News

Hi, everyone. I’m Dr Kenny Lin. I am a family physician and associate director of the Lancaster General Hospital Family Medicine Residency, and I blog at Common Sense Family Doctor.

The receding of the pandemic and the understandable desire to return to normalcy has made COVID-19 vaccines a lower priority for many of our patients. However, family physicians should keep in mind that from October 1, 2024, to September 6, 2025, COVID-19 was responsible for an estimated 3.2 to 4.6 million outpatient visits, 360,000 to 520,000 hospitalizations, and 42,000 to 60,000 deaths.

In a previous commentary, I discussed the worsening disconnect between the evidence supporting the effectiveness and safety of vaccinations and increasing reluctance of patients and parents to receive them, fueled by misinformation from federal health agencies and the packing of the Advisory Committee on Immunization Practices (ACIP) with vaccine skeptics. Since then, Secretary of Health and Human Services (HHS), Robert F. Kennedy, Jr, has fired Dr Susan Monarez, his handpicked director of the CDC. This caused three senior CDC officials to resign in protest and precipitated further turmoil at the embattled agency. 

The FDA has approved 3 updated COVID-19 vaccines targeted to currently circulating strains: an mRNA vaccine from Moderna (Spikevax) for those aged 6 months or older; an mRNA vaccine from Pfizer/BioNTech (Comirnaty) for those aged ≥ 5 years; and a protein subunit vaccine from Novavax (Nuvaxovid) for those aged ≥ 12 years. However, approvals restricting the scope of these approvals to certain high-risk groups, combined with the ACIP’s recent decision to not explicitly recommend them for any group, have complicated access for many patients.

Medical groups, including the American Academy of Pediatrics (AAP), the American Academy of Family Physicians (AAFP), and the American College of Obstetricians and Gynecologists (ACOG), have published their own recommendations (Table). Of note, in opposition to the FDA and ACIP, the AAP and AAFP strongly recommend routine vaccination for children aged 6 to 23 months because they have the highest risk for hospitalization. The AAFP and ACOG both recommend COVID-19 vaccination in pregnancy to protect the pregnant patient and provide passive antibody protection to their infants up to 6 months of age. The Vaccine Integrity Project’s review of 12 safety studies published since June 2024 found that mRNA vaccines were not associated with increases in any adverse maternal or infant outcomes and had a possible protective effect against preterm birth.

In my previous commentary, 70% of Medscape readers indicated that they would follow vaccination recommendations from AAP even if they differed from CDC guidance. Administering vaccines outside of FDA labeling indications (i.e., “off label”) typically requires a physician’s prescription, which will almost certainly reduce COVID-19 vaccine uptake in children and pregnant patients, given that most people received these shots in pharmacies during the 2024-25 season. CVS and Walgreens, the country’s two largest pharmacy chains, are requiring physician prescriptions or waiting for ACIP guidance to make the new vaccines available in many states. However, an increasing number of states have implemented executive orders or passed legislation to permit pharmacists to provide vaccines to anyone who wants them. For example, the Pennsylvania State Board of Pharmacy voted unanimously to issue guidance that would allow pharmacists to administer any vaccines recommended by AAFP, AAP, or ACOG.

Erosion of vaccine uptake could easily worsen the burden of illness for our patients and the health system. Navigating the unnecessarily complex landscape of COVID-19 vaccines will be challenging, but it remains worthwhile.
 

Kenneth W. Lin, MD, MPH, Associate Director, Department of Family Medicine, Lancaster General Hospital, Lancaster, Pennsylvania, has disclosed the following relevant financial relationships: Serve(d) as a director, officer, partner, employee, advisor, consultant, or trustee for: UpToDate; American Academy of Family Physicians; Archdiocese of Washington; Association of Prevention Teaching and Research.

A version of this article appeared on Medscape.com.

Hi, everyone. I’m Dr Kenny Lin. I am a family physician and associate director of the Lancaster General Hospital Family Medicine Residency, and I blog at Common Sense Family Doctor.

The receding of the pandemic and the understandable desire to return to normalcy has made COVID-19 vaccines a lower priority for many of our patients. However, family physicians should keep in mind that from October 1, 2024, to September 6, 2025, COVID-19 was responsible for an estimated 3.2 to 4.6 million outpatient visits, 360,000 to 520,000 hospitalizations, and 42,000 to 60,000 deaths.

In a previous commentary, I discussed the worsening disconnect between the evidence supporting the effectiveness and safety of vaccinations and increasing reluctance of patients and parents to receive them, fueled by misinformation from federal health agencies and the packing of the Advisory Committee on Immunization Practices (ACIP) with vaccine skeptics. Since then, Secretary of Health and Human Services (HHS), Robert F. Kennedy, Jr, has fired Dr Susan Monarez, his handpicked director of the CDC. This caused three senior CDC officials to resign in protest and precipitated further turmoil at the embattled agency. 

The FDA has approved 3 updated COVID-19 vaccines targeted to currently circulating strains: an mRNA vaccine from Moderna (Spikevax) for those aged 6 months or older; an mRNA vaccine from Pfizer/BioNTech (Comirnaty) for those aged ≥ 5 years; and a protein subunit vaccine from Novavax (Nuvaxovid) for those aged ≥ 12 years. However, approvals restricting the scope of these approvals to certain high-risk groups, combined with the ACIP’s recent decision to not explicitly recommend them for any group, have complicated access for many patients.

Medical groups, including the American Academy of Pediatrics (AAP), the American Academy of Family Physicians (AAFP), and the American College of Obstetricians and Gynecologists (ACOG), have published their own recommendations (Table). Of note, in opposition to the FDA and ACIP, the AAP and AAFP strongly recommend routine vaccination for children aged 6 to 23 months because they have the highest risk for hospitalization. The AAFP and ACOG both recommend COVID-19 vaccination in pregnancy to protect the pregnant patient and provide passive antibody protection to their infants up to 6 months of age. The Vaccine Integrity Project’s review of 12 safety studies published since June 2024 found that mRNA vaccines were not associated with increases in any adverse maternal or infant outcomes and had a possible protective effect against preterm birth.

In my previous commentary, 70% of Medscape readers indicated that they would follow vaccination recommendations from AAP even if they differed from CDC guidance. Administering vaccines outside of FDA labeling indications (i.e., “off label”) typically requires a physician’s prescription, which will almost certainly reduce COVID-19 vaccine uptake in children and pregnant patients, given that most people received these shots in pharmacies during the 2024-25 season. CVS and Walgreens, the country’s two largest pharmacy chains, are requiring physician prescriptions or waiting for ACIP guidance to make the new vaccines available in many states. However, an increasing number of states have implemented executive orders or passed legislation to permit pharmacists to provide vaccines to anyone who wants them. For example, the Pennsylvania State Board of Pharmacy voted unanimously to issue guidance that would allow pharmacists to administer any vaccines recommended by AAFP, AAP, or ACOG.

Erosion of vaccine uptake could easily worsen the burden of illness for our patients and the health system. Navigating the unnecessarily complex landscape of COVID-19 vaccines will be challenging, but it remains worthwhile.
 

Kenneth W. Lin, MD, MPH, Associate Director, Department of Family Medicine, Lancaster General Hospital, Lancaster, Pennsylvania, has disclosed the following relevant financial relationships: Serve(d) as a director, officer, partner, employee, advisor, consultant, or trustee for: UpToDate; American Academy of Family Physicians; Archdiocese of Washington; Association of Prevention Teaching and Research.

A version of this article appeared on Medscape.com.

Hi, everyone. I’m Dr Kenny Lin. I am a family physician and associate director of the Lancaster General Hospital Family Medicine Residency, and I blog at Common Sense Family Doctor.

The receding of the pandemic and the understandable desire to return to normalcy has made COVID-19 vaccines a lower priority for many of our patients. However, family physicians should keep in mind that from October 1, 2024, to September 6, 2025, COVID-19 was responsible for an estimated 3.2 to 4.6 million outpatient visits, 360,000 to 520,000 hospitalizations, and 42,000 to 60,000 deaths.

In a previous commentary, I discussed the worsening disconnect between the evidence supporting the effectiveness and safety of vaccinations and increasing reluctance of patients and parents to receive them, fueled by misinformation from federal health agencies and the packing of the Advisory Committee on Immunization Practices (ACIP) with vaccine skeptics. Since then, Secretary of Health and Human Services (HHS), Robert F. Kennedy, Jr, has fired Dr Susan Monarez, his handpicked director of the CDC. This caused three senior CDC officials to resign in protest and precipitated further turmoil at the embattled agency. 

The FDA has approved 3 updated COVID-19 vaccines targeted to currently circulating strains: an mRNA vaccine from Moderna (Spikevax) for those aged 6 months or older; an mRNA vaccine from Pfizer/BioNTech (Comirnaty) for those aged ≥ 5 years; and a protein subunit vaccine from Novavax (Nuvaxovid) for those aged ≥ 12 years. However, approvals restricting the scope of these approvals to certain high-risk groups, combined with the ACIP’s recent decision to not explicitly recommend them for any group, have complicated access for many patients.

Medical groups, including the American Academy of Pediatrics (AAP), the American Academy of Family Physicians (AAFP), and the American College of Obstetricians and Gynecologists (ACOG), have published their own recommendations (Table). Of note, in opposition to the FDA and ACIP, the AAP and AAFP strongly recommend routine vaccination for children aged 6 to 23 months because they have the highest risk for hospitalization. The AAFP and ACOG both recommend COVID-19 vaccination in pregnancy to protect the pregnant patient and provide passive antibody protection to their infants up to 6 months of age. The Vaccine Integrity Project’s review of 12 safety studies published since June 2024 found that mRNA vaccines were not associated with increases in any adverse maternal or infant outcomes and had a possible protective effect against preterm birth.

In my previous commentary, 70% of Medscape readers indicated that they would follow vaccination recommendations from AAP even if they differed from CDC guidance. Administering vaccines outside of FDA labeling indications (i.e., “off label”) typically requires a physician’s prescription, which will almost certainly reduce COVID-19 vaccine uptake in children and pregnant patients, given that most people received these shots in pharmacies during the 2024-25 season. CVS and Walgreens, the country’s two largest pharmacy chains, are requiring physician prescriptions or waiting for ACIP guidance to make the new vaccines available in many states. However, an increasing number of states have implemented executive orders or passed legislation to permit pharmacists to provide vaccines to anyone who wants them. For example, the Pennsylvania State Board of Pharmacy voted unanimously to issue guidance that would allow pharmacists to administer any vaccines recommended by AAFP, AAP, or ACOG.

Erosion of vaccine uptake could easily worsen the burden of illness for our patients and the health system. Navigating the unnecessarily complex landscape of COVID-19 vaccines will be challenging, but it remains worthwhile.
 

Kenneth W. Lin, MD, MPH, Associate Director, Department of Family Medicine, Lancaster General Hospital, Lancaster, Pennsylvania, has disclosed the following relevant financial relationships: Serve(d) as a director, officer, partner, employee, advisor, consultant, or trustee for: UpToDate; American Academy of Family Physicians; Archdiocese of Washington; Association of Prevention Teaching and Research.

A version of this article appeared on Medscape.com.

In this Practical AI column, we’ve explored everything from large language models to the nuances of trial matching, but one of the most immediate and impactful applications of AI is unfolding right now in breast imaging. For oncologists, this isn’t an abstract future — with new screening guidelines, dense-breast mandates, and a shrinking radiology workforce, it’s the imaging reports and patient questions landing in your clinic today.

Here is what oncologists need to know, and how to put it to work for their patients.

 

Why AI in Mammography Matters

More than 200 million women undergo breast cancer screening each year. In the US alone, 10% of the 40 million women screened annually require additional diagnostic imaging, and 4%–5% of these women are eventually diagnosed with breast cancer.

Two major shifts are redefining breast cancer screening in the US: The US Preventive Services Task Force (USPSTF) now recommends biennial screening from age 40 to 74 years, and notifying patients of breast density is a federal requirement as of September 10, 2024. That means more mammograms, more patient questions, and more downstream oncology decisions. Patients will increasingly ask about “dense” breast results and what to do next. Add a national radiologist shortage into the mix, and the pressure on timely callbacks, biopsies, and treatment planning will only grow.

 

Can AI Help Without Compromising Care?

The short answer is yes. With AI, we may be able to transform these rate-limiting steps into opportunities for earlier detection, decentralized screening, and smarter triage and save hundreds of thousands of women from an unnecessary diagnostic procedure, if implemented deliberately.

Don’t Confuse Today’s AI With Yesterday’s CAD 

Think of older computer-aided detection (CAD) like a 1990s chemotherapy drug: It sometimes helped, but it came with significant toxicity and rarely delivered consistent survival benefits. Today’s deep-learning AI is closer to targeted therapy — trained on millions of “trial participants” (mammograms), more precise, and applied in specific contexts where it adds value. If you once dismissed CAD as noise, it’s time to revisit what AI can now offer.

The role of AI is broader than drawing boxes. It provides second readings, worklist triage, risk prediction, density assessment, and decision support. FDA has cleared several AI tools for both 2D and digital breast tomosynthesis (DBT), which include iCAD ProFound (DBT), ScreenPoint Transpara (2D/DBT), and Lunit INSIGHT DBT. 

Some of the strongest evidence for AI in mammography is as a second reader during screening. Large trials show that AI plus one radiologist can match reading from two radiologists, cutting workload by about 40%. For example, the MASAI randomized trial showed that AI-supported screening achieved similar cancer detection but cut human screen-reading workload about 44% vs standard double reading (39,996 vs 40,024 participants). The primary interval cancer outcomes are maturing, but the safety analysis is reassuring.

Reducing second reads and arbitration time are important for clinicians because it frees capacity for callbacks and diagnostic workups. This will be especially key given that screening now starts at age 40. That will mean about 21 to 22 million more women are newly eligible, translating to about 10 to 11 million additional mammograms each year under biennial screening.

Another important area where AI can make its mark in mammography is triage and time to diagnosis. The results from a randomized implementation study showed that AI-prioritized worklists accelerated time to additional imaging and biopsy diagnosis without harming efficiency for others — exactly the kind of outcome patients feel.

Multiple studies have demonstrated improved diagnostic performance and shorter reading times when AI supports DBT interpretation, which is important because DBT can otherwise be time intensive.

We are also seeing rapid advancement in risk-based screening, moving beyond a single dense vs not dense approach. Deep-learning risk models, such as Mirai, predict 1- to 5-year breast cancer risk directly from the mammogram, and these tools are now being assessed prospectively to guide supplemental MRI. Cost-effectiveness modeling supports risk-stratified intervals vs one-size-fits-all schedules.

Finally, automated density tools, such as Transpara Density and Volpara, offer objective, reproducible volumetric measures that map to the Breast Imaging-Reporting and Data System, which is useful for Mammography Quality Standards Act-required reporting and as inputs to risk calculators.

While early evidence suggests AI may help surface future or interval cancers earlier, including more invasive tumors, the definitive impacts on interval cancer rates and mortality require longitudinal follow-up, which is now in progress.

 

Pitfalls to Watch For

Bias is real. Studies show false-positive differences by race, age, and density. AI can even infer racial identity from images, potentially amplifying disparities. Performance can also shift by vendor, demographics, and prevalence.

A Radiology study of 4855 DBT exams showed that an algorithm produced more false-positive case scores in Black patients and older patients (aged 71-80 years) patients and in women with extremely dense breasts. This can happen because AI can infer proxies for race directly from images, even when humans cannot, and this can propagate disparities if not addressed. External validations and reviews emphasize that performance can shift with device manufacturer, demographics, and prevalence, which is why all tools need to undergo local validation and calibration. 

Here’s a pragmatic adoption checklist before going live with an AI tool.

• Confirm FDA clearance: Verify the name and version of the algorithm, imaging modes (2D vs DBT), and operating points. Confirm 510(k) numbers.
• Local validation: Test on your patient mix and vendor stack (Hologic, GE, Siemens, Fuji). Compare this to your baseline recall rate, positive predictive value of recall (PPV1), cancer detection rate, and reading time. Commit to recalibration if drift occurs.
• Equity plan: Monitor false-positive and negative false-rates by age, race/ethnicity, and density; document corrective actions if disparities emerge. (This isn’t optional.)
• Workflow clarity: Is AI a second reader, an additional reader, or a triage tool? Who arbitrates discordance? What’s the escalation path for high-risk or interval cancer-like patterns?
• Regulatory strategy: Confirm whether the vendor has (or will file) a Predetermined Change Control Plan so models can be updated safely without repeated submissions. Also confirm how you’ll be notified about performance-relevant changes.
• Data governance: Audit logs of AI outputs, retention, protected health information handling, and the patient communication policy for AI-assisted reads.

After going live, set up a quarterly dashboard. It should include cancer detection rate per 1000 patients, recall rate, PPV1, interval cancer rate (as it matures), reading time, and turnaround time to diagnostic imaging or biopsy — all stratified by age, race/ethnicity, and density.

Here, I dissect what this discussion means through the lens of Moravec’s paradox (machines excel at what clinicians find hard, and vice versa) and offer a possible playbook for putting these tools to work.

 

What to Tell Patients

When speaking with patients, emphasize that a radiologist still reads their mammogram. AI helps with consistency and efficiency; it doesn’t replace human oversight. Patients with dense breasts should still expect a standard notice; discussion of individualized risk factors, such as family history, genetics, and prior biopsies; and consideration of supplemental imaging if risk warrants. But it’s also important to tell these patients that while dense breasts are common, they do not automatically mean high cancer risk.

As for screening schedules, remind patients that screening is at least biennial from 40 to 74 years of age per the USPSTF guidelines; however, specialty groups may recommend starting on an annual schedule at 40.

 

What You Can Implement Now

There are multiple practical use cases you can introduce now. One is to use AI as a second reader or an additional reader safety net to preserve detection while reducing human workload. This helps your breast center absorb screening expansion to age 40 without diluting quality. Another is to turn on AI triage to shorten the time to callback and biopsy for the few who need it most — patients notice and appreciate faster answers. You can also begin adopting automated density plus risk models to move beyond “dense/not dense.” For selected patients, AI-informed risk can justify MRI or tailored intervals. 

Here’s a quick cheat sheet (for your next leadership or tumor-board meeting).

 

Do:

• Use AI as a second or additional reader or triage tool, not as a black box.
• Track cancer detection rate, recall, PPV1, interval cancers, and reading time, stratified by age, race, and breast density.
• Pair automated density with AI risk to personalize screening and supplemental imaging.
• Enroll patients in future clinical trials, such as PRISM, the first large-scale randomized controlled trial of AI for screening mammography. This US-based, $16 million, seven-site study is funded by the Patient-Centered Outcomes Research Institute.

Don’t:

• Assume “AI = CAD.” The 2015 CAD story is over; modern deep learning systems are different and require different oversight.
• Go live without a local validation and equity plan or without clarity on software updates.
• Forget to remind patients that screening starts at age 40, and dense breast notifications are now universal. Use the visit to discuss risk, supplemental imaging, and why a human still directs their care.

The Bottom Line

AI won’t replace radiologists or read mammograms for us — just as PET scans didn’t replace oncologists and stethoscopes didn’t make cardiologists obsolete. What it will do is catch what the tired human eye might miss, shave days off anxious waiting, and turn breast density into data instead of doubt. For oncologists, that means staging sooner, enrolling smarter, and spending more time talking with patients instead of chasing callbacks.

In short, AI may not take the picture, but it helps us frame the story, making it sharper, faster, and with fewer blind spots. By pairing this powerful technology with rigorous, equity-focused local validation and transparent governance under the FDA’s emerging Predetermined Change Control Plan framework, we can realize the tangible benefits of practical AI for our patients without widening disparities. 

Now, during Breast Cancer Awareness Month, how about we add on AI to that pink ribbon — how cool would that be?

Thoughts? Drop me a line at [email protected]. Let’s keep the conversation — and pink ribbons — going.

Arturo Loaiza-Bonilla, MD, MSEd, is the co-founder and chief medical AI officer at Massive Bio, a company connecting patients to clinical trials using artificial intelligence. His research and professional interests focus on precision medicine, clinical trial design, digital health, entrepreneurship, and patient advocacy. Dr Loaiza-Bonilla serves as Systemwide Chief of Hematology and Oncology at St. Luke’s University Health Network, where he maintains a connection to patient care by attending to patients 2 days a week.

A version of this article first appeared on Medscape.com.

In this Practical AI column, we’ve explored everything from large language models to the nuances of trial matching, but one of the most immediate and impactful applications of AI is unfolding right now in breast imaging. For oncologists, this isn’t an abstract future — with new screening guidelines, dense-breast mandates, and a shrinking radiology workforce, it’s the imaging reports and patient questions landing in your clinic today.

Here is what oncologists need to know, and how to put it to work for their patients.

 

Why AI in Mammography Matters

More than 200 million women undergo breast cancer screening each year. In the US alone, 10% of the 40 million women screened annually require additional diagnostic imaging, and 4%–5% of these women are eventually diagnosed with breast cancer.

Two major shifts are redefining breast cancer screening in the US: The US Preventive Services Task Force (USPSTF) now recommends biennial screening from age 40 to 74 years, and notifying patients of breast density is a federal requirement as of September 10, 2024. That means more mammograms, more patient questions, and more downstream oncology decisions. Patients will increasingly ask about “dense” breast results and what to do next. Add a national radiologist shortage into the mix, and the pressure on timely callbacks, biopsies, and treatment planning will only grow.

 

Can AI Help Without Compromising Care?

The short answer is yes. With AI, we may be able to transform these rate-limiting steps into opportunities for earlier detection, decentralized screening, and smarter triage and save hundreds of thousands of women from an unnecessary diagnostic procedure, if implemented deliberately.

Don’t Confuse Today’s AI With Yesterday’s CAD 

Think of older computer-aided detection (CAD) like a 1990s chemotherapy drug: It sometimes helped, but it came with significant toxicity and rarely delivered consistent survival benefits. Today’s deep-learning AI is closer to targeted therapy — trained on millions of “trial participants” (mammograms), more precise, and applied in specific contexts where it adds value. If you once dismissed CAD as noise, it’s time to revisit what AI can now offer.

The role of AI is broader than drawing boxes. It provides second readings, worklist triage, risk prediction, density assessment, and decision support. FDA has cleared several AI tools for both 2D and digital breast tomosynthesis (DBT), which include iCAD ProFound (DBT), ScreenPoint Transpara (2D/DBT), and Lunit INSIGHT DBT. 

Some of the strongest evidence for AI in mammography is as a second reader during screening. Large trials show that AI plus one radiologist can match reading from two radiologists, cutting workload by about 40%. For example, the MASAI randomized trial showed that AI-supported screening achieved similar cancer detection but cut human screen-reading workload about 44% vs standard double reading (39,996 vs 40,024 participants). The primary interval cancer outcomes are maturing, but the safety analysis is reassuring.

Reducing second reads and arbitration time are important for clinicians because it frees capacity for callbacks and diagnostic workups. This will be especially key given that screening now starts at age 40. That will mean about 21 to 22 million more women are newly eligible, translating to about 10 to 11 million additional mammograms each year under biennial screening.

Another important area where AI can make its mark in mammography is triage and time to diagnosis. The results from a randomized implementation study showed that AI-prioritized worklists accelerated time to additional imaging and biopsy diagnosis without harming efficiency for others — exactly the kind of outcome patients feel.

Multiple studies have demonstrated improved diagnostic performance and shorter reading times when AI supports DBT interpretation, which is important because DBT can otherwise be time intensive.

We are also seeing rapid advancement in risk-based screening, moving beyond a single dense vs not dense approach. Deep-learning risk models, such as Mirai, predict 1- to 5-year breast cancer risk directly from the mammogram, and these tools are now being assessed prospectively to guide supplemental MRI. Cost-effectiveness modeling supports risk-stratified intervals vs one-size-fits-all schedules.

Finally, automated density tools, such as Transpara Density and Volpara, offer objective, reproducible volumetric measures that map to the Breast Imaging-Reporting and Data System, which is useful for Mammography Quality Standards Act-required reporting and as inputs to risk calculators.

While early evidence suggests AI may help surface future or interval cancers earlier, including more invasive tumors, the definitive impacts on interval cancer rates and mortality require longitudinal follow-up, which is now in progress.

 

Pitfalls to Watch For

Bias is real. Studies show false-positive differences by race, age, and density. AI can even infer racial identity from images, potentially amplifying disparities. Performance can also shift by vendor, demographics, and prevalence.

A Radiology study of 4855 DBT exams showed that an algorithm produced more false-positive case scores in Black patients and older patients (aged 71-80 years) patients and in women with extremely dense breasts. This can happen because AI can infer proxies for race directly from images, even when humans cannot, and this can propagate disparities if not addressed. External validations and reviews emphasize that performance can shift with device manufacturer, demographics, and prevalence, which is why all tools need to undergo local validation and calibration. 

Here’s a pragmatic adoption checklist before going live with an AI tool.

• Confirm FDA clearance: Verify the name and version of the algorithm, imaging modes (2D vs DBT), and operating points. Confirm 510(k) numbers.
• Local validation: Test on your patient mix and vendor stack (Hologic, GE, Siemens, Fuji). Compare this to your baseline recall rate, positive predictive value of recall (PPV1), cancer detection rate, and reading time. Commit to recalibration if drift occurs.
• Equity plan: Monitor false-positive and negative false-rates by age, race/ethnicity, and density; document corrective actions if disparities emerge. (This isn’t optional.)
• Workflow clarity: Is AI a second reader, an additional reader, or a triage tool? Who arbitrates discordance? What’s the escalation path for high-risk or interval cancer-like patterns?
• Regulatory strategy: Confirm whether the vendor has (or will file) a Predetermined Change Control Plan so models can be updated safely without repeated submissions. Also confirm how you’ll be notified about performance-relevant changes.
• Data governance: Audit logs of AI outputs, retention, protected health information handling, and the patient communication policy for AI-assisted reads.

After going live, set up a quarterly dashboard. It should include cancer detection rate per 1000 patients, recall rate, PPV1, interval cancer rate (as it matures), reading time, and turnaround time to diagnostic imaging or biopsy — all stratified by age, race/ethnicity, and density.

Here, I dissect what this discussion means through the lens of Moravec’s paradox (machines excel at what clinicians find hard, and vice versa) and offer a possible playbook for putting these tools to work.

 

What to Tell Patients

When speaking with patients, emphasize that a radiologist still reads their mammogram. AI helps with consistency and efficiency; it doesn’t replace human oversight. Patients with dense breasts should still expect a standard notice; discussion of individualized risk factors, such as family history, genetics, and prior biopsies; and consideration of supplemental imaging if risk warrants. But it’s also important to tell these patients that while dense breasts are common, they do not automatically mean high cancer risk.

As for screening schedules, remind patients that screening is at least biennial from 40 to 74 years of age per the USPSTF guidelines; however, specialty groups may recommend starting on an annual schedule at 40.

 

What You Can Implement Now

There are multiple practical use cases you can introduce now. One is to use AI as a second reader or an additional reader safety net to preserve detection while reducing human workload. This helps your breast center absorb screening expansion to age 40 without diluting quality. Another is to turn on AI triage to shorten the time to callback and biopsy for the few who need it most — patients notice and appreciate faster answers. You can also begin adopting automated density plus risk models to move beyond “dense/not dense.” For selected patients, AI-informed risk can justify MRI or tailored intervals. 

Here’s a quick cheat sheet (for your next leadership or tumor-board meeting).

 

Do:

• Use AI as a second or additional reader or triage tool, not as a black box.
• Track cancer detection rate, recall, PPV1, interval cancers, and reading time, stratified by age, race, and breast density.
• Pair automated density with AI risk to personalize screening and supplemental imaging.
• Enroll patients in future clinical trials, such as PRISM, the first large-scale randomized controlled trial of AI for screening mammography. This US-based, $16 million, seven-site study is funded by the Patient-Centered Outcomes Research Institute.

Don’t:

• Assume “AI = CAD.” The 2015 CAD story is over; modern deep learning systems are different and require different oversight.
• Go live without a local validation and equity plan or without clarity on software updates.
• Forget to remind patients that screening starts at age 40, and dense breast notifications are now universal. Use the visit to discuss risk, supplemental imaging, and why a human still directs their care.

The Bottom Line

AI won’t replace radiologists or read mammograms for us — just as PET scans didn’t replace oncologists and stethoscopes didn’t make cardiologists obsolete. What it will do is catch what the tired human eye might miss, shave days off anxious waiting, and turn breast density into data instead of doubt. For oncologists, that means staging sooner, enrolling smarter, and spending more time talking with patients instead of chasing callbacks.

In short, AI may not take the picture, but it helps us frame the story, making it sharper, faster, and with fewer blind spots. By pairing this powerful technology with rigorous, equity-focused local validation and transparent governance under the FDA’s emerging Predetermined Change Control Plan framework, we can realize the tangible benefits of practical AI for our patients without widening disparities. 

Now, during Breast Cancer Awareness Month, how about we add on AI to that pink ribbon — how cool would that be?

Thoughts? Drop me a line at [email protected]. Let’s keep the conversation — and pink ribbons — going.

Arturo Loaiza-Bonilla, MD, MSEd, is the co-founder and chief medical AI officer at Massive Bio, a company connecting patients to clinical trials using artificial intelligence. His research and professional interests focus on precision medicine, clinical trial design, digital health, entrepreneurship, and patient advocacy. Dr Loaiza-Bonilla serves as Systemwide Chief of Hematology and Oncology at St. Luke’s University Health Network, where he maintains a connection to patient care by attending to patients 2 days a week.

A version of this article first appeared on Medscape.com.

In this Practical AI column, we’ve explored everything from large language models to the nuances of trial matching, but one of the most immediate and impactful applications of AI is unfolding right now in breast imaging. For oncologists, this isn’t an abstract future — with new screening guidelines, dense-breast mandates, and a shrinking radiology workforce, it’s the imaging reports and patient questions landing in your clinic today.

Here is what oncologists need to know, and how to put it to work for their patients.

 

Why AI in Mammography Matters

More than 200 million women undergo breast cancer screening each year. In the US alone, 10% of the 40 million women screened annually require additional diagnostic imaging, and 4%–5% of these women are eventually diagnosed with breast cancer.

Two major shifts are redefining breast cancer screening in the US: The US Preventive Services Task Force (USPSTF) now recommends biennial screening from age 40 to 74 years, and notifying patients of breast density is a federal requirement as of September 10, 2024. That means more mammograms, more patient questions, and more downstream oncology decisions. Patients will increasingly ask about “dense” breast results and what to do next. Add a national radiologist shortage into the mix, and the pressure on timely callbacks, biopsies, and treatment planning will only grow.

 

Can AI Help Without Compromising Care?

The short answer is yes. With AI, we may be able to transform these rate-limiting steps into opportunities for earlier detection, decentralized screening, and smarter triage and save hundreds of thousands of women from an unnecessary diagnostic procedure, if implemented deliberately.

Don’t Confuse Today’s AI With Yesterday’s CAD 

Think of older computer-aided detection (CAD) like a 1990s chemotherapy drug: It sometimes helped, but it came with significant toxicity and rarely delivered consistent survival benefits. Today’s deep-learning AI is closer to targeted therapy — trained on millions of “trial participants” (mammograms), more precise, and applied in specific contexts where it adds value. If you once dismissed CAD as noise, it’s time to revisit what AI can now offer.

The role of AI is broader than drawing boxes. It provides second readings, worklist triage, risk prediction, density assessment, and decision support. FDA has cleared several AI tools for both 2D and digital breast tomosynthesis (DBT), which include iCAD ProFound (DBT), ScreenPoint Transpara (2D/DBT), and Lunit INSIGHT DBT. 

Some of the strongest evidence for AI in mammography is as a second reader during screening. Large trials show that AI plus one radiologist can match reading from two radiologists, cutting workload by about 40%. For example, the MASAI randomized trial showed that AI-supported screening achieved similar cancer detection but cut human screen-reading workload about 44% vs standard double reading (39,996 vs 40,024 participants). The primary interval cancer outcomes are maturing, but the safety analysis is reassuring.

Reducing second reads and arbitration time are important for clinicians because it frees capacity for callbacks and diagnostic workups. This will be especially key given that screening now starts at age 40. That will mean about 21 to 22 million more women are newly eligible, translating to about 10 to 11 million additional mammograms each year under biennial screening.

Another important area where AI can make its mark in mammography is triage and time to diagnosis. The results from a randomized implementation study showed that AI-prioritized worklists accelerated time to additional imaging and biopsy diagnosis without harming efficiency for others — exactly the kind of outcome patients feel.

Multiple studies have demonstrated improved diagnostic performance and shorter reading times when AI supports DBT interpretation, which is important because DBT can otherwise be time intensive.

We are also seeing rapid advancement in risk-based screening, moving beyond a single dense vs not dense approach. Deep-learning risk models, such as Mirai, predict 1- to 5-year breast cancer risk directly from the mammogram, and these tools are now being assessed prospectively to guide supplemental MRI. Cost-effectiveness modeling supports risk-stratified intervals vs one-size-fits-all schedules.

Finally, automated density tools, such as Transpara Density and Volpara, offer objective, reproducible volumetric measures that map to the Breast Imaging-Reporting and Data System, which is useful for Mammography Quality Standards Act-required reporting and as inputs to risk calculators.

While early evidence suggests AI may help surface future or interval cancers earlier, including more invasive tumors, the definitive impacts on interval cancer rates and mortality require longitudinal follow-up, which is now in progress.

 

Pitfalls to Watch For

Bias is real. Studies show false-positive differences by race, age, and density. AI can even infer racial identity from images, potentially amplifying disparities. Performance can also shift by vendor, demographics, and prevalence.

A Radiology study of 4855 DBT exams showed that an algorithm produced more false-positive case scores in Black patients and older patients (aged 71-80 years) patients and in women with extremely dense breasts. This can happen because AI can infer proxies for race directly from images, even when humans cannot, and this can propagate disparities if not addressed. External validations and reviews emphasize that performance can shift with device manufacturer, demographics, and prevalence, which is why all tools need to undergo local validation and calibration. 

Here’s a pragmatic adoption checklist before going live with an AI tool.

• Confirm FDA clearance: Verify the name and version of the algorithm, imaging modes (2D vs DBT), and operating points. Confirm 510(k) numbers.
• Local validation: Test on your patient mix and vendor stack (Hologic, GE, Siemens, Fuji). Compare this to your baseline recall rate, positive predictive value of recall (PPV1), cancer detection rate, and reading time. Commit to recalibration if drift occurs.
• Equity plan: Monitor false-positive and negative false-rates by age, race/ethnicity, and density; document corrective actions if disparities emerge. (This isn’t optional.)
• Workflow clarity: Is AI a second reader, an additional reader, or a triage tool? Who arbitrates discordance? What’s the escalation path for high-risk or interval cancer-like patterns?
• Regulatory strategy: Confirm whether the vendor has (or will file) a Predetermined Change Control Plan so models can be updated safely without repeated submissions. Also confirm how you’ll be notified about performance-relevant changes.
• Data governance: Audit logs of AI outputs, retention, protected health information handling, and the patient communication policy for AI-assisted reads.

After going live, set up a quarterly dashboard. It should include cancer detection rate per 1000 patients, recall rate, PPV1, interval cancer rate (as it matures), reading time, and turnaround time to diagnostic imaging or biopsy — all stratified by age, race/ethnicity, and density.

Here, I dissect what this discussion means through the lens of Moravec’s paradox (machines excel at what clinicians find hard, and vice versa) and offer a possible playbook for putting these tools to work.

 

What to Tell Patients

When speaking with patients, emphasize that a radiologist still reads their mammogram. AI helps with consistency and efficiency; it doesn’t replace human oversight. Patients with dense breasts should still expect a standard notice; discussion of individualized risk factors, such as family history, genetics, and prior biopsies; and consideration of supplemental imaging if risk warrants. But it’s also important to tell these patients that while dense breasts are common, they do not automatically mean high cancer risk.

As for screening schedules, remind patients that screening is at least biennial from 40 to 74 years of age per the USPSTF guidelines; however, specialty groups may recommend starting on an annual schedule at 40.

 

What You Can Implement Now

There are multiple practical use cases you can introduce now. One is to use AI as a second reader or an additional reader safety net to preserve detection while reducing human workload. This helps your breast center absorb screening expansion to age 40 without diluting quality. Another is to turn on AI triage to shorten the time to callback and biopsy for the few who need it most — patients notice and appreciate faster answers. You can also begin adopting automated density plus risk models to move beyond “dense/not dense.” For selected patients, AI-informed risk can justify MRI or tailored intervals. 

Here’s a quick cheat sheet (for your next leadership or tumor-board meeting).

 

Do:

• Use AI as a second or additional reader or triage tool, not as a black box.
• Track cancer detection rate, recall, PPV1, interval cancers, and reading time, stratified by age, race, and breast density.
• Pair automated density with AI risk to personalize screening and supplemental imaging.
• Enroll patients in future clinical trials, such as PRISM, the first large-scale randomized controlled trial of AI for screening mammography. This US-based, $16 million, seven-site study is funded by the Patient-Centered Outcomes Research Institute.

Don’t:

• Assume “AI = CAD.” The 2015 CAD story is over; modern deep learning systems are different and require different oversight.
• Go live without a local validation and equity plan or without clarity on software updates.
• Forget to remind patients that screening starts at age 40, and dense breast notifications are now universal. Use the visit to discuss risk, supplemental imaging, and why a human still directs their care.

The Bottom Line

AI won’t replace radiologists or read mammograms for us — just as PET scans didn’t replace oncologists and stethoscopes didn’t make cardiologists obsolete. What it will do is catch what the tired human eye might miss, shave days off anxious waiting, and turn breast density into data instead of doubt. For oncologists, that means staging sooner, enrolling smarter, and spending more time talking with patients instead of chasing callbacks.

In short, AI may not take the picture, but it helps us frame the story, making it sharper, faster, and with fewer blind spots. By pairing this powerful technology with rigorous, equity-focused local validation and transparent governance under the FDA’s emerging Predetermined Change Control Plan framework, we can realize the tangible benefits of practical AI for our patients without widening disparities. 

Now, during Breast Cancer Awareness Month, how about we add on AI to that pink ribbon — how cool would that be?

Thoughts? Drop me a line at [email protected]. Let’s keep the conversation — and pink ribbons — going.

Arturo Loaiza-Bonilla, MD, MSEd, is the co-founder and chief medical AI officer at Massive Bio, a company connecting patients to clinical trials using artificial intelligence. His research and professional interests focus on precision medicine, clinical trial design, digital health, entrepreneurship, and patient advocacy. Dr Loaiza-Bonilla serves as Systemwide Chief of Hematology and Oncology at St. Luke’s University Health Network, where he maintains a connection to patient care by attending to patients 2 days a week.

A version of this article first appeared on Medscape.com.

As a hospitalist, you are in a unique position to notice changes in your hospitalized patients. This frontline perspective can be used to improve inpatient attention and care, and differs from primary care, where a clinician might only see a patient once or twice a year, and subtle, gradual changes may be missed, said George Cao, MD, MBA, a hospitalist at the University of Vermont Medical Center in Burlington and assistant professor at UVM’s Larner College of Medicine. 

But in the hospital, Cao said even small shifts — like becoming less active, eating less, or changes in personality — can become much more obvious. 

“As hospitalists…we see patients throughout the day, in different situations, and often end up spending more time with them over the course of a week than their primary care provider might in a year,” Cao explained. “This gives us a real advantage in picking up on subtle changes in mental awareness.”

These assessments can also be evaluated with the benefit of daily labs, frequent bedside interactions, and 24–hour observations.

With older adults, Cao said it’s important to go beyond just what’s in the chart. 

“I always start by reviewing notes from the primary care provider and previous admissions, but some of the most valuable insights come from talking with family and close friends to get a true sense of the patient’s baseline — how they usually think, move, and interact,” he said.

 

Why to Watch for Declining Mental Awareness

Declining mental awareness in the inpatient setting is often a sign of an underlying problem — whether that’s a reversible medical condition, unrecognized dementia, or the development of delirium, Cao said.

“On the inpatient side, I pay close attention to more than just memory loss,” he said. 

Changes in how patients function day–to–day, shifts in their behavior, or even something as simple as not wanting to get out of bed can be early signs of an aging mind or untreated psychiatric issues, he noted. 

“Of course, we always rule out infections and medication side effects, but I also look for other reversible causes like thyroid problems, electrolyte imbalances, low oxygen, pain, urinary retention, constipation, and nutritional deficiencies,” Cao said.

Of note, delirium is the most common cause of sudden mental status changes in the hospital, and “it’s easy to miss if you’re not looking for it.”

He summarized that classic signs are an acute and fluctuating course with changes in alertness, but added there are other red flags too: disorientation, hallucinations, changes in sleep patterns, sporadic unsafe behaviors, mood swings, and changes in activity level, whether that’s agitation or just being unusually quiet. 

By combining what he notices bedside and what is learned from the medical record (and from the people who know the patient best), Cao said he’s able to catch these changes early, identify the underlying cause, and work toward the best possible outcome. 

“One of the main interventions is providing mental stimulation,” he said.

 

Why Mental Stimulation Is So Vital 

Mental stimulation of the patient is critical to recovery and may prevent prolonged illness, said Meghana R. Medavaram, MD, associate director of consultation liaison and emergency psychiatry at Montefiore Medical Center’s Weiler Hospital in New York City. “Keeping a patient active both physically and mentally can help prevent deconditioning and risks of prolonged immobility,” she said.

It’s important to note that when patients are out of their familiar routines, away from their usual environment and people, and their sleep is fragmented, this can make them even more vulnerable. Keeping patients mentally stimulated during their hospital stay can help maintain their attention, orientation, and a healthy sleep-wake cycle — all things that are easily thrown off in the hospital, Cao said. 

“These disruptions hit the pathways that control attention, wakefulness, and the sleep–wake cycle. That’s when you see attention drifting, orientation fading, and circadian rhythms unraveling, especially at night, which is why “sundowning” is so common, Cao said, referring to the syndrome where older adults or people with dementia experience behavioral changes in late afternoon or evening. “Mental stimulation is critical in the hospital because when the brain isn’t active and gets disoriented, it becomes an easy target for delirium.” 

He said delirium often develops in older adults when acute stressors like inflammation, low oxygen, metabolic imbalances, or sedating medications disrupt the brain’s arousal systems and networks, especially in older adults.

Therefore, Cao said, encourage your patients to be more engaged during the day through conversation, activities, or regular reorientation. “This supports the brain networks that help prevent inattention and confusion, which are the hallmarks of delirium. Daytime stimulation also helps build up the natural drive for nighttime sleep, so patients are less likely to nap during the day and be awake and disoriented at night.”

To support this, it’s helpful to schedule medications during waking hours instead of around–the–clock dosing that interrupts sleep, and to cluster nighttime care activities to minimize disturbances, Cao explained. Ensuring patients have their glasses, hearing aids, and familiar routines, along with encouraging mobility and hydration, further protects against delirium and supports patients’ cognitive health during hospitalization. “These same principles are just as important in outpatient subacute rehab settings and at home, so it’s essential to take home these strategies after discharge,” he said.

 

A Family Member or Friend May Help

Hospitalists can suggest straightforward ways to encourage families and friends to keep patients engaged during a hospital stay. Visits and chats can go a long way as conversations are incredibly grounding, Cao said. Other methods could be bringing in favorite foods or snacks, a phone chat or video call, or even showing prerecorded video messages. “These can be effective. Patients respond well to seeing and hearing familiar faces and voices, even if it’s just on a screen,” Cao said.

Beyond that, he said, activities such as watching and discussing the news, reading aloud, using tablets for games, watching movies, doing crossword puzzles, knitting, reminiscing, and playing word games can also be mentally stimulating for patients. 

In addition, safe exercises/activities that patients can do in bed — with advice from physical therapy and occupational therapy — are beneficial, Medavaram said. “These often include gentle range–of-motion activities,” she said. 

 

Share Importance of Mental Stimulation With Patients and Caregivers

If a hospitalist wants to motivate patients to keep their minds active, the framing should be simple, positive, and tied directly to their goals of getting better and getting home, said Medavaram. She provided this script suggestion:

“One of the best ways to help your recovery isn’t just taking your medicine, it’s keeping your mind active. When you’re in the hospital, it’s easy to spend the day lying in bed and staring at the TV in your room, but that can make your brain slow down and even cause confusion. Simple things — like reading, talking with visitors, doing puzzles, listening to music you enjoy, or telling a nurse about your favorite memories — can keep your brain sharp. Staying mentally active helps your thinking stay clear and can even help you get home sooner. Think of it like physical therapy for your brain.” 

A version of this article first appeared on Medscape.com.

As a hospitalist, you are in a unique position to notice changes in your hospitalized patients. This frontline perspective can be used to improve inpatient attention and care, and differs from primary care, where a clinician might only see a patient once or twice a year, and subtle, gradual changes may be missed, said George Cao, MD, MBA, a hospitalist at the University of Vermont Medical Center in Burlington and assistant professor at UVM’s Larner College of Medicine. 

But in the hospital, Cao said even small shifts — like becoming less active, eating less, or changes in personality — can become much more obvious. 

“As hospitalists…we see patients throughout the day, in different situations, and often end up spending more time with them over the course of a week than their primary care provider might in a year,” Cao explained. “This gives us a real advantage in picking up on subtle changes in mental awareness.”

These assessments can also be evaluated with the benefit of daily labs, frequent bedside interactions, and 24–hour observations.

With older adults, Cao said it’s important to go beyond just what’s in the chart. 

“I always start by reviewing notes from the primary care provider and previous admissions, but some of the most valuable insights come from talking with family and close friends to get a true sense of the patient’s baseline — how they usually think, move, and interact,” he said.

 

Why to Watch for Declining Mental Awareness

Declining mental awareness in the inpatient setting is often a sign of an underlying problem — whether that’s a reversible medical condition, unrecognized dementia, or the development of delirium, Cao said.

“On the inpatient side, I pay close attention to more than just memory loss,” he said. 

Changes in how patients function day–to–day, shifts in their behavior, or even something as simple as not wanting to get out of bed can be early signs of an aging mind or untreated psychiatric issues, he noted. 

“Of course, we always rule out infections and medication side effects, but I also look for other reversible causes like thyroid problems, electrolyte imbalances, low oxygen, pain, urinary retention, constipation, and nutritional deficiencies,” Cao said.

Of note, delirium is the most common cause of sudden mental status changes in the hospital, and “it’s easy to miss if you’re not looking for it.”

He summarized that classic signs are an acute and fluctuating course with changes in alertness, but added there are other red flags too: disorientation, hallucinations, changes in sleep patterns, sporadic unsafe behaviors, mood swings, and changes in activity level, whether that’s agitation or just being unusually quiet. 

By combining what he notices bedside and what is learned from the medical record (and from the people who know the patient best), Cao said he’s able to catch these changes early, identify the underlying cause, and work toward the best possible outcome. 

“One of the main interventions is providing mental stimulation,” he said.

 

Why Mental Stimulation Is So Vital 

Mental stimulation of the patient is critical to recovery and may prevent prolonged illness, said Meghana R. Medavaram, MD, associate director of consultation liaison and emergency psychiatry at Montefiore Medical Center’s Weiler Hospital in New York City. “Keeping a patient active both physically and mentally can help prevent deconditioning and risks of prolonged immobility,” she said.

It’s important to note that when patients are out of their familiar routines, away from their usual environment and people, and their sleep is fragmented, this can make them even more vulnerable. Keeping patients mentally stimulated during their hospital stay can help maintain their attention, orientation, and a healthy sleep-wake cycle — all things that are easily thrown off in the hospital, Cao said. 

“These disruptions hit the pathways that control attention, wakefulness, and the sleep–wake cycle. That’s when you see attention drifting, orientation fading, and circadian rhythms unraveling, especially at night, which is why “sundowning” is so common, Cao said, referring to the syndrome where older adults or people with dementia experience behavioral changes in late afternoon or evening. “Mental stimulation is critical in the hospital because when the brain isn’t active and gets disoriented, it becomes an easy target for delirium.” 

He said delirium often develops in older adults when acute stressors like inflammation, low oxygen, metabolic imbalances, or sedating medications disrupt the brain’s arousal systems and networks, especially in older adults.

Therefore, Cao said, encourage your patients to be more engaged during the day through conversation, activities, or regular reorientation. “This supports the brain networks that help prevent inattention and confusion, which are the hallmarks of delirium. Daytime stimulation also helps build up the natural drive for nighttime sleep, so patients are less likely to nap during the day and be awake and disoriented at night.”

To support this, it’s helpful to schedule medications during waking hours instead of around–the–clock dosing that interrupts sleep, and to cluster nighttime care activities to minimize disturbances, Cao explained. Ensuring patients have their glasses, hearing aids, and familiar routines, along with encouraging mobility and hydration, further protects against delirium and supports patients’ cognitive health during hospitalization. “These same principles are just as important in outpatient subacute rehab settings and at home, so it’s essential to take home these strategies after discharge,” he said.

 

A Family Member or Friend May Help

Hospitalists can suggest straightforward ways to encourage families and friends to keep patients engaged during a hospital stay. Visits and chats can go a long way as conversations are incredibly grounding, Cao said. Other methods could be bringing in favorite foods or snacks, a phone chat or video call, or even showing prerecorded video messages. “These can be effective. Patients respond well to seeing and hearing familiar faces and voices, even if it’s just on a screen,” Cao said.

Beyond that, he said, activities such as watching and discussing the news, reading aloud, using tablets for games, watching movies, doing crossword puzzles, knitting, reminiscing, and playing word games can also be mentally stimulating for patients. 

In addition, safe exercises/activities that patients can do in bed — with advice from physical therapy and occupational therapy — are beneficial, Medavaram said. “These often include gentle range–of-motion activities,” she said. 

 

Share Importance of Mental Stimulation With Patients and Caregivers

If a hospitalist wants to motivate patients to keep their minds active, the framing should be simple, positive, and tied directly to their goals of getting better and getting home, said Medavaram. She provided this script suggestion:

“One of the best ways to help your recovery isn’t just taking your medicine, it’s keeping your mind active. When you’re in the hospital, it’s easy to spend the day lying in bed and staring at the TV in your room, but that can make your brain slow down and even cause confusion. Simple things — like reading, talking with visitors, doing puzzles, listening to music you enjoy, or telling a nurse about your favorite memories — can keep your brain sharp. Staying mentally active helps your thinking stay clear and can even help you get home sooner. Think of it like physical therapy for your brain.” 

A version of this article first appeared on Medscape.com.

As a hospitalist, you are in a unique position to notice changes in your hospitalized patients. This frontline perspective can be used to improve inpatient attention and care, and differs from primary care, where a clinician might only see a patient once or twice a year, and subtle, gradual changes may be missed, said George Cao, MD, MBA, a hospitalist at the University of Vermont Medical Center in Burlington and assistant professor at UVM’s Larner College of Medicine. 

But in the hospital, Cao said even small shifts — like becoming less active, eating less, or changes in personality — can become much more obvious. 

“As hospitalists…we see patients throughout the day, in different situations, and often end up spending more time with them over the course of a week than their primary care provider might in a year,” Cao explained. “This gives us a real advantage in picking up on subtle changes in mental awareness.”

These assessments can also be evaluated with the benefit of daily labs, frequent bedside interactions, and 24–hour observations.

With older adults, Cao said it’s important to go beyond just what’s in the chart. 

“I always start by reviewing notes from the primary care provider and previous admissions, but some of the most valuable insights come from talking with family and close friends to get a true sense of the patient’s baseline — how they usually think, move, and interact,” he said.

 

Why to Watch for Declining Mental Awareness

Declining mental awareness in the inpatient setting is often a sign of an underlying problem — whether that’s a reversible medical condition, unrecognized dementia, or the development of delirium, Cao said.

“On the inpatient side, I pay close attention to more than just memory loss,” he said. 

Changes in how patients function day–to–day, shifts in their behavior, or even something as simple as not wanting to get out of bed can be early signs of an aging mind or untreated psychiatric issues, he noted. 

“Of course, we always rule out infections and medication side effects, but I also look for other reversible causes like thyroid problems, electrolyte imbalances, low oxygen, pain, urinary retention, constipation, and nutritional deficiencies,” Cao said.

Of note, delirium is the most common cause of sudden mental status changes in the hospital, and “it’s easy to miss if you’re not looking for it.”

He summarized that classic signs are an acute and fluctuating course with changes in alertness, but added there are other red flags too: disorientation, hallucinations, changes in sleep patterns, sporadic unsafe behaviors, mood swings, and changes in activity level, whether that’s agitation or just being unusually quiet. 

By combining what he notices bedside and what is learned from the medical record (and from the people who know the patient best), Cao said he’s able to catch these changes early, identify the underlying cause, and work toward the best possible outcome. 

“One of the main interventions is providing mental stimulation,” he said.

 

Why Mental Stimulation Is So Vital 

Mental stimulation of the patient is critical to recovery and may prevent prolonged illness, said Meghana R. Medavaram, MD, associate director of consultation liaison and emergency psychiatry at Montefiore Medical Center’s Weiler Hospital in New York City. “Keeping a patient active both physically and mentally can help prevent deconditioning and risks of prolonged immobility,” she said.

It’s important to note that when patients are out of their familiar routines, away from their usual environment and people, and their sleep is fragmented, this can make them even more vulnerable. Keeping patients mentally stimulated during their hospital stay can help maintain their attention, orientation, and a healthy sleep-wake cycle — all things that are easily thrown off in the hospital, Cao said. 

“These disruptions hit the pathways that control attention, wakefulness, and the sleep–wake cycle. That’s when you see attention drifting, orientation fading, and circadian rhythms unraveling, especially at night, which is why “sundowning” is so common, Cao said, referring to the syndrome where older adults or people with dementia experience behavioral changes in late afternoon or evening. “Mental stimulation is critical in the hospital because when the brain isn’t active and gets disoriented, it becomes an easy target for delirium.” 

He said delirium often develops in older adults when acute stressors like inflammation, low oxygen, metabolic imbalances, or sedating medications disrupt the brain’s arousal systems and networks, especially in older adults.

Therefore, Cao said, encourage your patients to be more engaged during the day through conversation, activities, or regular reorientation. “This supports the brain networks that help prevent inattention and confusion, which are the hallmarks of delirium. Daytime stimulation also helps build up the natural drive for nighttime sleep, so patients are less likely to nap during the day and be awake and disoriented at night.”

To support this, it’s helpful to schedule medications during waking hours instead of around–the–clock dosing that interrupts sleep, and to cluster nighttime care activities to minimize disturbances, Cao explained. Ensuring patients have their glasses, hearing aids, and familiar routines, along with encouraging mobility and hydration, further protects against delirium and supports patients’ cognitive health during hospitalization. “These same principles are just as important in outpatient subacute rehab settings and at home, so it’s essential to take home these strategies after discharge,” he said.

 

A Family Member or Friend May Help

Hospitalists can suggest straightforward ways to encourage families and friends to keep patients engaged during a hospital stay. Visits and chats can go a long way as conversations are incredibly grounding, Cao said. Other methods could be bringing in favorite foods or snacks, a phone chat or video call, or even showing prerecorded video messages. “These can be effective. Patients respond well to seeing and hearing familiar faces and voices, even if it’s just on a screen,” Cao said.

Beyond that, he said, activities such as watching and discussing the news, reading aloud, using tablets for games, watching movies, doing crossword puzzles, knitting, reminiscing, and playing word games can also be mentally stimulating for patients. 

In addition, safe exercises/activities that patients can do in bed — with advice from physical therapy and occupational therapy — are beneficial, Medavaram said. “These often include gentle range–of-motion activities,” she said. 

 

Share Importance of Mental Stimulation With Patients and Caregivers

If a hospitalist wants to motivate patients to keep their minds active, the framing should be simple, positive, and tied directly to their goals of getting better and getting home, said Medavaram. She provided this script suggestion:

“One of the best ways to help your recovery isn’t just taking your medicine, it’s keeping your mind active. When you’re in the hospital, it’s easy to spend the day lying in bed and staring at the TV in your room, but that can make your brain slow down and even cause confusion. Simple things — like reading, talking with visitors, doing puzzles, listening to music you enjoy, or telling a nurse about your favorite memories — can keep your brain sharp. Staying mentally active helps your thinking stay clear and can even help you get home sooner. Think of it like physical therapy for your brain.” 

A version of this article first appeared on Medscape.com.

A recent worldwide survey found the United States to have the highest reported prevalence of type 2 diabetes mellitus (T2DM) among young people aged 10 to 19 years. Research on the prevalence of the disease among Indigenous populations is scarce, however, leaving these individuals at a potentially greater risk.

The estimated prevalence of T2DM has nearly doubled over the past 2 decades, with cases per 1000 youths aged 10 to 19 years increasing from 0.34 in 2001 to 0.46 in 2009 to 0.67 in 2017, a relative increase of 95.3% over 16 years. In 2012, the SEARCH study of youth-onset T2DM found American Indians and non-Hispanic Black individuals had the highest incidence (46.5/100,000/year in American Indians and 32.6/100,000/year in non-Hispanic Black individuals), compared with non-Hispanic White individuals (3.9/100,000/year).

About 28,000 US youth aged < 20 years had T2DM in 2017, a figure expected to reach 48,000 in 2060 based on increasing prevalence and incidence rates. Assuming the trends observed between 2002 and 2017 continue, an estimated 220,000 young people will have T2DM. 

However, the lack of recent research of T2DM in young indigenous populations may have masked a serious problem among Native Americans. A 2025 literature review of 49 studies call it a “type 2 diabetes crisis” among Indigenous communities; not because of the disease, but due to high rates of complications. Though Indigenous peoples are estimated to inhabit > 90 countries and collectively represent > 370 million people, the studies included in the review involved individuals from 6 countries and 2 self-governing states (US, Canada, Australia, Aotearoa New Zealand, Nauru, Argentina, the Cook Islands, and Niue) and at least 45 Indigenous populations after search criteria were satisfied. Data were derived from population-based screening and health databases, including from 432 IHS facilities and 6 IHS regions.

Of the study populations, 27 (75%) reported diabetes prevalence above 1 per 1000. Age-specific data, available in 44 studies, showed increased prevalence with age: 0 to 4 per 1000 at age < 10 years; 0 to 44 per 1000 at age 10 to 19 years; and 0 to 64 per 1000 at age 15 to 25 years. 

In young adults aged 15 to 25 years, prevalence was highest in Akimel O’odham and Tohono O’odham Peoples from the Gila River Indian Community in Arizona. Among children aged < 10 years, the highest prevalence was reported in Cherokee Nation children. Some groups reported no diabetes, such as the Northern Plains Indians from Montana and Wyoming.

Statistics showing the speed of expanding prevalence were particularly notable. For Akimel O’odham and Tohono O’odham Indian youth, diabetes prevalence increased more than eightfold over 2 decades (particularly in those aged < 15).

A 2021 study of 500 participants who were diagnosed with T2DM in youth were followed for a mean of 13 years. By the time they were 26, 67.5% had hypertension, 51.6% had dyslipidemia, 54.8% had diabetic kidney disease, and 32.4% had nerve disease. 

Indigenous North American children may also have an even greater risk for later complications. A Canadian study found that among Canadian First Nations Peoples the incidence of end-stage kidney disease was 2.8 times higher and the mortality rate was double that of non-Indigenous people with youth-onset T2DM despite similar age at diagnosis and duration of disease. 

To combat the steady increase of T2DM prevalence among Indigenous youth, researchers advise “urgent action” to improve data equity through the inclusion of Indigenous populations in health surveillance, routine disaggregation by Indigenous status, and culturally safe research partnerships led by Indigenous communities. Standardized age group classifications, age- and gender-specific reporting, and assessment of comorbid obesity are essential, they add, to define health care needs and identify regions that would benefit from enhanced early detection and management.

A recent worldwide survey found the United States to have the highest reported prevalence of type 2 diabetes mellitus (T2DM) among young people aged 10 to 19 years. Research on the prevalence of the disease among Indigenous populations is scarce, however, leaving these individuals at a potentially greater risk.

The estimated prevalence of T2DM has nearly doubled over the past 2 decades, with cases per 1000 youths aged 10 to 19 years increasing from 0.34 in 2001 to 0.46 in 2009 to 0.67 in 2017, a relative increase of 95.3% over 16 years. In 2012, the SEARCH study of youth-onset T2DM found American Indians and non-Hispanic Black individuals had the highest incidence (46.5/100,000/year in American Indians and 32.6/100,000/year in non-Hispanic Black individuals), compared with non-Hispanic White individuals (3.9/100,000/year).

About 28,000 US youth aged < 20 years had T2DM in 2017, a figure expected to reach 48,000 in 2060 based on increasing prevalence and incidence rates. Assuming the trends observed between 2002 and 2017 continue, an estimated 220,000 young people will have T2DM. 

However, the lack of recent research of T2DM in young indigenous populations may have masked a serious problem among Native Americans. A 2025 literature review of 49 studies call it a “type 2 diabetes crisis” among Indigenous communities; not because of the disease, but due to high rates of complications. Though Indigenous peoples are estimated to inhabit > 90 countries and collectively represent > 370 million people, the studies included in the review involved individuals from 6 countries and 2 self-governing states (US, Canada, Australia, Aotearoa New Zealand, Nauru, Argentina, the Cook Islands, and Niue) and at least 45 Indigenous populations after search criteria were satisfied. Data were derived from population-based screening and health databases, including from 432 IHS facilities and 6 IHS regions.

Of the study populations, 27 (75%) reported diabetes prevalence above 1 per 1000. Age-specific data, available in 44 studies, showed increased prevalence with age: 0 to 4 per 1000 at age < 10 years; 0 to 44 per 1000 at age 10 to 19 years; and 0 to 64 per 1000 at age 15 to 25 years. 

In young adults aged 15 to 25 years, prevalence was highest in Akimel O’odham and Tohono O’odham Peoples from the Gila River Indian Community in Arizona. Among children aged < 10 years, the highest prevalence was reported in Cherokee Nation children. Some groups reported no diabetes, such as the Northern Plains Indians from Montana and Wyoming.

Statistics showing the speed of expanding prevalence were particularly notable. For Akimel O’odham and Tohono O’odham Indian youth, diabetes prevalence increased more than eightfold over 2 decades (particularly in those aged < 15).

A 2021 study of 500 participants who were diagnosed with T2DM in youth were followed for a mean of 13 years. By the time they were 26, 67.5% had hypertension, 51.6% had dyslipidemia, 54.8% had diabetic kidney disease, and 32.4% had nerve disease. 

Indigenous North American children may also have an even greater risk for later complications. A Canadian study found that among Canadian First Nations Peoples the incidence of end-stage kidney disease was 2.8 times higher and the mortality rate was double that of non-Indigenous people with youth-onset T2DM despite similar age at diagnosis and duration of disease. 

To combat the steady increase of T2DM prevalence among Indigenous youth, researchers advise “urgent action” to improve data equity through the inclusion of Indigenous populations in health surveillance, routine disaggregation by Indigenous status, and culturally safe research partnerships led by Indigenous communities. Standardized age group classifications, age- and gender-specific reporting, and assessment of comorbid obesity are essential, they add, to define health care needs and identify regions that would benefit from enhanced early detection and management.

A recent worldwide survey found the United States to have the highest reported prevalence of type 2 diabetes mellitus (T2DM) among young people aged 10 to 19 years. Research on the prevalence of the disease among Indigenous populations is scarce, however, leaving these individuals at a potentially greater risk.

The estimated prevalence of T2DM has nearly doubled over the past 2 decades, with cases per 1000 youths aged 10 to 19 years increasing from 0.34 in 2001 to 0.46 in 2009 to 0.67 in 2017, a relative increase of 95.3% over 16 years. In 2012, the SEARCH study of youth-onset T2DM found American Indians and non-Hispanic Black individuals had the highest incidence (46.5/100,000/year in American Indians and 32.6/100,000/year in non-Hispanic Black individuals), compared with non-Hispanic White individuals (3.9/100,000/year).

About 28,000 US youth aged < 20 years had T2DM in 2017, a figure expected to reach 48,000 in 2060 based on increasing prevalence and incidence rates. Assuming the trends observed between 2002 and 2017 continue, an estimated 220,000 young people will have T2DM. 

However, the lack of recent research of T2DM in young indigenous populations may have masked a serious problem among Native Americans. A 2025 literature review of 49 studies call it a “type 2 diabetes crisis” among Indigenous communities; not because of the disease, but due to high rates of complications. Though Indigenous peoples are estimated to inhabit > 90 countries and collectively represent > 370 million people, the studies included in the review involved individuals from 6 countries and 2 self-governing states (US, Canada, Australia, Aotearoa New Zealand, Nauru, Argentina, the Cook Islands, and Niue) and at least 45 Indigenous populations after search criteria were satisfied. Data were derived from population-based screening and health databases, including from 432 IHS facilities and 6 IHS regions.

Of the study populations, 27 (75%) reported diabetes prevalence above 1 per 1000. Age-specific data, available in 44 studies, showed increased prevalence with age: 0 to 4 per 1000 at age < 10 years; 0 to 44 per 1000 at age 10 to 19 years; and 0 to 64 per 1000 at age 15 to 25 years. 

In young adults aged 15 to 25 years, prevalence was highest in Akimel O’odham and Tohono O’odham Peoples from the Gila River Indian Community in Arizona. Among children aged < 10 years, the highest prevalence was reported in Cherokee Nation children. Some groups reported no diabetes, such as the Northern Plains Indians from Montana and Wyoming.

Statistics showing the speed of expanding prevalence were particularly notable. For Akimel O’odham and Tohono O’odham Indian youth, diabetes prevalence increased more than eightfold over 2 decades (particularly in those aged < 15).

A 2021 study of 500 participants who were diagnosed with T2DM in youth were followed for a mean of 13 years. By the time they were 26, 67.5% had hypertension, 51.6% had dyslipidemia, 54.8% had diabetic kidney disease, and 32.4% had nerve disease. 

Indigenous North American children may also have an even greater risk for later complications. A Canadian study found that among Canadian First Nations Peoples the incidence of end-stage kidney disease was 2.8 times higher and the mortality rate was double that of non-Indigenous people with youth-onset T2DM despite similar age at diagnosis and duration of disease. 

To combat the steady increase of T2DM prevalence among Indigenous youth, researchers advise “urgent action” to improve data equity through the inclusion of Indigenous populations in health surveillance, routine disaggregation by Indigenous status, and culturally safe research partnerships led by Indigenous communities. Standardized age group classifications, age- and gender-specific reporting, and assessment of comorbid obesity are essential, they add, to define health care needs and identify regions that would benefit from enhanced early detection and management.

The FDA approved a supplemental new drug application for the JAK inhibitor upadacitinib (Rinvoq, AbbVie) permitting its use in the treatment of adults with moderately to severely active ulcerative colitis and Crohn’s disease.

The updated indication allows for starting upadacitinib before a TNF blocker in patients for whom use of these treatments is clinically inadvisable and who have received at least one approved systemic therapy, the company said in a statement. 

Previously, upadacitinib was indicated only in adults with moderately to severely active ulcerative colitis or Crohn’s disease who had an inadequate response or intolerance to one or more TNF blockers. 

“Ulcerative colitis and Crohn’s disease can impact every aspect of a patient’s life. This label update gives healthcare providers the option to prescribe Rinvoq for patients with moderately to severely active inflammatory bowel disease after the use of one approved systemic therapy if TNF blockers are deemed clinically inadvisable by the prescribing physician,” Kori Wallace, MD, PhD, vice president and global head of immunology clinical development at AbbVie, said in the statement. 

Full prescribing information is available online. 

Wallace is an employee of AbbVie.

A version of this article appeared on Medscape.com . 

The FDA approved a supplemental new drug application for the JAK inhibitor upadacitinib (Rinvoq, AbbVie) permitting its use in the treatment of adults with moderately to severely active ulcerative colitis and Crohn’s disease.

The updated indication allows for starting upadacitinib before a TNF blocker in patients for whom use of these treatments is clinically inadvisable and who have received at least one approved systemic therapy, the company said in a statement. 

Previously, upadacitinib was indicated only in adults with moderately to severely active ulcerative colitis or Crohn’s disease who had an inadequate response or intolerance to one or more TNF blockers. 

“Ulcerative colitis and Crohn’s disease can impact every aspect of a patient’s life. This label update gives healthcare providers the option to prescribe Rinvoq for patients with moderately to severely active inflammatory bowel disease after the use of one approved systemic therapy if TNF blockers are deemed clinically inadvisable by the prescribing physician,” Kori Wallace, MD, PhD, vice president and global head of immunology clinical development at AbbVie, said in the statement. 

Full prescribing information is available online. 

Wallace is an employee of AbbVie.

A version of this article appeared on Medscape.com . 

The FDA approved a supplemental new drug application for the JAK inhibitor upadacitinib (Rinvoq, AbbVie) permitting its use in the treatment of adults with moderately to severely active ulcerative colitis and Crohn’s disease.

The updated indication allows for starting upadacitinib before a TNF blocker in patients for whom use of these treatments is clinically inadvisable and who have received at least one approved systemic therapy, the company said in a statement. 

Previously, upadacitinib was indicated only in adults with moderately to severely active ulcerative colitis or Crohn’s disease who had an inadequate response or intolerance to one or more TNF blockers. 

“Ulcerative colitis and Crohn’s disease can impact every aspect of a patient’s life. This label update gives healthcare providers the option to prescribe Rinvoq for patients with moderately to severely active inflammatory bowel disease after the use of one approved systemic therapy if TNF blockers are deemed clinically inadvisable by the prescribing physician,” Kori Wallace, MD, PhD, vice president and global head of immunology clinical development at AbbVie, said in the statement. 

Full prescribing information is available online. 

Wallace is an employee of AbbVie.

A version of this article appeared on Medscape.com . 

The role of the hospitalist is multidisciplinary and one of the primary responsibilities in your role is to notice and act on the changes you notice regarding your patients, including mental awareness and acuity.

"Evaluation of orientation and level of awareness is a core component of any hospitalist's daily evaluation," said Tara Scribner, MD, an internal medicine hospitalist, The University of Vermont Medical Center; associate program director for POCUS and Procedure Curriculum, UVMMC Internal Medicine Residency Program; and an assistant professor, Robert Larner, M.D. College of Medicine, Burlington, Vermont. "Beyond this, a broader assessment of executive function and functional abilities always occurs at some point during a hospital admission as discharge location and situation depends on this."

While it's relatively easy to identify signs of dementia using information from collateral sources, she also noted it's often difficult to determine whether a patient is experiencing progressive dementia or a more acute encephalopathy such as delirium if collateral sources are not available.

"Once a baseline has been established, hospitalists are in a unique position to identify subtle and acute shifts in mental acuity over the course of a hospital stay," Scribner said. "Unlike our primary care colleagues, who are well-positioned to observe for signs of dementia, we see our patients on a daily basis, sometimes more than once daily, and can track changes which occur over a matter of hours or days."

What Are Signs to Watch

During examinations and assessments, pay attention to shifts in the behavior of patients.

"Subtle signs of delirium and/or declining mental awareness can include disorientation about date, location, reason for admission," said Meghana R. Medavaram, MD, associate director of Consultation Liaison and Emergency Psychiatry, Weiler Hospital at Montefiore Health System in Bronx, New York.

Another sign would be mild inattention, such as drifting off during conversations or even having a hard time understanding and following multistep commands, she also said.

"We can also see sudden irritability or even the opposite, odd politeness or familiarity. We notice these changes occur as fluctuations throughout the day, sometimes with a clinician seeing a different 'personality' in the morning vs afternoon or evening," Medavaram said. "A key message we emphasize for our hospitalist colleagues is to not wait for overt agitation, or hallucinations to step in when assessing a patient and coming up with a treatment plan."

How Would Diet Play a Role

Excess consumption of alcohol is the most common way a patient's diet can affect changes in mental status, said Scribner. "Excess alcohol use has been linked to a significantly increased risk of dementia including both Alzheimer's and to alcohol-related brain damage including Korsakoff syndrome, as well as to the more acute Wernicke encephalopathy through vitamin B1 deficiency."

Also, vitamin deficiencies such as B12 have been linked to development of dementia and other cognitive impairment and can be related to alcohol consumption as well as to dietary habits such as vegetarianism, even in the absence of alcohol intake. Identification and treatment of B12 deficiency is a potentially reversible cause of cognitive impairment, she also said.

Do Medications Affect Mental State

Medications can be a significant cause of acute changes in mental status. "These changes are often reversible and include somnolence and both hypoactive and hyperactive delirium. Adjustment of a patient's usual medications is often necessary in hospitalized patients experiencing acute encephalopathy," Scribner said.

What About Depression

The relationship between dementia and development of dementia is complex and poorly understood, she said, however, those who deal with depression are at a higher risk of developing dementia, and also that patients with dementia are at a higher risk for development of depression.

How to Distinguish Between Short- and Long-term Issues

A thorough hospitalist is typically able to identify the acuity of mental status changes by the time of discharge and therefore predict the likelihood of recovery.

Progressive mental status changes occurring over months to years are almost always representative of dementia and are irreversible, whereas most (but not all) acute encephalopathies are recoverable over days to weeks or months.

Determining which of these is present involves interrogation of collateral sources such as family and friends, assessment of orientation and other signs of delirium, and observation of recovery during the period of hospital admission. It is worth noting that episodes of delirium are associated with a higher risk for long-term cognitive decline and development of dementia.

Written by Erica Lamberg.

A version of this article first appeared on Medscape.com.

The role of the hospitalist is multidisciplinary and one of the primary responsibilities in your role is to notice and act on the changes you notice regarding your patients, including mental awareness and acuity.

"Evaluation of orientation and level of awareness is a core component of any hospitalist's daily evaluation," said Tara Scribner, MD, an internal medicine hospitalist, The University of Vermont Medical Center; associate program director for POCUS and Procedure Curriculum, UVMMC Internal Medicine Residency Program; and an assistant professor, Robert Larner, M.D. College of Medicine, Burlington, Vermont. "Beyond this, a broader assessment of executive function and functional abilities always occurs at some point during a hospital admission as discharge location and situation depends on this."

While it's relatively easy to identify signs of dementia using information from collateral sources, she also noted it's often difficult to determine whether a patient is experiencing progressive dementia or a more acute encephalopathy such as delirium if collateral sources are not available.

"Once a baseline has been established, hospitalists are in a unique position to identify subtle and acute shifts in mental acuity over the course of a hospital stay," Scribner said. "Unlike our primary care colleagues, who are well-positioned to observe for signs of dementia, we see our patients on a daily basis, sometimes more than once daily, and can track changes which occur over a matter of hours or days."

What Are Signs to Watch

During examinations and assessments, pay attention to shifts in the behavior of patients.

"Subtle signs of delirium and/or declining mental awareness can include disorientation about date, location, reason for admission," said Meghana R. Medavaram, MD, associate director of Consultation Liaison and Emergency Psychiatry, Weiler Hospital at Montefiore Health System in Bronx, New York.

Another sign would be mild inattention, such as drifting off during conversations or even having a hard time understanding and following multistep commands, she also said.

"We can also see sudden irritability or even the opposite, odd politeness or familiarity. We notice these changes occur as fluctuations throughout the day, sometimes with a clinician seeing a different 'personality' in the morning vs afternoon or evening," Medavaram said. "A key message we emphasize for our hospitalist colleagues is to not wait for overt agitation, or hallucinations to step in when assessing a patient and coming up with a treatment plan."

How Would Diet Play a Role

Excess consumption of alcohol is the most common way a patient's diet can affect changes in mental status, said Scribner. "Excess alcohol use has been linked to a significantly increased risk of dementia including both Alzheimer's and to alcohol-related brain damage including Korsakoff syndrome, as well as to the more acute Wernicke encephalopathy through vitamin B1 deficiency."

Also, vitamin deficiencies such as B12 have been linked to development of dementia and other cognitive impairment and can be related to alcohol consumption as well as to dietary habits such as vegetarianism, even in the absence of alcohol intake. Identification and treatment of B12 deficiency is a potentially reversible cause of cognitive impairment, she also said.

Do Medications Affect Mental State

Medications can be a significant cause of acute changes in mental status. "These changes are often reversible and include somnolence and both hypoactive and hyperactive delirium. Adjustment of a patient's usual medications is often necessary in hospitalized patients experiencing acute encephalopathy," Scribner said.

What About Depression

The relationship between dementia and development of dementia is complex and poorly understood, she said, however, those who deal with depression are at a higher risk of developing dementia, and also that patients with dementia are at a higher risk for development of depression.

How to Distinguish Between Short- and Long-term Issues

A thorough hospitalist is typically able to identify the acuity of mental status changes by the time of discharge and therefore predict the likelihood of recovery.

Progressive mental status changes occurring over months to years are almost always representative of dementia and are irreversible, whereas most (but not all) acute encephalopathies are recoverable over days to weeks or months.

Determining which of these is present involves interrogation of collateral sources such as family and friends, assessment of orientation and other signs of delirium, and observation of recovery during the period of hospital admission. It is worth noting that episodes of delirium are associated with a higher risk for long-term cognitive decline and development of dementia.

Written by Erica Lamberg.

A version of this article first appeared on Medscape.com.

The role of the hospitalist is multidisciplinary and one of the primary responsibilities in your role is to notice and act on the changes you notice regarding your patients, including mental awareness and acuity.

"Evaluation of orientation and level of awareness is a core component of any hospitalist's daily evaluation," said Tara Scribner, MD, an internal medicine hospitalist, The University of Vermont Medical Center; associate program director for POCUS and Procedure Curriculum, UVMMC Internal Medicine Residency Program; and an assistant professor, Robert Larner, M.D. College of Medicine, Burlington, Vermont. "Beyond this, a broader assessment of executive function and functional abilities always occurs at some point during a hospital admission as discharge location and situation depends on this."

While it's relatively easy to identify signs of dementia using information from collateral sources, she also noted it's often difficult to determine whether a patient is experiencing progressive dementia or a more acute encephalopathy such as delirium if collateral sources are not available.

"Once a baseline has been established, hospitalists are in a unique position to identify subtle and acute shifts in mental acuity over the course of a hospital stay," Scribner said. "Unlike our primary care colleagues, who are well-positioned to observe for signs of dementia, we see our patients on a daily basis, sometimes more than once daily, and can track changes which occur over a matter of hours or days."

What Are Signs to Watch

During examinations and assessments, pay attention to shifts in the behavior of patients.

"Subtle signs of delirium and/or declining mental awareness can include disorientation about date, location, reason for admission," said Meghana R. Medavaram, MD, associate director of Consultation Liaison and Emergency Psychiatry, Weiler Hospital at Montefiore Health System in Bronx, New York.

Another sign would be mild inattention, such as drifting off during conversations or even having a hard time understanding and following multistep commands, she also said.

"We can also see sudden irritability or even the opposite, odd politeness or familiarity. We notice these changes occur as fluctuations throughout the day, sometimes with a clinician seeing a different 'personality' in the morning vs afternoon or evening," Medavaram said. "A key message we emphasize for our hospitalist colleagues is to not wait for overt agitation, or hallucinations to step in when assessing a patient and coming up with a treatment plan."

How Would Diet Play a Role

Excess consumption of alcohol is the most common way a patient's diet can affect changes in mental status, said Scribner. "Excess alcohol use has been linked to a significantly increased risk of dementia including both Alzheimer's and to alcohol-related brain damage including Korsakoff syndrome, as well as to the more acute Wernicke encephalopathy through vitamin B1 deficiency."

Also, vitamin deficiencies such as B12 have been linked to development of dementia and other cognitive impairment and can be related to alcohol consumption as well as to dietary habits such as vegetarianism, even in the absence of alcohol intake. Identification and treatment of B12 deficiency is a potentially reversible cause of cognitive impairment, she also said.

Do Medications Affect Mental State

Medications can be a significant cause of acute changes in mental status. "These changes are often reversible and include somnolence and both hypoactive and hyperactive delirium. Adjustment of a patient's usual medications is often necessary in hospitalized patients experiencing acute encephalopathy," Scribner said.

What About Depression

The relationship between dementia and development of dementia is complex and poorly understood, she said, however, those who deal with depression are at a higher risk of developing dementia, and also that patients with dementia are at a higher risk for development of depression.

How to Distinguish Between Short- and Long-term Issues

A thorough hospitalist is typically able to identify the acuity of mental status changes by the time of discharge and therefore predict the likelihood of recovery.

Progressive mental status changes occurring over months to years are almost always representative of dementia and are irreversible, whereas most (but not all) acute encephalopathies are recoverable over days to weeks or months.

Determining which of these is present involves interrogation of collateral sources such as family and friends, assessment of orientation and other signs of delirium, and observation of recovery during the period of hospital admission. It is worth noting that episodes of delirium are associated with a higher risk for long-term cognitive decline and development of dementia.

Written by Erica Lamberg.

A version of this article first appeared on Medscape.com.

According to the National Institute on Drug Abuse, > 1 in 10 veterans have been diagnosed with substance use disorder (SUD). Additionally, 7 out of every 100 veterans will have posttraumatic stress disorder (PTSD) at some point in their life, per research from the US Department of Veterans Affairs (VA). However, a common and perhaps unsuspected parallel is found in those statistics: loneliness.

Of the 4069 veterans who participated in the 2019-2020 National Health and Resilience in Veterans Survey, 56.9% reported they felt lonely sometimes or often, while 1 in 5 reported feeling lonely often.

An Epidemic

In his 2023 advisory, Former US Surgeon General Vivek Murthy called it an epidemic noting that when he spoke with veterans during a cross-country listening tour, he heard how they felt “isolated, invisible, and insignificant.” About 1 in 2 adults in America experience loneliness, even before the COVID-19 pandemic isolation.

Loneliness can have individual and synergistic ill effects, including a greater risk of cardiovascular disease, dementia, stroke, depression, anxiety, and premature death. It also can both trigger and exacerbate substance use and PTSD.

A study using data from the RAND Health and Retirement Study Longitudinal File 2020 (N = 5259) found significant associations between loneliness and being unmarried/unpartnered, and greater depressive symptoms for both veterans and civilians, as well as significant negative associations between loneliness and greater life satisfaction and positive affect. Health conditions that limited an individual's ability to work was a “unique risk factor for loneliness among veterans.”

The National Health and Resilience in Veterans Study found that those aged ≤ 50 years were 3 times more likely to screen positive for PTSD compared to older veterans. In a survey of 409 veterans, many who engaged in problematic substance use during the COVID-19 pandemic reported that despite having social supports they still felt lonely. In regression analyses, higher levels of loneliness were associated with more negative impacts of the pandemic, greater substance use, and poorer physical and mental health functioning.

Addressing Loneliness

Researchers believe an answer to some mental health and substance abuse problems may lie in addressing loneliness. Positive psychology is providing promising results in the treatment of SUD. Bryant Stone, from the Johns Hopkins Bloomberg School of Public Health, emphasizes focusing on well-being and quality of life rather than solely on abstinence with “positive psychological interventions,” or activities and behavioral interventions that target positive variables to promote adaptive functioning.

Veterans can face tough challenges as they rejoin civilian life. How successfully they meet and conquer those challenges, especially if they include drug problems, may directly relate to their general feeling of well-being.

The PERMA model outlines 5 core elements to assess well-being: Positive emotions, Engagement, Relationships, Meaning, and Accomplishment. A study based on that model found loneliness to be a “particularly significant factor” among key variables influencing the prevention and treatment of SUDs. The study of 156 veterans with self-reported mental health conditions found the ability to engage in social roles and activities was positively correlated with overall well-being and negatively correlated with degree of problems related to drug abuse. 

Rural Veterans

The estimated 4.4 million veterans living in rural communities may benefit most from interventions that tackle isolation. Compared with urban counterparts, they’re more likely to be older, have more complex medical issues, have a service-connected disability, and be unemployed. Those factors, compounded by geographical and social isolation, can have a substantial impact on well-being.

A study centered on the initial validation of a short (5-item) version of PERMA found that individuals who scored higher on the short form tended to report higher levels of optimism, resilience, and happiness. Thus, the short form may be particularly useful for rural veterans who do not always have easy access to health care.

VA has instituted a variety of programs to encourage and support social connection. During the COVID-19 pandemic, telehealth interventions targeted social support and loneliness among veterans—albeit with mixed results. VA CONNECT, a 10-session group telehealth intervention that integrated peer support, did not show significant changes in loneliness, but did significantly reduce perceived stress. 

Another initiative, Compassionate Contact Corps, trained volunteers made weekly phone calls aimed at reducing loneliness and fostering social connection. Started in Columbus, Ohio, in 2020, > 80 sites had adopted the initiative by 2021, with 310 volunteers, 5320 visits, and 4757 hours spent with veterans.

In 2014, VA peer specialists developed and co-hosted Veterans Socials through community partnerships between VA, veteran-serving organizations, and veteran community leaders. As of 2025, 178 known Veterans Socials were spread across 26 states and territories.

The researchers say their case examples collectively demonstrate that Veterans Socials have the potential to serve as a vital platform for peer support, resource sharing, and health service use among veterans. Virtual Veterans Socials also provided hosts with a channel to reach potentially isolated veterans who might not otherwise access services while simultaneously offering veterans an opportunity for social connection.

According to the National Institute on Drug Abuse, > 1 in 10 veterans have been diagnosed with substance use disorder (SUD). Additionally, 7 out of every 100 veterans will have posttraumatic stress disorder (PTSD) at some point in their life, per research from the US Department of Veterans Affairs (VA). However, a common and perhaps unsuspected parallel is found in those statistics: loneliness.

Of the 4069 veterans who participated in the 2019-2020 National Health and Resilience in Veterans Survey, 56.9% reported they felt lonely sometimes or often, while 1 in 5 reported feeling lonely often.

An Epidemic

In his 2023 advisory, Former US Surgeon General Vivek Murthy called it an epidemic noting that when he spoke with veterans during a cross-country listening tour, he heard how they felt “isolated, invisible, and insignificant.” About 1 in 2 adults in America experience loneliness, even before the COVID-19 pandemic isolation.

Loneliness can have individual and synergistic ill effects, including a greater risk of cardiovascular disease, dementia, stroke, depression, anxiety, and premature death. It also can both trigger and exacerbate substance use and PTSD.

A study using data from the RAND Health and Retirement Study Longitudinal File 2020 (N = 5259) found significant associations between loneliness and being unmarried/unpartnered, and greater depressive symptoms for both veterans and civilians, as well as significant negative associations between loneliness and greater life satisfaction and positive affect. Health conditions that limited an individual's ability to work was a “unique risk factor for loneliness among veterans.”

The National Health and Resilience in Veterans Study found that those aged ≤ 50 years were 3 times more likely to screen positive for PTSD compared to older veterans. In a survey of 409 veterans, many who engaged in problematic substance use during the COVID-19 pandemic reported that despite having social supports they still felt lonely. In regression analyses, higher levels of loneliness were associated with more negative impacts of the pandemic, greater substance use, and poorer physical and mental health functioning.

Addressing Loneliness

Researchers believe an answer to some mental health and substance abuse problems may lie in addressing loneliness. Positive psychology is providing promising results in the treatment of SUD. Bryant Stone, from the Johns Hopkins Bloomberg School of Public Health, emphasizes focusing on well-being and quality of life rather than solely on abstinence with “positive psychological interventions,” or activities and behavioral interventions that target positive variables to promote adaptive functioning.

Veterans can face tough challenges as they rejoin civilian life. How successfully they meet and conquer those challenges, especially if they include drug problems, may directly relate to their general feeling of well-being.

The PERMA model outlines 5 core elements to assess well-being: Positive emotions, Engagement, Relationships, Meaning, and Accomplishment. A study based on that model found loneliness to be a “particularly significant factor” among key variables influencing the prevention and treatment of SUDs. The study of 156 veterans with self-reported mental health conditions found the ability to engage in social roles and activities was positively correlated with overall well-being and negatively correlated with degree of problems related to drug abuse. 

Rural Veterans

The estimated 4.4 million veterans living in rural communities may benefit most from interventions that tackle isolation. Compared with urban counterparts, they’re more likely to be older, have more complex medical issues, have a service-connected disability, and be unemployed. Those factors, compounded by geographical and social isolation, can have a substantial impact on well-being.

A study centered on the initial validation of a short (5-item) version of PERMA found that individuals who scored higher on the short form tended to report higher levels of optimism, resilience, and happiness. Thus, the short form may be particularly useful for rural veterans who do not always have easy access to health care.

VA has instituted a variety of programs to encourage and support social connection. During the COVID-19 pandemic, telehealth interventions targeted social support and loneliness among veterans—albeit with mixed results. VA CONNECT, a 10-session group telehealth intervention that integrated peer support, did not show significant changes in loneliness, but did significantly reduce perceived stress. 

Another initiative, Compassionate Contact Corps, trained volunteers made weekly phone calls aimed at reducing loneliness and fostering social connection. Started in Columbus, Ohio, in 2020, > 80 sites had adopted the initiative by 2021, with 310 volunteers, 5320 visits, and 4757 hours spent with veterans.

In 2014, VA peer specialists developed and co-hosted Veterans Socials through community partnerships between VA, veteran-serving organizations, and veteran community leaders. As of 2025, 178 known Veterans Socials were spread across 26 states and territories.

The researchers say their case examples collectively demonstrate that Veterans Socials have the potential to serve as a vital platform for peer support, resource sharing, and health service use among veterans. Virtual Veterans Socials also provided hosts with a channel to reach potentially isolated veterans who might not otherwise access services while simultaneously offering veterans an opportunity for social connection.

According to the National Institute on Drug Abuse, > 1 in 10 veterans have been diagnosed with substance use disorder (SUD). Additionally, 7 out of every 100 veterans will have posttraumatic stress disorder (PTSD) at some point in their life, per research from the US Department of Veterans Affairs (VA). However, a common and perhaps unsuspected parallel is found in those statistics: loneliness.

Of the 4069 veterans who participated in the 2019-2020 National Health and Resilience in Veterans Survey, 56.9% reported they felt lonely sometimes or often, while 1 in 5 reported feeling lonely often.

An Epidemic

In his 2023 advisory, Former US Surgeon General Vivek Murthy called it an epidemic noting that when he spoke with veterans during a cross-country listening tour, he heard how they felt “isolated, invisible, and insignificant.” About 1 in 2 adults in America experience loneliness, even before the COVID-19 pandemic isolation.

Loneliness can have individual and synergistic ill effects, including a greater risk of cardiovascular disease, dementia, stroke, depression, anxiety, and premature death. It also can both trigger and exacerbate substance use and PTSD.

A study using data from the RAND Health and Retirement Study Longitudinal File 2020 (N = 5259) found significant associations between loneliness and being unmarried/unpartnered, and greater depressive symptoms for both veterans and civilians, as well as significant negative associations between loneliness and greater life satisfaction and positive affect. Health conditions that limited an individual's ability to work was a “unique risk factor for loneliness among veterans.”

The National Health and Resilience in Veterans Study found that those aged ≤ 50 years were 3 times more likely to screen positive for PTSD compared to older veterans. In a survey of 409 veterans, many who engaged in problematic substance use during the COVID-19 pandemic reported that despite having social supports they still felt lonely. In regression analyses, higher levels of loneliness were associated with more negative impacts of the pandemic, greater substance use, and poorer physical and mental health functioning.

Addressing Loneliness

Researchers believe an answer to some mental health and substance abuse problems may lie in addressing loneliness. Positive psychology is providing promising results in the treatment of SUD. Bryant Stone, from the Johns Hopkins Bloomberg School of Public Health, emphasizes focusing on well-being and quality of life rather than solely on abstinence with “positive psychological interventions,” or activities and behavioral interventions that target positive variables to promote adaptive functioning.

Veterans can face tough challenges as they rejoin civilian life. How successfully they meet and conquer those challenges, especially if they include drug problems, may directly relate to their general feeling of well-being.

The PERMA model outlines 5 core elements to assess well-being: Positive emotions, Engagement, Relationships, Meaning, and Accomplishment. A study based on that model found loneliness to be a “particularly significant factor” among key variables influencing the prevention and treatment of SUDs. The study of 156 veterans with self-reported mental health conditions found the ability to engage in social roles and activities was positively correlated with overall well-being and negatively correlated with degree of problems related to drug abuse. 

Rural Veterans

The estimated 4.4 million veterans living in rural communities may benefit most from interventions that tackle isolation. Compared with urban counterparts, they’re more likely to be older, have more complex medical issues, have a service-connected disability, and be unemployed. Those factors, compounded by geographical and social isolation, can have a substantial impact on well-being.

A study centered on the initial validation of a short (5-item) version of PERMA found that individuals who scored higher on the short form tended to report higher levels of optimism, resilience, and happiness. Thus, the short form may be particularly useful for rural veterans who do not always have easy access to health care.

VA has instituted a variety of programs to encourage and support social connection. During the COVID-19 pandemic, telehealth interventions targeted social support and loneliness among veterans—albeit with mixed results. VA CONNECT, a 10-session group telehealth intervention that integrated peer support, did not show significant changes in loneliness, but did significantly reduce perceived stress. 

Another initiative, Compassionate Contact Corps, trained volunteers made weekly phone calls aimed at reducing loneliness and fostering social connection. Started in Columbus, Ohio, in 2020, > 80 sites had adopted the initiative by 2021, with 310 volunteers, 5320 visits, and 4757 hours spent with veterans.

In 2014, VA peer specialists developed and co-hosted Veterans Socials through community partnerships between VA, veteran-serving organizations, and veteran community leaders. As of 2025, 178 known Veterans Socials were spread across 26 states and territories.

The researchers say their case examples collectively demonstrate that Veterans Socials have the potential to serve as a vital platform for peer support, resource sharing, and health service use among veterans. Virtual Veterans Socials also provided hosts with a channel to reach potentially isolated veterans who might not otherwise access services while simultaneously offering veterans an opportunity for social connection.

Nearly half of physicians in Canada report high levels of burnout, according to preliminary data from the 2025 National Physician Health Survey (NPHS). The new data show that 46% of physicians report high levels of burnout, down from 2021 (53%) but significantly above the level of 2017 (30%), when the first survey was conducted. The full NPHS 2025 Foundational Report will be released later this year.

Other significant findings include the following:

• 74% of physicians reported experiencing bullying, harassment, microaggressions, or discrimination, a slight but meaningful reduction form 78% in 2021.
• 64% of physicians reported spending significant time on electronic medical records outside regular hours.
• 46% of physicians said that their mental health is worse than it was before the start of the pandemic, down 14% from 2021.
• 60% reported being satisfied or very satisfied with work-life balance, an improvement from 49% in 2021, though slightly below 2017 (62%).
• 37% of physicians plan to reduce their clinical hours in the next 2 years.

Margot Burnell, MD, president of the Canadian Medical Association (CMA), told Medscape Medical News that she was "disappointed" with the results.

"I hoped that the burnout numbers would decrease more than they have," she said. "Physicians are still under extreme stress in trying to provide the care for patients that they wish to give."

Reductions in Hours

The most distressing finding is that > one-third of physicians (37%) plan to reduce their hours within 24 hours -- at a time of growing physician shortages -- said Burnell.

"The one positive (finding) that stands out is that physicians are taking care of their own health and wellness and report that it's helping," she said. About 65% of physicians reported having accessed at least 1 wellness support in the past 5 years, up 11% since 2021.

The NPHS includes responses from about 3300 practicing physicians, medical residents, and fellows who were surveyed from March 14 to April 15.

Among the CMA's top priorities is to reduce the administrative burden because that tops the list of what physicians say would help them with burnout, said Burnell.

"The other area is to provide and encourage team-based care," she continued. "That provides some relief for physicians." It also is important to promote the approaches that seem to be helping, such as wellness support and artificial intelligence (AI), she said. In this survey, 59% of respondents who used AI said that it decreased their time spent on administrative tasks.

Burnout by Specialty

Future analyses will examine burnout by specialty, Burnell said. Burnout is particularly high among emergency physicians, regardless of province, according to previous work by Kerstin de Wit, MD, emergency physician and research director for the Department of Emergency Medicine at Queen's University in Kingston, Ontario, and colleagues.

The NPHS findings are not surprising, she told Medscape Medical News. "We resurveyed all our emergency physicians in January and found similar results, in that the levels of burnout were marginally less than they were in 2022 but still significantly higher than they were in 2020. Still, a majority of (emergency department) physicians qualify as having high burnout levels."

The Pandemic's Role

A telling finding of her team's research is that emergency physician burnout levels are now higher than they were in December 2020, the first year of the COVID pandemic, said De Wit. "I don't think you can say burnout is because of COVID. It's because of the problems in the medical system."

Among those problems in hospitals are a shortage of beds, physicians, and nurses and inadequate numbers of physicians in outpatient clinics "so patients are waiting for years" for conditions to be treated, she added.

"We don't have the resources that we need to maintain the standards that we had even 10, 15 years ago. The whole system is collapsing. Government underfunding is huge. Routinely, our emergency department is 100% full of ward patients, so we don't have a room with a door or a curtain to see patients in. All the emergency patients are seen in corridors or the waiting room in full view of everyone else. We have people with serious medical conditions who are dying in waiting rooms because we can't get them in."

The issues are complex, but the overarching problem is chronic underfunding that results in physicians "feeling overworked and powerless to help patients," said De Wit.

Burnell and de Wit reported having no relevant financial relationships.

Marcia Frellick is an independent health care journalist and a regular contributor to Medscape Medical News.

A version of this article first appeared on Medscape.com.

Nearly half of physicians in Canada report high levels of burnout, according to preliminary data from the 2025 National Physician Health Survey (NPHS). The new data show that 46% of physicians report high levels of burnout, down from 2021 (53%) but significantly above the level of 2017 (30%), when the first survey was conducted. The full NPHS 2025 Foundational Report will be released later this year.

Other significant findings include the following:

• 74% of physicians reported experiencing bullying, harassment, microaggressions, or discrimination, a slight but meaningful reduction form 78% in 2021.
• 64% of physicians reported spending significant time on electronic medical records outside regular hours.
• 46% of physicians said that their mental health is worse than it was before the start of the pandemic, down 14% from 2021.
• 60% reported being satisfied or very satisfied with work-life balance, an improvement from 49% in 2021, though slightly below 2017 (62%).
• 37% of physicians plan to reduce their clinical hours in the next 2 years.

Margot Burnell, MD, president of the Canadian Medical Association (CMA), told Medscape Medical News that she was "disappointed" with the results.

"I hoped that the burnout numbers would decrease more than they have," she said. "Physicians are still under extreme stress in trying to provide the care for patients that they wish to give."

Reductions in Hours

The most distressing finding is that > one-third of physicians (37%) plan to reduce their hours within 24 hours -- at a time of growing physician shortages -- said Burnell.

"The one positive (finding) that stands out is that physicians are taking care of their own health and wellness and report that it's helping," she said. About 65% of physicians reported having accessed at least 1 wellness support in the past 5 years, up 11% since 2021.

The NPHS includes responses from about 3300 practicing physicians, medical residents, and fellows who were surveyed from March 14 to April 15.

Among the CMA's top priorities is to reduce the administrative burden because that tops the list of what physicians say would help them with burnout, said Burnell.

"The other area is to provide and encourage team-based care," she continued. "That provides some relief for physicians." It also is important to promote the approaches that seem to be helping, such as wellness support and artificial intelligence (AI), she said. In this survey, 59% of respondents who used AI said that it decreased their time spent on administrative tasks.

Burnout by Specialty

Future analyses will examine burnout by specialty, Burnell said. Burnout is particularly high among emergency physicians, regardless of province, according to previous work by Kerstin de Wit, MD, emergency physician and research director for the Department of Emergency Medicine at Queen's University in Kingston, Ontario, and colleagues.

The NPHS findings are not surprising, she told Medscape Medical News. "We resurveyed all our emergency physicians in January and found similar results, in that the levels of burnout were marginally less than they were in 2022 but still significantly higher than they were in 2020. Still, a majority of (emergency department) physicians qualify as having high burnout levels."

The Pandemic's Role

A telling finding of her team's research is that emergency physician burnout levels are now higher than they were in December 2020, the first year of the COVID pandemic, said De Wit. "I don't think you can say burnout is because of COVID. It's because of the problems in the medical system."

Among those problems in hospitals are a shortage of beds, physicians, and nurses and inadequate numbers of physicians in outpatient clinics "so patients are waiting for years" for conditions to be treated, she added.

"We don't have the resources that we need to maintain the standards that we had even 10, 15 years ago. The whole system is collapsing. Government underfunding is huge. Routinely, our emergency department is 100% full of ward patients, so we don't have a room with a door or a curtain to see patients in. All the emergency patients are seen in corridors or the waiting room in full view of everyone else. We have people with serious medical conditions who are dying in waiting rooms because we can't get them in."

The issues are complex, but the overarching problem is chronic underfunding that results in physicians "feeling overworked and powerless to help patients," said De Wit.

Burnell and de Wit reported having no relevant financial relationships.

Marcia Frellick is an independent health care journalist and a regular contributor to Medscape Medical News.

A version of this article first appeared on Medscape.com.

Nearly half of physicians in Canada report high levels of burnout, according to preliminary data from the 2025 National Physician Health Survey (NPHS). The new data show that 46% of physicians report high levels of burnout, down from 2021 (53%) but significantly above the level of 2017 (30%), when the first survey was conducted. The full NPHS 2025 Foundational Report will be released later this year.

Other significant findings include the following:

• 74% of physicians reported experiencing bullying, harassment, microaggressions, or discrimination, a slight but meaningful reduction form 78% in 2021.
• 64% of physicians reported spending significant time on electronic medical records outside regular hours.
• 46% of physicians said that their mental health is worse than it was before the start of the pandemic, down 14% from 2021.
• 60% reported being satisfied or very satisfied with work-life balance, an improvement from 49% in 2021, though slightly below 2017 (62%).
• 37% of physicians plan to reduce their clinical hours in the next 2 years.

Margot Burnell, MD, president of the Canadian Medical Association (CMA), told Medscape Medical News that she was "disappointed" with the results.

"I hoped that the burnout numbers would decrease more than they have," she said. "Physicians are still under extreme stress in trying to provide the care for patients that they wish to give."

Reductions in Hours

The most distressing finding is that > one-third of physicians (37%) plan to reduce their hours within 24 hours -- at a time of growing physician shortages -- said Burnell.

"The one positive (finding) that stands out is that physicians are taking care of their own health and wellness and report that it's helping," she said. About 65% of physicians reported having accessed at least 1 wellness support in the past 5 years, up 11% since 2021.

The NPHS includes responses from about 3300 practicing physicians, medical residents, and fellows who were surveyed from March 14 to April 15.

Among the CMA's top priorities is to reduce the administrative burden because that tops the list of what physicians say would help them with burnout, said Burnell.

"The other area is to provide and encourage team-based care," she continued. "That provides some relief for physicians." It also is important to promote the approaches that seem to be helping, such as wellness support and artificial intelligence (AI), she said. In this survey, 59% of respondents who used AI said that it decreased their time spent on administrative tasks.

Burnout by Specialty

Future analyses will examine burnout by specialty, Burnell said. Burnout is particularly high among emergency physicians, regardless of province, according to previous work by Kerstin de Wit, MD, emergency physician and research director for the Department of Emergency Medicine at Queen's University in Kingston, Ontario, and colleagues.

The NPHS findings are not surprising, she told Medscape Medical News. "We resurveyed all our emergency physicians in January and found similar results, in that the levels of burnout were marginally less than they were in 2022 but still significantly higher than they were in 2020. Still, a majority of (emergency department) physicians qualify as having high burnout levels."

The Pandemic's Role

A telling finding of her team's research is that emergency physician burnout levels are now higher than they were in December 2020, the first year of the COVID pandemic, said De Wit. "I don't think you can say burnout is because of COVID. It's because of the problems in the medical system."

Among those problems in hospitals are a shortage of beds, physicians, and nurses and inadequate numbers of physicians in outpatient clinics "so patients are waiting for years" for conditions to be treated, she added.

"We don't have the resources that we need to maintain the standards that we had even 10, 15 years ago. The whole system is collapsing. Government underfunding is huge. Routinely, our emergency department is 100% full of ward patients, so we don't have a room with a door or a curtain to see patients in. All the emergency patients are seen in corridors or the waiting room in full view of everyone else. We have people with serious medical conditions who are dying in waiting rooms because we can't get them in."

The issues are complex, but the overarching problem is chronic underfunding that results in physicians "feeling overworked and powerless to help patients," said De Wit.

Burnell and de Wit reported having no relevant financial relationships.

Marcia Frellick is an independent health care journalist and a regular contributor to Medscape Medical News.

A version of this article first appeared on Medscape.com.