologists, and lifeguard training organizations to ensure that the participants receive consistent and comprehensive training.¹⁰ Additionally, public health campaigns can support these efforts by raising awareness about the importance of sun safety and regular skin checks.⁶ Tailored training modules/materials, ongoing technical assistance, and active, multicomponent approaches that account for both individual and environmental factors can increase program implementation in a variety of community settings.

Final Thoughts

Through effective education, lifeguards can potentially have a substantial impact on skin cancer prevention, both among lifeguards themselves and the general public. By promoting proper sunscreen use, lifeguards can help reduce the incidence and mortality associated with skin cancers. Future studies should focus on developing and implementing targeted education initiatives for lifeguards, fostering collaboration between relevant stakeholders, and raising public awareness about the importance of sun safety and early skin cancer detection. These efforts ultimately could lead to improved public health outcomes and reduced skin cancer rates, particularly in high-risk populations that frequently are exposed to UV radiation.

Lifeguards play a crucial role in ensuring water safety, but they also are uniquely positioned to promote skin cancer prevention and proper sunscreen use.^1,2 There are several benefits and challenges to offering skin cancer prevention training for lifeguards.³ We examine the advantages of training, highlight the role lifeguards can play in larger public skin cancer prevention efforts, and address practical techniques for developing lifeguardfocused skin cancer education programs. By providing this knowledge to lifeguards, we can improve community health outcomes and encourage sun-safe behaviors in high-risk outdoor locations.

Benefits of Skin Cancer Prevention Training for Lifeguards

Research has shown that lifeguards are at an elevated risk for basal cell carcinoma, squamous cell carcinoma, and melanoma due to frequent prolonged occupational sun exposure.^1,2,4-6 Therefore, comprehensive education on skin cancer prevention—including instruction on proper sunscreen application techniques and the importance of regular reapplication as well as how to recognize suspicious skin lesions—should be incorporated into lifeguard certification programs. One study evaluating the effectiveness of a skin cancer prevention program for lifeguards found that many of the participants lacked a thorough understanding of the different types of skin cancer.⁵ Another study found that lifeguards at pools in areas where societal norms supporting sun safety are stronger exhibited noticeably more sun protection practices, with regression estimates of 0.22 (95% CI, 0.17-0.26).⁷ Empowering lifeguards with valuable health knowledge during their regular training could potentially reduce their risk for skin cancer,⁴ as they may be more inclined to use sunscreen appropriately and reach out to a dermatologist for regular skin checks and evaluation of suspicious lesions.

Role of Lifeguards in Public Skin Cancer Prevention Efforts

Once trained on skin cancer prevention, lifeguards also can play a pivotal role in promoting sunscreen use among the public. Despite the widespread availability of high-quality sunscreens, many swimmers and beachgoers neglect to regularly apply or reapply sunscreen, especially on commonly exposed areas such as the back, shoulders, and face.⁸ Educating lifeguards on skin cancer prevention could enhance health outcomes by increasing early detection rates and promoting sun-safe behaviors among the general public.⁹ However, additional training requirements might increase the cost and time commitment for lifeguard certification, potentially leading to staffing shortages.^3,7 There also is a risk of lifeguards overstepping their role and providing inaccurate medical advice, which could cause distress or even lead to liability issues.⁷ Balancing these factors will be crucial in developing effective and sustainable skin cancer prevention programs for lifeguards.

Implementing Lifeguard Skin Cancer Training

Implementing skin cancer prevention training programs for lifeguards requires strategic collaboration between dermatologists, and lifeguard training organizations to ensure that the participants receive consistent and comprehensive training.¹⁰ Additionally, public health campaigns can support these efforts by raising awareness about the importance of sun safety and regular skin checks.⁶ Tailored training modules/materials, ongoing technical assistance, and active, multicomponent approaches that account for both individual and environmental factors can increase program implementation in a variety of community settings.

Final Thoughts

Through effective education, lifeguards can potentially have a substantial impact on skin cancer prevention, both among lifeguards themselves and the general public. By promoting proper sunscreen use, lifeguards can help reduce the incidence and mortality associated with skin cancers. Future studies should focus on developing and implementing targeted education initiatives for lifeguards, fostering collaboration between relevant stakeholders, and raising public awareness about the importance of sun safety and early skin cancer detection. These efforts ultimately could lead to improved public health outcomes and reduced skin cancer rates, particularly in high-risk populations that frequently are exposed to UV radiation.