Women's Health

While the incidence of lung cancer is decreasing in men, it continues to rise in women. With more than 19,000 new cases in France each year, lung cancer is now the third most commonly diagnosed cancer among women. This trend is also seen in other European countries but appears to be region-specific because other continents report a decline in incidence among women. Moreover, although overall prognosis remains better in the female population, the trend is worrying: Mortality associated with the disease is increasing in women, unlike in men with lung cancer. A session at the French-Language Pneumology Congress held from January 30 to February 1, 2026, in Lille, France, provided an opportunity to review the situation.

Efficacy and Toxicity

Lung tumors in women have a distinct tumor profile: Women have a higher proportion of adenocarcinomas than men and a higher frequency of somatic mutations (EGFR, BRAF, or HER2), including in nonsmokers. In addition, 65% of lung cancers in women are associated with smoking compared with 87% of those in men.

The role of estrogens is central because they interact directly with tumor growth signaling pathways. Moreover, “sex is the second leading factor of variability in drug pharmacokinetics after weight and accounts for 28% of anticancer drug kinetics,” emphasized Julien Mazières, pulmonologist, Toulouse University Hospital, Toulouse, France. Also involved in this equation are a higher body fat percentage, lower gastric acidity, and, above all, reduced renal and hepatic clearance.

As a result, exposure to drugs — represented by the area under the curve — is often greater in women and translates into not only improved progression-free survival with targeted therapies and chemotherapy but also increased toxicity. Carboplatin and paclitaxel are among the drugs whose kinetics are most affected by clearance. There are differences in clearance of more than 20% for these drugs in women vs men, though dosages are not systematically adjusted except for weight-based dosing. This vulnerability to adverse effects is particularly pronounced with targeted therapies, with more neuropsychiatric and gastrointestinal disorders. Data on the efficacy of immunotherapy in lung cancer by sex are contradictory. However, endocrine-related adverse effects and pneumonitis are more frequent in women, especially before menopause.

Women remain underrepresented in clinical trials, and sex-specific analyses of results are too rarely performed, which limits understanding of mechanisms and prevents tailoring management recommendations according to sex.

Impaired Quality of Life

Lung cancer most severely impairs physical functioning in women. “In the absence of sex-stratified studies, psycho-oncologists’ experience suggests that women have more cognitive disorders, anxiety, and depression associated with this disease. Its impact on quality of life is major, with deterioration of social relationships and reduced treatment adherence,” summarized Céline Mascaux, MD, PhD, pulmonologist, Strasbourg University Hospital, Strasbourg, France. Women also face social and family pressure — a mental burden that pushes them to “hold on” for their loved ones. Regarding sexual health, women with lung cancer who are sexually active often report dissatisfaction with the quality of their sexual relations because of fatigue, lack of energy, sadness, and shortness of breath, not to mention treatment-related sexual dysfunction. These problems are often not given sufficient attention by physicians.

Finally, fertility requires greater attention from the medical community: According to the VICAN study conducted by France’s National Health Insurance Fund, a discussion about fertility preservation did not take place at the time of cancer diagnosis for 60% of men and 67% of women of childbearing age. “In lung cancer specifically, the desire for children nevertheless exists in nearly 40% of patients of childbearing age,” regretted Jacques Cadranel, pulmonologist, Tenon Hospital, Paris, France. This desire does not appear to have influenced therapeutic strategy, and fertility preservation was ultimately proposed in only a third of cases and was carried out in only 3% of women compared with21% of men.

This story has been translated from Univadis France, part of the Medscape Professional Network.

A version of this story first appeared on Medscape.com

While the incidence of lung cancer is decreasing in men, it continues to rise in women. With more than 19,000 new cases in France each year, lung cancer is now the third most commonly diagnosed cancer among women. This trend is also seen in other European countries but appears to be region-specific because other continents report a decline in incidence among women. Moreover, although overall prognosis remains better in the female population, the trend is worrying: Mortality associated with the disease is increasing in women, unlike in men with lung cancer. A session at the French-Language Pneumology Congress held from January 30 to February 1, 2026, in Lille, France, provided an opportunity to review the situation.

Efficacy and Toxicity

Lung tumors in women have a distinct tumor profile: Women have a higher proportion of adenocarcinomas than men and a higher frequency of somatic mutations (EGFR, BRAF, or HER2), including in nonsmokers. In addition, 65% of lung cancers in women are associated with smoking compared with 87% of those in men.

The role of estrogens is central because they interact directly with tumor growth signaling pathways. Moreover, “sex is the second leading factor of variability in drug pharmacokinetics after weight and accounts for 28% of anticancer drug kinetics,” emphasized Julien Mazières, pulmonologist, Toulouse University Hospital, Toulouse, France. Also involved in this equation are a higher body fat percentage, lower gastric acidity, and, above all, reduced renal and hepatic clearance.

As a result, exposure to drugs — represented by the area under the curve — is often greater in women and translates into not only improved progression-free survival with targeted therapies and chemotherapy but also increased toxicity. Carboplatin and paclitaxel are among the drugs whose kinetics are most affected by clearance. There are differences in clearance of more than 20% for these drugs in women vs men, though dosages are not systematically adjusted except for weight-based dosing. This vulnerability to adverse effects is particularly pronounced with targeted therapies, with more neuropsychiatric and gastrointestinal disorders. Data on the efficacy of immunotherapy in lung cancer by sex are contradictory. However, endocrine-related adverse effects and pneumonitis are more frequent in women, especially before menopause.

Women remain underrepresented in clinical trials, and sex-specific analyses of results are too rarely performed, which limits understanding of mechanisms and prevents tailoring management recommendations according to sex.

Impaired Quality of Life

Lung cancer most severely impairs physical functioning in women. “In the absence of sex-stratified studies, psycho-oncologists’ experience suggests that women have more cognitive disorders, anxiety, and depression associated with this disease. Its impact on quality of life is major, with deterioration of social relationships and reduced treatment adherence,” summarized Céline Mascaux, MD, PhD, pulmonologist, Strasbourg University Hospital, Strasbourg, France. Women also face social and family pressure — a mental burden that pushes them to “hold on” for their loved ones. Regarding sexual health, women with lung cancer who are sexually active often report dissatisfaction with the quality of their sexual relations because of fatigue, lack of energy, sadness, and shortness of breath, not to mention treatment-related sexual dysfunction. These problems are often not given sufficient attention by physicians.

Finally, fertility requires greater attention from the medical community: According to the VICAN study conducted by France’s National Health Insurance Fund, a discussion about fertility preservation did not take place at the time of cancer diagnosis for 60% of men and 67% of women of childbearing age. “In lung cancer specifically, the desire for children nevertheless exists in nearly 40% of patients of childbearing age,” regretted Jacques Cadranel, pulmonologist, Tenon Hospital, Paris, France. This desire does not appear to have influenced therapeutic strategy, and fertility preservation was ultimately proposed in only a third of cases and was carried out in only 3% of women compared with21% of men.

This story has been translated from Univadis France, part of the Medscape Professional Network.

A version of this story first appeared on Medscape.com

While the incidence of lung cancer is decreasing in men, it continues to rise in women. With more than 19,000 new cases in France each year, lung cancer is now the third most commonly diagnosed cancer among women. This trend is also seen in other European countries but appears to be region-specific because other continents report a decline in incidence among women. Moreover, although overall prognosis remains better in the female population, the trend is worrying: Mortality associated with the disease is increasing in women, unlike in men with lung cancer. A session at the French-Language Pneumology Congress held from January 30 to February 1, 2026, in Lille, France, provided an opportunity to review the situation.

Efficacy and Toxicity

Lung tumors in women have a distinct tumor profile: Women have a higher proportion of adenocarcinomas than men and a higher frequency of somatic mutations (EGFR, BRAF, or HER2), including in nonsmokers. In addition, 65% of lung cancers in women are associated with smoking compared with 87% of those in men.

The role of estrogens is central because they interact directly with tumor growth signaling pathways. Moreover, “sex is the second leading factor of variability in drug pharmacokinetics after weight and accounts for 28% of anticancer drug kinetics,” emphasized Julien Mazières, pulmonologist, Toulouse University Hospital, Toulouse, France. Also involved in this equation are a higher body fat percentage, lower gastric acidity, and, above all, reduced renal and hepatic clearance.

As a result, exposure to drugs — represented by the area under the curve — is often greater in women and translates into not only improved progression-free survival with targeted therapies and chemotherapy but also increased toxicity. Carboplatin and paclitaxel are among the drugs whose kinetics are most affected by clearance. There are differences in clearance of more than 20% for these drugs in women vs men, though dosages are not systematically adjusted except for weight-based dosing. This vulnerability to adverse effects is particularly pronounced with targeted therapies, with more neuropsychiatric and gastrointestinal disorders. Data on the efficacy of immunotherapy in lung cancer by sex are contradictory. However, endocrine-related adverse effects and pneumonitis are more frequent in women, especially before menopause.

Women remain underrepresented in clinical trials, and sex-specific analyses of results are too rarely performed, which limits understanding of mechanisms and prevents tailoring management recommendations according to sex.

Impaired Quality of Life

Lung cancer most severely impairs physical functioning in women. “In the absence of sex-stratified studies, psycho-oncologists’ experience suggests that women have more cognitive disorders, anxiety, and depression associated with this disease. Its impact on quality of life is major, with deterioration of social relationships and reduced treatment adherence,” summarized Céline Mascaux, MD, PhD, pulmonologist, Strasbourg University Hospital, Strasbourg, France. Women also face social and family pressure — a mental burden that pushes them to “hold on” for their loved ones. Regarding sexual health, women with lung cancer who are sexually active often report dissatisfaction with the quality of their sexual relations because of fatigue, lack of energy, sadness, and shortness of breath, not to mention treatment-related sexual dysfunction. These problems are often not given sufficient attention by physicians.

Finally, fertility requires greater attention from the medical community: According to the VICAN study conducted by France’s National Health Insurance Fund, a discussion about fertility preservation did not take place at the time of cancer diagnosis for 60% of men and 67% of women of childbearing age. “In lung cancer specifically, the desire for children nevertheless exists in nearly 40% of patients of childbearing age,” regretted Jacques Cadranel, pulmonologist, Tenon Hospital, Paris, France. This desire does not appear to have influenced therapeutic strategy, and fertility preservation was ultimately proposed in only a third of cases and was carried out in only 3% of women compared with21% of men.

This story has been translated from Univadis France, part of the Medscape Professional Network.

A version of this story first appeared on Medscape.com

Background

Rural women veterans often confront unique healthcare barriers—geographic isolation, gender-related stigma, and limited provider cultural sensitivity that undermine trust and engagement. In response, we co-designed an interprofessional communication curriculum to promote relational, patient-centered care grounded in psychological need support.

Innovation

Anchored in Self Determination Theory (SDT), this curriculum equips nurses and social workers with need-supportive communication strategies that nurture autonomy, competence, and relatedness, integrating two transformative learning methods for enhancing respectful and inclusive listening:

• Cultural humility reflections for veteran-centered care—personal narratives, storytelling, and power-awareness discussions to build lifelong reflective practices.
• Medical improv simulations—adaptive improvisational role plays for healthcare environments fostering presence, adaptability, empathy, trust-building, and real-time responsiveness.

Delivered via a multiday health professions learning lab, the training combines asynchronous workshops with in-person facilitated interactions. Core modules cover SDT foundations, need supportive dialogue, veteran-centered cultural humility, and shared decision-making practices that uplift rural women veterans’ voices. Using Kirkpatrick’s Four Level Model, we assess impact at multiple tiers:

1. Reaction: Participant satisfaction and perceived training relevance.
2. Learning: Pre/post assessments track SDT knowledge and communication skills gains.
3. Behavior: Observe simulations and self-reported changes in communication practices.
4. Results: Qualitative satisfaction metrics and care engagement trends among rural women veterans.

Results

A pilot cohort (N = 20) across two rural sites is pending implementation. pre/post surveys will assess any improved confidence in applying need supportive communication and the most effective component in building empathetic presence. Feedback measures will also indicate the significance of combined uses of medical improv and cultural humility on deepened relational capacity and trust.

Discussion

This program operationalizes SDT within healthcare communications, integrating cultural humility and improvisation learning modalities to enhance care quality for rural women veterans, ultimately strengthening provider-patient connections. Using health professions learning lab environments can foster sustained behavioral impacts. Future iterations will expand to additional rural VA sites, co-designing with the voices of women veterans through focus groups.

Background

Rural women veterans often confront unique healthcare barriers—geographic isolation, gender-related stigma, and limited provider cultural sensitivity that undermine trust and engagement. In response, we co-designed an interprofessional communication curriculum to promote relational, patient-centered care grounded in psychological need support.

Innovation

Anchored in Self Determination Theory (SDT), this curriculum equips nurses and social workers with need-supportive communication strategies that nurture autonomy, competence, and relatedness, integrating two transformative learning methods for enhancing respectful and inclusive listening:

• Cultural humility reflections for veteran-centered care—personal narratives, storytelling, and power-awareness discussions to build lifelong reflective practices.
• Medical improv simulations—adaptive improvisational role plays for healthcare environments fostering presence, adaptability, empathy, trust-building, and real-time responsiveness.

Delivered via a multiday health professions learning lab, the training combines asynchronous workshops with in-person facilitated interactions. Core modules cover SDT foundations, need supportive dialogue, veteran-centered cultural humility, and shared decision-making practices that uplift rural women veterans’ voices. Using Kirkpatrick’s Four Level Model, we assess impact at multiple tiers:

1. Reaction: Participant satisfaction and perceived training relevance.
2. Learning: Pre/post assessments track SDT knowledge and communication skills gains.
3. Behavior: Observe simulations and self-reported changes in communication practices.
4. Results: Qualitative satisfaction metrics and care engagement trends among rural women veterans.

Results

A pilot cohort (N = 20) across two rural sites is pending implementation. pre/post surveys will assess any improved confidence in applying need supportive communication and the most effective component in building empathetic presence. Feedback measures will also indicate the significance of combined uses of medical improv and cultural humility on deepened relational capacity and trust.

Discussion

This program operationalizes SDT within healthcare communications, integrating cultural humility and improvisation learning modalities to enhance care quality for rural women veterans, ultimately strengthening provider-patient connections. Using health professions learning lab environments can foster sustained behavioral impacts. Future iterations will expand to additional rural VA sites, co-designing with the voices of women veterans through focus groups.

Background

Rural women veterans often confront unique healthcare barriers—geographic isolation, gender-related stigma, and limited provider cultural sensitivity that undermine trust and engagement. In response, we co-designed an interprofessional communication curriculum to promote relational, patient-centered care grounded in psychological need support.

Innovation

Anchored in Self Determination Theory (SDT), this curriculum equips nurses and social workers with need-supportive communication strategies that nurture autonomy, competence, and relatedness, integrating two transformative learning methods for enhancing respectful and inclusive listening:

• Cultural humility reflections for veteran-centered care—personal narratives, storytelling, and power-awareness discussions to build lifelong reflective practices.
• Medical improv simulations—adaptive improvisational role plays for healthcare environments fostering presence, adaptability, empathy, trust-building, and real-time responsiveness.

Delivered via a multiday health professions learning lab, the training combines asynchronous workshops with in-person facilitated interactions. Core modules cover SDT foundations, need supportive dialogue, veteran-centered cultural humility, and shared decision-making practices that uplift rural women veterans’ voices. Using Kirkpatrick’s Four Level Model, we assess impact at multiple tiers:

1. Reaction: Participant satisfaction and perceived training relevance.
2. Learning: Pre/post assessments track SDT knowledge and communication skills gains.
3. Behavior: Observe simulations and self-reported changes in communication practices.
4. Results: Qualitative satisfaction metrics and care engagement trends among rural women veterans.

Results

A pilot cohort (N = 20) across two rural sites is pending implementation. pre/post surveys will assess any improved confidence in applying need supportive communication and the most effective component in building empathetic presence. Feedback measures will also indicate the significance of combined uses of medical improv and cultural humility on deepened relational capacity and trust.

Discussion

This program operationalizes SDT within healthcare communications, integrating cultural humility and improvisation learning modalities to enhance care quality for rural women veterans, ultimately strengthening provider-patient connections. Using health professions learning lab environments can foster sustained behavioral impacts. Future iterations will expand to additional rural VA sites, co-designing with the voices of women veterans through focus groups.

The Medicines and Healthcare products Regulatory Agency (MHRA) has approved tisotumab vedotin (Genmab AS) for adults with recurrent or metastatic cervical cancer.

The decision, made via the International Recognition Procedure, applies to patients whose disease has progressed after prior systemic therapy. It provides a new treatment option for a high-risk group with limited alternatives.

How the Treatment Works

Tisotumab vedotin is an antibody-drug conjugate that combines a tissue factor-directed human monoclonal antibody with monomethyl auristatin E, a microtubule-disrupting agent. The therapy targets tissue factor, which is overexpressed in a several solid tumours, including recurrent cervical cancer.

It is administered as a 30-minute intravenous infusion once every 3 weeks.

What Trials Showed

The approval is based on evidence from multiple clinical studies demonstrating tisotumab vedotin's efficacy in previously treated patients.

In the phase 2 innovaTV 204 study, 102 patients were enrolled and 101 received at least 1 dose of tisotumab vedotin. The confirmed objective response rate was 24%, including seven complete responses and 17 partial responses, demonstrating clinically meaningful activity in a heavily pretreated population.

Further evidence came from the phase 3 innovaTV-301 trial, which randomly assigned 502 patients to receive either tisotumab vedotin or investigator's-choice chemotherapy.

Median overall survival was 11.5 months with the new therapy compared with 9.5 months in the chemotherapy arm, translating to roughly a 30% reduction in the risk for death. The confirmed objective response rate was also significantly higher with tisotumab vedotin—17.8% vs 5.2%—underscoring its advantage over standard treatment options.

Safety and Tolerability

Ocular toxicity and peripheral neuropathy were the most notable adverse reactions.

Common treatment-related events in the phase 2 study included alopecia (38%), epistaxis (30%), nausea, conjunctivitis (26%), and fatigue (26%).

Grade 3 or higher treatment-related adverse events occurred in about 28% of patients. Clinicians should be alert to conjunctivitis and keratitis as well as sensory neuropathic symptoms (numbness, tingling, or a burning sensation in the hands and feet).

Julian Beach, interim executive director of healthcare quality and access at the MHRA, said that patient safety is the agency's "top priority." "We will continue to monitor its safety closely as it becomes more widely used," he added.

The Summary of Product Characteristics and Patient Information Leaflets will be published on the MHRA website within 7 days of approval.

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

The Medicines and Healthcare products Regulatory Agency (MHRA) has approved tisotumab vedotin (Genmab AS) for adults with recurrent or metastatic cervical cancer.

The decision, made via the International Recognition Procedure, applies to patients whose disease has progressed after prior systemic therapy. It provides a new treatment option for a high-risk group with limited alternatives.

How the Treatment Works

Tisotumab vedotin is an antibody-drug conjugate that combines a tissue factor-directed human monoclonal antibody with monomethyl auristatin E, a microtubule-disrupting agent. The therapy targets tissue factor, which is overexpressed in a several solid tumours, including recurrent cervical cancer.

It is administered as a 30-minute intravenous infusion once every 3 weeks.

What Trials Showed

The approval is based on evidence from multiple clinical studies demonstrating tisotumab vedotin's efficacy in previously treated patients.

In the phase 2 innovaTV 204 study, 102 patients were enrolled and 101 received at least 1 dose of tisotumab vedotin. The confirmed objective response rate was 24%, including seven complete responses and 17 partial responses, demonstrating clinically meaningful activity in a heavily pretreated population.

Further evidence came from the phase 3 innovaTV-301 trial, which randomly assigned 502 patients to receive either tisotumab vedotin or investigator's-choice chemotherapy.

Median overall survival was 11.5 months with the new therapy compared with 9.5 months in the chemotherapy arm, translating to roughly a 30% reduction in the risk for death. The confirmed objective response rate was also significantly higher with tisotumab vedotin—17.8% vs 5.2%—underscoring its advantage over standard treatment options.

Safety and Tolerability

Ocular toxicity and peripheral neuropathy were the most notable adverse reactions.

Common treatment-related events in the phase 2 study included alopecia (38%), epistaxis (30%), nausea, conjunctivitis (26%), and fatigue (26%).

Grade 3 or higher treatment-related adverse events occurred in about 28% of patients. Clinicians should be alert to conjunctivitis and keratitis as well as sensory neuropathic symptoms (numbness, tingling, or a burning sensation in the hands and feet).

Julian Beach, interim executive director of healthcare quality and access at the MHRA, said that patient safety is the agency's "top priority." "We will continue to monitor its safety closely as it becomes more widely used," he added.

The Summary of Product Characteristics and Patient Information Leaflets will be published on the MHRA website within 7 days of approval.

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

The Medicines and Healthcare products Regulatory Agency (MHRA) has approved tisotumab vedotin (Genmab AS) for adults with recurrent or metastatic cervical cancer.

The decision, made via the International Recognition Procedure, applies to patients whose disease has progressed after prior systemic therapy. It provides a new treatment option for a high-risk group with limited alternatives.

How the Treatment Works

Tisotumab vedotin is an antibody-drug conjugate that combines a tissue factor-directed human monoclonal antibody with monomethyl auristatin E, a microtubule-disrupting agent. The therapy targets tissue factor, which is overexpressed in a several solid tumours, including recurrent cervical cancer.

It is administered as a 30-minute intravenous infusion once every 3 weeks.

What Trials Showed

The approval is based on evidence from multiple clinical studies demonstrating tisotumab vedotin's efficacy in previously treated patients.

In the phase 2 innovaTV 204 study, 102 patients were enrolled and 101 received at least 1 dose of tisotumab vedotin. The confirmed objective response rate was 24%, including seven complete responses and 17 partial responses, demonstrating clinically meaningful activity in a heavily pretreated population.

Further evidence came from the phase 3 innovaTV-301 trial, which randomly assigned 502 patients to receive either tisotumab vedotin or investigator's-choice chemotherapy.

Median overall survival was 11.5 months with the new therapy compared with 9.5 months in the chemotherapy arm, translating to roughly a 30% reduction in the risk for death. The confirmed objective response rate was also significantly higher with tisotumab vedotin—17.8% vs 5.2%—underscoring its advantage over standard treatment options.

Safety and Tolerability

Ocular toxicity and peripheral neuropathy were the most notable adverse reactions.

Common treatment-related events in the phase 2 study included alopecia (38%), epistaxis (30%), nausea, conjunctivitis (26%), and fatigue (26%).

Grade 3 or higher treatment-related adverse events occurred in about 28% of patients. Clinicians should be alert to conjunctivitis and keratitis as well as sensory neuropathic symptoms (numbness, tingling, or a burning sensation in the hands and feet).

Julian Beach, interim executive director of healthcare quality and access at the MHRA, said that patient safety is the agency's "top priority." "We will continue to monitor its safety closely as it becomes more widely used," he added.

The Summary of Product Characteristics and Patient Information Leaflets will be published on the MHRA website within 7 days of approval.

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

The more than 2 million women US veterans are the fastest-growing military population. While research into women veterans has traditionally lagged, more recently studies have begun to focus on their needs impacts of combat and service on women. These studies have found that women veterans preferred tailored solutions focused on women veterans.

A November 2025 study is one of the first to examine the impact of combat on women veterans. It found that those in combat roles had higher levels of depression, posttraumatic stress disorder (PTSD), dissociation, and overall poorer health compared with civilians and noncombat women military personnel. Previous research had found that women veterans had higher rates of lifetime and past-year PTSD (13.4%) compared with female civilians (8.0%), male veterans (7.7%), and male civilians (3.4%). A 2020 US Department of Veterans (VA) study of 4,928,638 men and 448,455 women similarly found that women had nearly twice the rates of depression and anxiety compared with men.

For many veterans, mental health issues may develop or be exacerbated in their return to civilian life. That transition can be especially confusing and isolating for women veterans, according to a 2024 study: “They neither fit in the military due to gendered relations centered on masculinity, or civilian life where they are largely misunderstood as ‘veterans.’ This ‘no woman’s land’ is poorly understood.” Few programs for transitioning veterans have been found effective for women veterans because they’ve been developed for a largely male veteran population. That includes mental health support programs.

Some women may prefer women-only groups, and even that choice may be dependent on their background, service history, socioeconomic level, and other factors. They may feel more comfortable in women-only groups if they’ve experienced MST. Others who have served in combat may choose mixed-gender programs. One study found that some women benefited from being in a mixed-gender group because it enabled them to work on difficulties with men in a safe environment. Other research has found that women veterans with substance use disorders are reluctant to seek help alongside men in the same facilities. 

Accessing care may be especially challenging for rural women veterans. However, separate facilities and women-only groups are not always available, particularly in rural areas where there may be very few women veterans. And even if they are available, rural women are often up against barriers that urban women do not face, such as having to travel long distances to get care. Clinicians also may be hard to find in rural areas. Some participants in a 2025 study were hampered not only by a lack of female practitioners, but practitioners who were well trained to understand and treat the unique needs of female veterans: “[It’s] incredibly difficult to find a mental health practitioner that understands a veteran’s unique experience as a woman,” a participant said.

The more than 2 million women US veterans are the fastest-growing military population. While research into women veterans has traditionally lagged, more recently studies have begun to focus on their needs impacts of combat and service on women. These studies have found that women veterans preferred tailored solutions focused on women veterans.

A November 2025 study is one of the first to examine the impact of combat on women veterans. It found that those in combat roles had higher levels of depression, posttraumatic stress disorder (PTSD), dissociation, and overall poorer health compared with civilians and noncombat women military personnel. Previous research had found that women veterans had higher rates of lifetime and past-year PTSD (13.4%) compared with female civilians (8.0%), male veterans (7.7%), and male civilians (3.4%). A 2020 US Department of Veterans (VA) study of 4,928,638 men and 448,455 women similarly found that women had nearly twice the rates of depression and anxiety compared with men.

For many veterans, mental health issues may develop or be exacerbated in their return to civilian life. That transition can be especially confusing and isolating for women veterans, according to a 2024 study: “They neither fit in the military due to gendered relations centered on masculinity, or civilian life where they are largely misunderstood as ‘veterans.’ This ‘no woman’s land’ is poorly understood.” Few programs for transitioning veterans have been found effective for women veterans because they’ve been developed for a largely male veteran population. That includes mental health support programs.

Some women may prefer women-only groups, and even that choice may be dependent on their background, service history, socioeconomic level, and other factors. They may feel more comfortable in women-only groups if they’ve experienced MST. Others who have served in combat may choose mixed-gender programs. One study found that some women benefited from being in a mixed-gender group because it enabled them to work on difficulties with men in a safe environment. Other research has found that women veterans with substance use disorders are reluctant to seek help alongside men in the same facilities. 

Accessing care may be especially challenging for rural women veterans. However, separate facilities and women-only groups are not always available, particularly in rural areas where there may be very few women veterans. And even if they are available, rural women are often up against barriers that urban women do not face, such as having to travel long distances to get care. Clinicians also may be hard to find in rural areas. Some participants in a 2025 study were hampered not only by a lack of female practitioners, but practitioners who were well trained to understand and treat the unique needs of female veterans: “[It’s] incredibly difficult to find a mental health practitioner that understands a veteran’s unique experience as a woman,” a participant said.

The more than 2 million women US veterans are the fastest-growing military population. While research into women veterans has traditionally lagged, more recently studies have begun to focus on their needs impacts of combat and service on women. These studies have found that women veterans preferred tailored solutions focused on women veterans.

A November 2025 study is one of the first to examine the impact of combat on women veterans. It found that those in combat roles had higher levels of depression, posttraumatic stress disorder (PTSD), dissociation, and overall poorer health compared with civilians and noncombat women military personnel. Previous research had found that women veterans had higher rates of lifetime and past-year PTSD (13.4%) compared with female civilians (8.0%), male veterans (7.7%), and male civilians (3.4%). A 2020 US Department of Veterans (VA) study of 4,928,638 men and 448,455 women similarly found that women had nearly twice the rates of depression and anxiety compared with men.

For many veterans, mental health issues may develop or be exacerbated in their return to civilian life. That transition can be especially confusing and isolating for women veterans, according to a 2024 study: “They neither fit in the military due to gendered relations centered on masculinity, or civilian life where they are largely misunderstood as ‘veterans.’ This ‘no woman’s land’ is poorly understood.” Few programs for transitioning veterans have been found effective for women veterans because they’ve been developed for a largely male veteran population. That includes mental health support programs.

Some women may prefer women-only groups, and even that choice may be dependent on their background, service history, socioeconomic level, and other factors. They may feel more comfortable in women-only groups if they’ve experienced MST. Others who have served in combat may choose mixed-gender programs. One study found that some women benefited from being in a mixed-gender group because it enabled them to work on difficulties with men in a safe environment. Other research has found that women veterans with substance use disorders are reluctant to seek help alongside men in the same facilities. 

Accessing care may be especially challenging for rural women veterans. However, separate facilities and women-only groups are not always available, particularly in rural areas where there may be very few women veterans. And even if they are available, rural women are often up against barriers that urban women do not face, such as having to travel long distances to get care. Clinicians also may be hard to find in rural areas. Some participants in a 2025 study were hampered not only by a lack of female practitioners, but practitioners who were well trained to understand and treat the unique needs of female veterans: “[It’s] incredibly difficult to find a mental health practitioner that understands a veteran’s unique experience as a woman,” a participant said.

TOPLINE: Psychiatric disorders affect 37.8% of veteran vs 37.3% of nonveteran in a study of > 42,000 women aged ≥ 65 years. Most differences between veterans and nonveterans were statistically insignificant after removing confounders.

METHODOLOGY: 

• Researchers analyzed 42,031 Women's Health Initiative (WHI) participants aged > 65 years at enrollment (1993-1998), including 1,512 veterans and 40,519 non-veterans, through linked WHI-Medicare databases with approximately 15 years of follow-up.

• Analysis included multivariable logistic and Cox regression models to evaluate characteristics associated with prevalent and incident psychiatric disorders, respectively.

• Participants were followed from WHI enrollment until first psychiatric diagnosis, with censoring at death, end of follow-up, or December 31, 2013.

• Investigators examined relationships between individual-level and neighborhood-level socioeconomic status indicators with psychiatric disorders before and after stratification by veteran status.

TAKEAWAY:

• The overall prevalence of psychiatric disorders was 37.3%, with an incidence rate of 25.5 per 1,000 person-years, showing no significant differences between veterans and non-veterans (odds ratio [OR], 0.95; 95% confidence interval [CI], 0.85-0.06).

• There was a higher prevalence of psychiatric disorders for women veterans with technical, sales, or administrative occupations (adjusted OR [aOR], 1.72; 95 % CI, 1.02, 2.89) and those with “other” occupations (aOR, 2.09; 95 % CI, 1.13, 3.88) when compared with women veterans with managerial or professional occupations.

• Mood and anxiety disorders emerged as the leading types of psychiatric conditions among both veteran and nonveteran women.

IN PRACTICE: "Although interaction effects by veteran status were nonsignificant,” the authors of the study explained, “lower education, household income, and neighborhood socioeconomic status were associated with higher frequencies of psychiatric disorders only among women non-veterans.”

SOURCE: The study was led by Jack Tsai and the US Department of Veterans Affairs National Center on Homelessness Among Veterans in Washington, DC. It was published online in Journal of Affective Disorders.

LIMITATIONS: The study faced several limitations including potential selection and survival biases, as findings correspond only to Women's Health Initiative participants who survived until age 65 or later. Information bias likely occurred due to self-reported measures and sole reliance on International Classification of Disease, 9th revision, Clinical Modification diagnostic codes from Medicare claims. Additionally, socioeconomic status indicators assessed at enrollment may not reflect early life or midlife exposures that could influence psychiatric diagnoses.

 DISCLOSURES: The Women’s Health Initiative program received funding from the National Heart, Lung, and Blood Institute, National Institutes of Health, U.S. Department of Health and Human Services through grants 75N92021D00001, 75N92021D00002, 75N92021D00003, 75N92021D00004, and 75N92021D00005.

This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication.

TOPLINE: Psychiatric disorders affect 37.8% of veteran vs 37.3% of nonveteran in a study of > 42,000 women aged ≥ 65 years. Most differences between veterans and nonveterans were statistically insignificant after removing confounders.

METHODOLOGY: 

• Researchers analyzed 42,031 Women's Health Initiative (WHI) participants aged > 65 years at enrollment (1993-1998), including 1,512 veterans and 40,519 non-veterans, through linked WHI-Medicare databases with approximately 15 years of follow-up.

• Analysis included multivariable logistic and Cox regression models to evaluate characteristics associated with prevalent and incident psychiatric disorders, respectively.

• Participants were followed from WHI enrollment until first psychiatric diagnosis, with censoring at death, end of follow-up, or December 31, 2013.

• Investigators examined relationships between individual-level and neighborhood-level socioeconomic status indicators with psychiatric disorders before and after stratification by veteran status.

TAKEAWAY:

• The overall prevalence of psychiatric disorders was 37.3%, with an incidence rate of 25.5 per 1,000 person-years, showing no significant differences between veterans and non-veterans (odds ratio [OR], 0.95; 95% confidence interval [CI], 0.85-0.06).

• There was a higher prevalence of psychiatric disorders for women veterans with technical, sales, or administrative occupations (adjusted OR [aOR], 1.72; 95 % CI, 1.02, 2.89) and those with “other” occupations (aOR, 2.09; 95 % CI, 1.13, 3.88) when compared with women veterans with managerial or professional occupations.

• Mood and anxiety disorders emerged as the leading types of psychiatric conditions among both veteran and nonveteran women.

IN PRACTICE: "Although interaction effects by veteran status were nonsignificant,” the authors of the study explained, “lower education, household income, and neighborhood socioeconomic status were associated with higher frequencies of psychiatric disorders only among women non-veterans.”

SOURCE: The study was led by Jack Tsai and the US Department of Veterans Affairs National Center on Homelessness Among Veterans in Washington, DC. It was published online in Journal of Affective Disorders.

LIMITATIONS: The study faced several limitations including potential selection and survival biases, as findings correspond only to Women's Health Initiative participants who survived until age 65 or later. Information bias likely occurred due to self-reported measures and sole reliance on International Classification of Disease, 9th revision, Clinical Modification diagnostic codes from Medicare claims. Additionally, socioeconomic status indicators assessed at enrollment may not reflect early life or midlife exposures that could influence psychiatric diagnoses.

 DISCLOSURES: The Women’s Health Initiative program received funding from the National Heart, Lung, and Blood Institute, National Institutes of Health, U.S. Department of Health and Human Services through grants 75N92021D00001, 75N92021D00002, 75N92021D00003, 75N92021D00004, and 75N92021D00005.

This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication.

TOPLINE: Psychiatric disorders affect 37.8% of veteran vs 37.3% of nonveteran in a study of > 42,000 women aged ≥ 65 years. Most differences between veterans and nonveterans were statistically insignificant after removing confounders.

METHODOLOGY: 

• Researchers analyzed 42,031 Women's Health Initiative (WHI) participants aged > 65 years at enrollment (1993-1998), including 1,512 veterans and 40,519 non-veterans, through linked WHI-Medicare databases with approximately 15 years of follow-up.

• Analysis included multivariable logistic and Cox regression models to evaluate characteristics associated with prevalent and incident psychiatric disorders, respectively.

• Participants were followed from WHI enrollment until first psychiatric diagnosis, with censoring at death, end of follow-up, or December 31, 2013.

• Investigators examined relationships between individual-level and neighborhood-level socioeconomic status indicators with psychiatric disorders before and after stratification by veteran status.

TAKEAWAY:

• The overall prevalence of psychiatric disorders was 37.3%, with an incidence rate of 25.5 per 1,000 person-years, showing no significant differences between veterans and non-veterans (odds ratio [OR], 0.95; 95% confidence interval [CI], 0.85-0.06).

• There was a higher prevalence of psychiatric disorders for women veterans with technical, sales, or administrative occupations (adjusted OR [aOR], 1.72; 95 % CI, 1.02, 2.89) and those with “other” occupations (aOR, 2.09; 95 % CI, 1.13, 3.88) when compared with women veterans with managerial or professional occupations.

• Mood and anxiety disorders emerged as the leading types of psychiatric conditions among both veteran and nonveteran women.

IN PRACTICE: "Although interaction effects by veteran status were nonsignificant,” the authors of the study explained, “lower education, household income, and neighborhood socioeconomic status were associated with higher frequencies of psychiatric disorders only among women non-veterans.”

SOURCE: The study was led by Jack Tsai and the US Department of Veterans Affairs National Center on Homelessness Among Veterans in Washington, DC. It was published online in Journal of Affective Disorders.

LIMITATIONS: The study faced several limitations including potential selection and survival biases, as findings correspond only to Women's Health Initiative participants who survived until age 65 or later. Information bias likely occurred due to self-reported measures and sole reliance on International Classification of Disease, 9th revision, Clinical Modification diagnostic codes from Medicare claims. Additionally, socioeconomic status indicators assessed at enrollment may not reflect early life or midlife exposures that could influence psychiatric diagnoses.

 DISCLOSURES: The Women’s Health Initiative program received funding from the National Heart, Lung, and Blood Institute, National Institutes of Health, U.S. Department of Health and Human Services through grants 75N92021D00001, 75N92021D00002, 75N92021D00003, 75N92021D00004, and 75N92021D00005.

This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication.

Cardiovascular disease (CVD) is the leading cause of death among women in the United States.¹ Most CVD is due to the buildup of plaque (ie, cholesterol, proteins, calcium, and inflammatory cells) in artery walls.² The plaque may lead to atherosclerotic cardiovascular disease (ASCVD), which includes coronary heart disease, cerebrovascular disease, peripheral artery disease, and aortic atherosclerotic disease.^2,3 Control and reduction of ASCVD risk factors, including high cholesterol levels, elevated blood pressure, insulin resistance, smoking, and a sedentary lifestyle, can contribute to a reduction in ASCVD morbidity and mortality.² People with type 2 diabetes mellitus (T2DM) have an increased prevalence of lipid abnormalities, contributing to their high risk of ASCVD.^4,5

The prescribing of statins (3-hydroxy-3-methyl-glutaryl-coenzmye A reductase inhibitors) is the cornerstone of lipid-lowering therapy and cardiovascular risk reduction for primary and secondary prevention of ASCVD.⁶ The American Diabetes Association (ADA) and American College of Cardiology/American Heart Association (ACC/AHA) recommend moderate- to high-intensity statins for primary prevention in patients with T2DM and high-intensity statins for secondary prevention in those with or without diabetes when not contraindicated.^4,5,7 Despite eligibility according to guideline recommendations, research predominantly shows that women are less likely to receive statin therapy; however, this trend is improving. ^[6,8-11] To explain the sex differences in statin use, Nanna et al found that there is a combination of women being offered statin therapy less frequently, declining therapy more frequently, and discontinuing treatment more frequently.¹¹ One possibility for discontinuing treatment could be statin-associated muscle symptoms (SAMS), which occur in about 10% of patients.¹² The incidence of adverse effects (AEs) may be related to the way statins are metabolized.

Pharmacogenomic testing is free for veterans through the US Department of Veterans Affairs (VA) PHASER program, which offers information and recommendations for a panel of 11 gene variants. The panel includes genes related to common medication classes such as anticoagulants, antiplatelets, proton pump inhibitors, nonsteroidal anti-inflammatory drugs, opioids, antidepressants, and statins. The VA PHASER panel includes the solute carrier organic anion transporter family member 1B1 (SLCO1B1) gene, which is predominantly expressed in the liver and facilitates the hepatic uptake of most statins.^13,14 A reduced function of SLCO1B1 can lead to higher statin levels, resulting in increased concentrations that may potentially cause SAMS.^13,14 Some alleles associated with reduced function include SLCO1B1*5, *15, *23, *31, and *46 to *49, whereas others are associated with increased function, such as SLCO1B1 *14 and *20 (Appendix).¹⁵ Supporting evidence shows the SLCO1B1*5 nucleotide polymorphism increases plasma levels of simvastatin and atorvastatin, affecting effectiveness or toxicity. ¹³ Females tend to have a lower body weight and higher percentage of body fat compared with males, which might lead to higher concentrations of lipophilic drugs, including atorvastatin and simvastatin, which may be exacerbated by decreased function of SLCO1B1*5.¹⁵ With pharmacogenomic testing, therapeutic recommendations can be made to improve the overall safety and efficacy of statins, thus improving adherence using a patient-specific approach.^14,15

Methods

Carl Vinson VA Medical Center (CVVAMC) serves about 42,000 veterans in Central and South Georgia, of which about 15% are female. Of the female veterans enrolled in care, 63% identify as Black, 27% White, and 1.5% as Asian, American Indian/Alaska Native, or Native Hawaiian/Other Pacific Islander. The 2020 Veterans Chartbook report showed that female veterans and minority racial and ethnic groups had worse access to health care and higher mortality rates than their male and non-Hispanic White counterparts.¹⁶

The Primary Care Equity Dashboard (PCED) was developed to engage the VA health care workforce in the process of identifying and addressing inequities in local patient populations.¹⁷ Using electronic quality measure data, the PCED provides Veterans Integrated Service Network-level and facility-level performance on several metrics.¹⁸ The PCED had not been previously used at the CVVAMC, and few publications or quality improvement projects regarding its use have been reported by the VA Office of Health Equity. PCED helped identify disparities when comparing female to male patients in the prescribing of statin therapy for patients with CVD and statin therapy for patients with T2DM.

VA PHASER pharmacogenomic analyses provided an opportunity to expand this quality improvement project. Sanford Health and the VA collaborated on the PHASER program to offer free genetic testing for veterans. The program launched in 2019 and expanded to various VA sites, including CVVAMC in March 2023. This program has been extended to December 31, 2025.

The primary objective of this quality improvement project was to increase statin prescribing among female veterans with T2DM and/or CVD to reduce cardiovascular risk. Secondary outcomes included increased pharmacogenomic testing and the assessment of pharmacogenomic results related to statin therapy. This project was approved by the CVVAMC Pharmacy and Therapeutics Committee. The PCED was used to identify female veterans with T2DM and/or CVD without an active prescription for a statin between July and October 2023. A review of Computerized Patient Record System patient charts was completed to screen for prespecified inclusion and exclusion criteria. Veterans were included if they were assigned female at birth, were enrolled in care at CVVAMC, and had a diagnosis of T2DM or CVD (history of myocardial infarction, coronary bypass graft, percutaneous coronary intervention, or other revascularization in any setting).

Veterans were excluded if they were currently pregnant, trying to conceive, breastfeeding, had a T1DM diagnosis, had previously documented hypersensitivity to a statin, active liver failure or decompensated cirrhosis, previously documented statin-associated rhabdomyolysis or autoimmune myopathy, an active prescription for a proprotein convertase subtilisin/kexin type 9 inhibitor, or previously documented statin intolerance (defined as the inability to tolerate ≥ 3 statins, with ≥ 1 prescribed at low intensity or alternate-day dosing). The female veterans were compared to 2 comparators: the facility's male veterans and the VA national average, identified via the PCED.

Once a veteran was screened, they were telephoned between October 2023 and February 2024 and provided education on statin use and pharmacogenomic testing using a standardized note template. An order was placed for participants who provided verbal consent for pharmacogenomic testing. Those who agreed to statin initiation were referred to a clinical pharmacist practitioner (CPP) who contacted them at a later date to prescribe a statin following the recommendations of the 2019 ACC/AHA and 2023 ADA guidelines and pharmacogenomic testing, if applicable.^4,5,7 Appropriate monitoring and follow-up occurred at the discretion of each CPP. Data collection included: age, race, diagnoses (T2DM, CVD, or both), baseline lipid panel (total cholesterol, triglycerides, high-density lipoprotein, low-density lipoprotein), hepatic function, name and dose of statin, reasons for declining statin therapy, and pharmacogenomic testing results related to SLCO1B1.

Results

At baseline in July 2023, 77.8% of female veterans with T2DM were prescribed a statin, which exceeded the national VA average (77.0%), but was below the rate for male veterans (78.7%) in the facility comparator group.17 Additionally, 82.2% of females with CVD were prescribed a statin, which was below the national VA average of 86.0% and the 84.9% of male veterans in the facility comparator group.17 The PCED identified 189 female veterans from July 2023 to October 2023 who may benefit from statin therapy. Thirty-three females met the exclusion criteria. Of the 156 included veterans, 129 (82.7%) were successfully contacted and 27 (17.3%) could not be reached by telephone after 3 attempts (Figure 1). The 129 female veterans contacted had a mean age of 59 years and the majority were Black (82.9%) (Table 1).

Primary Outcomes

Of the 129 contacted veterans, 31 (24.0%) had a non-VA statin prescription, 13 (10.1%) had an active VA statin prescription, and 85 (65.9%) did not have a statin prescription, despite being eligible. Statin adherence was confirmed with participants, and the medication list was updated accordingly.

Of the 85 veterans with no active statin therapy, 37 (43.5%) accepted a new statin prescription and 48 (56.5%) declined. There were various reasons provided for declining statin therapy: 17 participants (35.4%) declined due to concern for AEs (Table 2).

From July 2023 to March 2024, the percentage of female veterans with active statin therapy with T2DM increased from 77.8% to 79.0%. For those with active statin therapy with CVD, usage increased from 82.2% to 90.2%, which exceeded the national VA average and facility male comparator group (Figures 2 and 3).¹⁷

Secondary Outcomes

Seventy-one of 129 veterans (55.0%) gave verbal consent, and 47 (66.2%) completed the pharmacogenomic testing; 58 (45.0%) declined. Five veterans (10.6%) had a known SLCO1B1 allele variant present. One veteran required a change in statin therapy based on the results (eAppendix).

Discussion

This project aimed to increase statin prescribing among female veterans with T2DM and/or CVD to reduce cardiovascular risk and increase pharmacogenomic testing using the PCED and care managed by CPPs. The results of this quality improvement project illustrated that both metrics have improved at CVVAMC as a result of the intervention. The results in both metrics now exceed the PCED national VA average, and the CVD metric also exceeds that of the facility male comparator group. While there was only a 1.2% increase from July 2023 to March 2024 for patients with T2DM, there was an 8.0% increase for patients with CVD. Despite standardized education on statin use, more veterans declined therapy than accepted it, mostly due to concern for AEs. Recording the reasons for declining statin therapy offered valuable insight that can be used in additional discussions with veterans and clinicians.

Pharmacogenomics gives clinicians the unique opportunity to take a proactive approach to better predict drug responses, potentially allowing for less trial and error with medications, fewer AEs, greater trust in the clinician, and improved medication adherence. The CPPs incorporated pharmacogenomic testing into their practice, which led to identifying 5 SLCO1B1 gene abnormalities. The PCED served as a powerful tool for advancing equity-focused quality improvement initiatives on a local level and was crucial in prioritizing the detection of veterans potentially receiving suboptimal care.

Limitations

The nature of “cold calls” made it challenging to establish contact for inclusion in this study. An alternative to increase engagement could have been scheduled phone or face-to-face visits. While the use of the PCED was crucial, data did not account for statins listed in the non-VA medication list. All 31 patients with statins prescribed outside the VA had a start date added to provide the most accurate representation of the data moving forward.

Another limitation in this project was its small sample size and population. CVVAMC serves about 6200 female veterans, with roughly 63% identifying as Black. The preponderance of Black individuals (83%) in this project is typical for the female patient population at CVVAMC but may not reflect the demographics of other populations. Other limitations to this project consisted of scheduling conflicts. Appointments for laboratory draws at community-based outpatient clinics were subject to availability, which resulted in some delay in completion of pharmacogenomic testing.

Conclusions

CPPs can help reduce inequity in health care delivery. Increased incorporation of the PCED into regular practice within the VA is recommended to continue addressing sex disparities in statin use, diabetes control, blood pressure management, cancer screenings, and vaccination needs. CVVAMC plans to expand its use through another quality improvement project focused on reducing sex disparities in blood pressure management. Improving educational resources made available to veterans on the importance of statin therapy and potential to mitigate AEs through use of the VA PHASER program also would be helpful. This project successfully improved CVVAMC metrics for female veterans appropriately prescribed statin therapy and increased access to pharmacogenomic testing. Most importantly, it helped close the sex-based gap in CVD risk reduction care.

Cardiovascular disease (CVD) is the leading cause of death among women in the United States.¹ Most CVD is due to the buildup of plaque (ie, cholesterol, proteins, calcium, and inflammatory cells) in artery walls.² The plaque may lead to atherosclerotic cardiovascular disease (ASCVD), which includes coronary heart disease, cerebrovascular disease, peripheral artery disease, and aortic atherosclerotic disease.^2,3 Control and reduction of ASCVD risk factors, including high cholesterol levels, elevated blood pressure, insulin resistance, smoking, and a sedentary lifestyle, can contribute to a reduction in ASCVD morbidity and mortality.² People with type 2 diabetes mellitus (T2DM) have an increased prevalence of lipid abnormalities, contributing to their high risk of ASCVD.^4,5

The prescribing of statins (3-hydroxy-3-methyl-glutaryl-coenzmye A reductase inhibitors) is the cornerstone of lipid-lowering therapy and cardiovascular risk reduction for primary and secondary prevention of ASCVD.⁶ The American Diabetes Association (ADA) and American College of Cardiology/American Heart Association (ACC/AHA) recommend moderate- to high-intensity statins for primary prevention in patients with T2DM and high-intensity statins for secondary prevention in those with or without diabetes when not contraindicated.^4,5,7 Despite eligibility according to guideline recommendations, research predominantly shows that women are less likely to receive statin therapy; however, this trend is improving. ^[6,8-11] To explain the sex differences in statin use, Nanna et al found that there is a combination of women being offered statin therapy less frequently, declining therapy more frequently, and discontinuing treatment more frequently.¹¹ One possibility for discontinuing treatment could be statin-associated muscle symptoms (SAMS), which occur in about 10% of patients.¹² The incidence of adverse effects (AEs) may be related to the way statins are metabolized.

Pharmacogenomic testing is free for veterans through the US Department of Veterans Affairs (VA) PHASER program, which offers information and recommendations for a panel of 11 gene variants. The panel includes genes related to common medication classes such as anticoagulants, antiplatelets, proton pump inhibitors, nonsteroidal anti-inflammatory drugs, opioids, antidepressants, and statins. The VA PHASER panel includes the solute carrier organic anion transporter family member 1B1 (SLCO1B1) gene, which is predominantly expressed in the liver and facilitates the hepatic uptake of most statins.^13,14 A reduced function of SLCO1B1 can lead to higher statin levels, resulting in increased concentrations that may potentially cause SAMS.^13,14 Some alleles associated with reduced function include SLCO1B1*5, *15, *23, *31, and *46 to *49, whereas others are associated with increased function, such as SLCO1B1 *14 and *20 (Appendix).¹⁵ Supporting evidence shows the SLCO1B1*5 nucleotide polymorphism increases plasma levels of simvastatin and atorvastatin, affecting effectiveness or toxicity. ¹³ Females tend to have a lower body weight and higher percentage of body fat compared with males, which might lead to higher concentrations of lipophilic drugs, including atorvastatin and simvastatin, which may be exacerbated by decreased function of SLCO1B1*5.¹⁵ With pharmacogenomic testing, therapeutic recommendations can be made to improve the overall safety and efficacy of statins, thus improving adherence using a patient-specific approach.^14,15

Methods

Carl Vinson VA Medical Center (CVVAMC) serves about 42,000 veterans in Central and South Georgia, of which about 15% are female. Of the female veterans enrolled in care, 63% identify as Black, 27% White, and 1.5% as Asian, American Indian/Alaska Native, or Native Hawaiian/Other Pacific Islander. The 2020 Veterans Chartbook report showed that female veterans and minority racial and ethnic groups had worse access to health care and higher mortality rates than their male and non-Hispanic White counterparts.¹⁶

The Primary Care Equity Dashboard (PCED) was developed to engage the VA health care workforce in the process of identifying and addressing inequities in local patient populations.¹⁷ Using electronic quality measure data, the PCED provides Veterans Integrated Service Network-level and facility-level performance on several metrics.¹⁸ The PCED had not been previously used at the CVVAMC, and few publications or quality improvement projects regarding its use have been reported by the VA Office of Health Equity. PCED helped identify disparities when comparing female to male patients in the prescribing of statin therapy for patients with CVD and statin therapy for patients with T2DM.

VA PHASER pharmacogenomic analyses provided an opportunity to expand this quality improvement project. Sanford Health and the VA collaborated on the PHASER program to offer free genetic testing for veterans. The program launched in 2019 and expanded to various VA sites, including CVVAMC in March 2023. This program has been extended to December 31, 2025.

The primary objective of this quality improvement project was to increase statin prescribing among female veterans with T2DM and/or CVD to reduce cardiovascular risk. Secondary outcomes included increased pharmacogenomic testing and the assessment of pharmacogenomic results related to statin therapy. This project was approved by the CVVAMC Pharmacy and Therapeutics Committee. The PCED was used to identify female veterans with T2DM and/or CVD without an active prescription for a statin between July and October 2023. A review of Computerized Patient Record System patient charts was completed to screen for prespecified inclusion and exclusion criteria. Veterans were included if they were assigned female at birth, were enrolled in care at CVVAMC, and had a diagnosis of T2DM or CVD (history of myocardial infarction, coronary bypass graft, percutaneous coronary intervention, or other revascularization in any setting).

Veterans were excluded if they were currently pregnant, trying to conceive, breastfeeding, had a T1DM diagnosis, had previously documented hypersensitivity to a statin, active liver failure or decompensated cirrhosis, previously documented statin-associated rhabdomyolysis or autoimmune myopathy, an active prescription for a proprotein convertase subtilisin/kexin type 9 inhibitor, or previously documented statin intolerance (defined as the inability to tolerate ≥ 3 statins, with ≥ 1 prescribed at low intensity or alternate-day dosing). The female veterans were compared to 2 comparators: the facility's male veterans and the VA national average, identified via the PCED.

Once a veteran was screened, they were telephoned between October 2023 and February 2024 and provided education on statin use and pharmacogenomic testing using a standardized note template. An order was placed for participants who provided verbal consent for pharmacogenomic testing. Those who agreed to statin initiation were referred to a clinical pharmacist practitioner (CPP) who contacted them at a later date to prescribe a statin following the recommendations of the 2019 ACC/AHA and 2023 ADA guidelines and pharmacogenomic testing, if applicable.^4,5,7 Appropriate monitoring and follow-up occurred at the discretion of each CPP. Data collection included: age, race, diagnoses (T2DM, CVD, or both), baseline lipid panel (total cholesterol, triglycerides, high-density lipoprotein, low-density lipoprotein), hepatic function, name and dose of statin, reasons for declining statin therapy, and pharmacogenomic testing results related to SLCO1B1.

Results

At baseline in July 2023, 77.8% of female veterans with T2DM were prescribed a statin, which exceeded the national VA average (77.0%), but was below the rate for male veterans (78.7%) in the facility comparator group.17 Additionally, 82.2% of females with CVD were prescribed a statin, which was below the national VA average of 86.0% and the 84.9% of male veterans in the facility comparator group.17 The PCED identified 189 female veterans from July 2023 to October 2023 who may benefit from statin therapy. Thirty-three females met the exclusion criteria. Of the 156 included veterans, 129 (82.7%) were successfully contacted and 27 (17.3%) could not be reached by telephone after 3 attempts (Figure 1). The 129 female veterans contacted had a mean age of 59 years and the majority were Black (82.9%) (Table 1).

Primary Outcomes

Of the 129 contacted veterans, 31 (24.0%) had a non-VA statin prescription, 13 (10.1%) had an active VA statin prescription, and 85 (65.9%) did not have a statin prescription, despite being eligible. Statin adherence was confirmed with participants, and the medication list was updated accordingly.

Of the 85 veterans with no active statin therapy, 37 (43.5%) accepted a new statin prescription and 48 (56.5%) declined. There were various reasons provided for declining statin therapy: 17 participants (35.4%) declined due to concern for AEs (Table 2).

From July 2023 to March 2024, the percentage of female veterans with active statin therapy with T2DM increased from 77.8% to 79.0%. For those with active statin therapy with CVD, usage increased from 82.2% to 90.2%, which exceeded the national VA average and facility male comparator group (Figures 2 and 3).¹⁷

Secondary Outcomes

Seventy-one of 129 veterans (55.0%) gave verbal consent, and 47 (66.2%) completed the pharmacogenomic testing; 58 (45.0%) declined. Five veterans (10.6%) had a known SLCO1B1 allele variant present. One veteran required a change in statin therapy based on the results (eAppendix).

Discussion

This project aimed to increase statin prescribing among female veterans with T2DM and/or CVD to reduce cardiovascular risk and increase pharmacogenomic testing using the PCED and care managed by CPPs. The results of this quality improvement project illustrated that both metrics have improved at CVVAMC as a result of the intervention. The results in both metrics now exceed the PCED national VA average, and the CVD metric also exceeds that of the facility male comparator group. While there was only a 1.2% increase from July 2023 to March 2024 for patients with T2DM, there was an 8.0% increase for patients with CVD. Despite standardized education on statin use, more veterans declined therapy than accepted it, mostly due to concern for AEs. Recording the reasons for declining statin therapy offered valuable insight that can be used in additional discussions with veterans and clinicians.

Pharmacogenomics gives clinicians the unique opportunity to take a proactive approach to better predict drug responses, potentially allowing for less trial and error with medications, fewer AEs, greater trust in the clinician, and improved medication adherence. The CPPs incorporated pharmacogenomic testing into their practice, which led to identifying 5 SLCO1B1 gene abnormalities. The PCED served as a powerful tool for advancing equity-focused quality improvement initiatives on a local level and was crucial in prioritizing the detection of veterans potentially receiving suboptimal care.

Limitations

The nature of “cold calls” made it challenging to establish contact for inclusion in this study. An alternative to increase engagement could have been scheduled phone or face-to-face visits. While the use of the PCED was crucial, data did not account for statins listed in the non-VA medication list. All 31 patients with statins prescribed outside the VA had a start date added to provide the most accurate representation of the data moving forward.

Another limitation in this project was its small sample size and population. CVVAMC serves about 6200 female veterans, with roughly 63% identifying as Black. The preponderance of Black individuals (83%) in this project is typical for the female patient population at CVVAMC but may not reflect the demographics of other populations. Other limitations to this project consisted of scheduling conflicts. Appointments for laboratory draws at community-based outpatient clinics were subject to availability, which resulted in some delay in completion of pharmacogenomic testing.

Conclusions

CPPs can help reduce inequity in health care delivery. Increased incorporation of the PCED into regular practice within the VA is recommended to continue addressing sex disparities in statin use, diabetes control, blood pressure management, cancer screenings, and vaccination needs. CVVAMC plans to expand its use through another quality improvement project focused on reducing sex disparities in blood pressure management. Improving educational resources made available to veterans on the importance of statin therapy and potential to mitigate AEs through use of the VA PHASER program also would be helpful. This project successfully improved CVVAMC metrics for female veterans appropriately prescribed statin therapy and increased access to pharmacogenomic testing. Most importantly, it helped close the sex-based gap in CVD risk reduction care.

Cardiovascular disease (CVD) is the leading cause of death among women in the United States.¹ Most CVD is due to the buildup of plaque (ie, cholesterol, proteins, calcium, and inflammatory cells) in artery walls.² The plaque may lead to atherosclerotic cardiovascular disease (ASCVD), which includes coronary heart disease, cerebrovascular disease, peripheral artery disease, and aortic atherosclerotic disease.^2,3 Control and reduction of ASCVD risk factors, including high cholesterol levels, elevated blood pressure, insulin resistance, smoking, and a sedentary lifestyle, can contribute to a reduction in ASCVD morbidity and mortality.² People with type 2 diabetes mellitus (T2DM) have an increased prevalence of lipid abnormalities, contributing to their high risk of ASCVD.^4,5

The prescribing of statins (3-hydroxy-3-methyl-glutaryl-coenzmye A reductase inhibitors) is the cornerstone of lipid-lowering therapy and cardiovascular risk reduction for primary and secondary prevention of ASCVD.⁶ The American Diabetes Association (ADA) and American College of Cardiology/American Heart Association (ACC/AHA) recommend moderate- to high-intensity statins for primary prevention in patients with T2DM and high-intensity statins for secondary prevention in those with or without diabetes when not contraindicated.^4,5,7 Despite eligibility according to guideline recommendations, research predominantly shows that women are less likely to receive statin therapy; however, this trend is improving. ^[6,8-11] To explain the sex differences in statin use, Nanna et al found that there is a combination of women being offered statin therapy less frequently, declining therapy more frequently, and discontinuing treatment more frequently.¹¹ One possibility for discontinuing treatment could be statin-associated muscle symptoms (SAMS), which occur in about 10% of patients.¹² The incidence of adverse effects (AEs) may be related to the way statins are metabolized.

Pharmacogenomic testing is free for veterans through the US Department of Veterans Affairs (VA) PHASER program, which offers information and recommendations for a panel of 11 gene variants. The panel includes genes related to common medication classes such as anticoagulants, antiplatelets, proton pump inhibitors, nonsteroidal anti-inflammatory drugs, opioids, antidepressants, and statins. The VA PHASER panel includes the solute carrier organic anion transporter family member 1B1 (SLCO1B1) gene, which is predominantly expressed in the liver and facilitates the hepatic uptake of most statins.^13,14 A reduced function of SLCO1B1 can lead to higher statin levels, resulting in increased concentrations that may potentially cause SAMS.^13,14 Some alleles associated with reduced function include SLCO1B1*5, *15, *23, *31, and *46 to *49, whereas others are associated with increased function, such as SLCO1B1 *14 and *20 (Appendix).¹⁵ Supporting evidence shows the SLCO1B1*5 nucleotide polymorphism increases plasma levels of simvastatin and atorvastatin, affecting effectiveness or toxicity. ¹³ Females tend to have a lower body weight and higher percentage of body fat compared with males, which might lead to higher concentrations of lipophilic drugs, including atorvastatin and simvastatin, which may be exacerbated by decreased function of SLCO1B1*5.¹⁵ With pharmacogenomic testing, therapeutic recommendations can be made to improve the overall safety and efficacy of statins, thus improving adherence using a patient-specific approach.^14,15

Methods

Carl Vinson VA Medical Center (CVVAMC) serves about 42,000 veterans in Central and South Georgia, of which about 15% are female. Of the female veterans enrolled in care, 63% identify as Black, 27% White, and 1.5% as Asian, American Indian/Alaska Native, or Native Hawaiian/Other Pacific Islander. The 2020 Veterans Chartbook report showed that female veterans and minority racial and ethnic groups had worse access to health care and higher mortality rates than their male and non-Hispanic White counterparts.¹⁶

The Primary Care Equity Dashboard (PCED) was developed to engage the VA health care workforce in the process of identifying and addressing inequities in local patient populations.¹⁷ Using electronic quality measure data, the PCED provides Veterans Integrated Service Network-level and facility-level performance on several metrics.¹⁸ The PCED had not been previously used at the CVVAMC, and few publications or quality improvement projects regarding its use have been reported by the VA Office of Health Equity. PCED helped identify disparities when comparing female to male patients in the prescribing of statin therapy for patients with CVD and statin therapy for patients with T2DM.

VA PHASER pharmacogenomic analyses provided an opportunity to expand this quality improvement project. Sanford Health and the VA collaborated on the PHASER program to offer free genetic testing for veterans. The program launched in 2019 and expanded to various VA sites, including CVVAMC in March 2023. This program has been extended to December 31, 2025.

The primary objective of this quality improvement project was to increase statin prescribing among female veterans with T2DM and/or CVD to reduce cardiovascular risk. Secondary outcomes included increased pharmacogenomic testing and the assessment of pharmacogenomic results related to statin therapy. This project was approved by the CVVAMC Pharmacy and Therapeutics Committee. The PCED was used to identify female veterans with T2DM and/or CVD without an active prescription for a statin between July and October 2023. A review of Computerized Patient Record System patient charts was completed to screen for prespecified inclusion and exclusion criteria. Veterans were included if they were assigned female at birth, were enrolled in care at CVVAMC, and had a diagnosis of T2DM or CVD (history of myocardial infarction, coronary bypass graft, percutaneous coronary intervention, or other revascularization in any setting).

Veterans were excluded if they were currently pregnant, trying to conceive, breastfeeding, had a T1DM diagnosis, had previously documented hypersensitivity to a statin, active liver failure or decompensated cirrhosis, previously documented statin-associated rhabdomyolysis or autoimmune myopathy, an active prescription for a proprotein convertase subtilisin/kexin type 9 inhibitor, or previously documented statin intolerance (defined as the inability to tolerate ≥ 3 statins, with ≥ 1 prescribed at low intensity or alternate-day dosing). The female veterans were compared to 2 comparators: the facility's male veterans and the VA national average, identified via the PCED.

Once a veteran was screened, they were telephoned between October 2023 and February 2024 and provided education on statin use and pharmacogenomic testing using a standardized note template. An order was placed for participants who provided verbal consent for pharmacogenomic testing. Those who agreed to statin initiation were referred to a clinical pharmacist practitioner (CPP) who contacted them at a later date to prescribe a statin following the recommendations of the 2019 ACC/AHA and 2023 ADA guidelines and pharmacogenomic testing, if applicable.^4,5,7 Appropriate monitoring and follow-up occurred at the discretion of each CPP. Data collection included: age, race, diagnoses (T2DM, CVD, or both), baseline lipid panel (total cholesterol, triglycerides, high-density lipoprotein, low-density lipoprotein), hepatic function, name and dose of statin, reasons for declining statin therapy, and pharmacogenomic testing results related to SLCO1B1.

Results

At baseline in July 2023, 77.8% of female veterans with T2DM were prescribed a statin, which exceeded the national VA average (77.0%), but was below the rate for male veterans (78.7%) in the facility comparator group.17 Additionally, 82.2% of females with CVD were prescribed a statin, which was below the national VA average of 86.0% and the 84.9% of male veterans in the facility comparator group.17 The PCED identified 189 female veterans from July 2023 to October 2023 who may benefit from statin therapy. Thirty-three females met the exclusion criteria. Of the 156 included veterans, 129 (82.7%) were successfully contacted and 27 (17.3%) could not be reached by telephone after 3 attempts (Figure 1). The 129 female veterans contacted had a mean age of 59 years and the majority were Black (82.9%) (Table 1).

Primary Outcomes

Of the 129 contacted veterans, 31 (24.0%) had a non-VA statin prescription, 13 (10.1%) had an active VA statin prescription, and 85 (65.9%) did not have a statin prescription, despite being eligible. Statin adherence was confirmed with participants, and the medication list was updated accordingly.

Of the 85 veterans with no active statin therapy, 37 (43.5%) accepted a new statin prescription and 48 (56.5%) declined. There were various reasons provided for declining statin therapy: 17 participants (35.4%) declined due to concern for AEs (Table 2).

From July 2023 to March 2024, the percentage of female veterans with active statin therapy with T2DM increased from 77.8% to 79.0%. For those with active statin therapy with CVD, usage increased from 82.2% to 90.2%, which exceeded the national VA average and facility male comparator group (Figures 2 and 3).¹⁷

Secondary Outcomes

Seventy-one of 129 veterans (55.0%) gave verbal consent, and 47 (66.2%) completed the pharmacogenomic testing; 58 (45.0%) declined. Five veterans (10.6%) had a known SLCO1B1 allele variant present. One veteran required a change in statin therapy based on the results (eAppendix).

Discussion

This project aimed to increase statin prescribing among female veterans with T2DM and/or CVD to reduce cardiovascular risk and increase pharmacogenomic testing using the PCED and care managed by CPPs. The results of this quality improvement project illustrated that both metrics have improved at CVVAMC as a result of the intervention. The results in both metrics now exceed the PCED national VA average, and the CVD metric also exceeds that of the facility male comparator group. While there was only a 1.2% increase from July 2023 to March 2024 for patients with T2DM, there was an 8.0% increase for patients with CVD. Despite standardized education on statin use, more veterans declined therapy than accepted it, mostly due to concern for AEs. Recording the reasons for declining statin therapy offered valuable insight that can be used in additional discussions with veterans and clinicians.

Pharmacogenomics gives clinicians the unique opportunity to take a proactive approach to better predict drug responses, potentially allowing for less trial and error with medications, fewer AEs, greater trust in the clinician, and improved medication adherence. The CPPs incorporated pharmacogenomic testing into their practice, which led to identifying 5 SLCO1B1 gene abnormalities. The PCED served as a powerful tool for advancing equity-focused quality improvement initiatives on a local level and was crucial in prioritizing the detection of veterans potentially receiving suboptimal care.

Limitations

The nature of “cold calls” made it challenging to establish contact for inclusion in this study. An alternative to increase engagement could have been scheduled phone or face-to-face visits. While the use of the PCED was crucial, data did not account for statins listed in the non-VA medication list. All 31 patients with statins prescribed outside the VA had a start date added to provide the most accurate representation of the data moving forward.

Another limitation in this project was its small sample size and population. CVVAMC serves about 6200 female veterans, with roughly 63% identifying as Black. The preponderance of Black individuals (83%) in this project is typical for the female patient population at CVVAMC but may not reflect the demographics of other populations. Other limitations to this project consisted of scheduling conflicts. Appointments for laboratory draws at community-based outpatient clinics were subject to availability, which resulted in some delay in completion of pharmacogenomic testing.

Conclusions

CPPs can help reduce inequity in health care delivery. Increased incorporation of the PCED into regular practice within the VA is recommended to continue addressing sex disparities in statin use, diabetes control, blood pressure management, cancer screenings, and vaccination needs. CVVAMC plans to expand its use through another quality improvement project focused on reducing sex disparities in blood pressure management. Improving educational resources made available to veterans on the importance of statin therapy and potential to mitigate AEs through use of the VA PHASER program also would be helpful. This project successfully improved CVVAMC metrics for female veterans appropriately prescribed statin therapy and increased access to pharmacogenomic testing. Most importantly, it helped close the sex-based gap in CVD risk reduction care.

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.