AVAHO

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.

The ongoing US government partial shutdown has unintended consequences for seniors and their doctors as most telehealth appointments are now no longer being covered by Medicare.

That's because without a budget deal, federal lawmakers did not renew some pandemic-era telehealth flexibilities allowing Medicare beneficiaries to have medical appointments with doctors over audio or video at home.

This policy was first put into place under the first Trump Administration in 2020 during the COVID-19 pandemic. Previously, Medicare covered very limited telehealth services for rural patients.

For the past 5 years, lawmakers have always managed to renew the telehealth flexibilities in every government funding bill before the expiration date. This year, however, they expired for the first time on October 1.

Federal lawmakers remain at odds on the 2026 federal funding bill, meaning the shutdown could last into more days and even weeks.

But with Congress in a standoff, clinicians and patients outside Washington, DC, are already grappling with the consequences of the funding impasse.

Clinicians, Patients Already Feeling Effects

For the South Dakota-based Sanford Health System, which is the largest rural health system in the country, the past week without the Medicare telehealth waivers being in place has caused a lot of anxiety and uncertainty for both patients and clinicians.

Dave Newman, an endocrinologist and chief medical officer of virtual care at Sanford, said the health system decided to keep providing Medicare telehealth appointments to patients for now.

"We're maintaining telehealth access because we know that's the best thing for our patients. We've got full confidence that reimbursement will follow, but patients can't wait for Congress to act at this point," Newman told Medscape Medical News. "They still need access to their specialists. They still need access to their primary care providers, and this is one of the only ways that a lot of our patients get access. For them, it's either virtual care or no care at all."

Newman said as the shutdown continues, Sanford may reconsidered whether it can keep providing these appointments without reimbursement.

Some health systems have stopped providing an Medicare telehealth appointments, said Alexis Apple, director of federal affairs at the American Telemedicine Association. That means patients must appear in person for their doctor's appointment or cancel.

NYU Langone Health system's website currently has a banner that reads: "Due to the federal government shutdown, Medicare and Medicaid patients are unable to schedule new telehealth/video visits. If you already have a visit scheduled, it will continue as planned. If not, contact your doctor's office to schedule an in-person appointment.

"It's creating lots of confusion in the industry from patients, providers, hospital systems. You know, what do we do next? How do we grapple with this shutdown?" said Apple. "Patients have been able to receive care within their homes over the past 5 years, and now, all of a sudden, they've been stripped of that access."

Medicare patients who continue telehealth after October 1 may find out they're on the hook for the bill, if Congress doesn't act, said Apple.

Some physicians worry that commercial insurance payers may follow suit and no longer cover virtual appointments. Medicare, which is the largest health care payer in the country, is often seen as the standard for what services should be covered.

Patients and doctors have come to rely on telehealth as an integral part of health care, said Richard Chou, an anesthesiologist at the US Department of Veterans Affairs (VA) in Sacramento, California.

"You're seeing that postpandemic, telehealth is kind of a new way of doing things. It's part of the day for us as doctors," said Chou. He said tha tmany of his VA patients do their preliminary surgery appointments via telehealth before coming into the facility.

"Telehealth is that bridge to making sure patients get the care they need, and when these patients don't get that preliminary care they need, this builds up and builds up," said Chou. "And next thing you know, you have people flooding the emergency rooms, and we can't have that."

Will Telehealth Reimbursement See a Permanent Fix?

With Congressional budget negotiations at an impasse, it remains unclear when the shutdown will end.

Health care spending disagreements weigh heavily in negotiations. Democrats are currently unwilling to give the votes to pass the 60-vote threshold in the Senate unless Republicans agree to extend Affordable Care Act subsidies that expire at the end of the year. Democrats also want to reverse the Medicaid cuts that were part of the large Republican domestic tax and spending bill passed by Congress earlier this year.

When lawmakers do reach an agreement and reopen the government, it's likely telehealth flexibilities will be included in any package but for how long remains in question.

A newly introduced bipartisan bill would permanently allow Medicare patients to access telehealth appointments in their homes. But the legislation has been estimated to be very costly.

Federal data does show that telehealth appointments have been popular with Medicare recipients and increased over time since telehealth became more accessible.

"I used to say that virtual care was the future of medicine, and now it's just kind of the present of medicine. It used to be like a cool technology that we used to advertise, now it's just the standard of care," said Newman. "We think that permanent coverage would mean stability for both patients and providers."

Victoria Knight is a freelance reporter based in Washington, DC.

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

The ongoing US government partial shutdown has unintended consequences for seniors and their doctors as most telehealth appointments are now no longer being covered by Medicare.

That's because without a budget deal, federal lawmakers did not renew some pandemic-era telehealth flexibilities allowing Medicare beneficiaries to have medical appointments with doctors over audio or video at home.

This policy was first put into place under the first Trump Administration in 2020 during the COVID-19 pandemic. Previously, Medicare covered very limited telehealth services for rural patients.

For the past 5 years, lawmakers have always managed to renew the telehealth flexibilities in every government funding bill before the expiration date. This year, however, they expired for the first time on October 1.

Federal lawmakers remain at odds on the 2026 federal funding bill, meaning the shutdown could last into more days and even weeks.

But with Congress in a standoff, clinicians and patients outside Washington, DC, are already grappling with the consequences of the funding impasse.

Clinicians, Patients Already Feeling Effects

For the South Dakota-based Sanford Health System, which is the largest rural health system in the country, the past week without the Medicare telehealth waivers being in place has caused a lot of anxiety and uncertainty for both patients and clinicians.

Dave Newman, an endocrinologist and chief medical officer of virtual care at Sanford, said the health system decided to keep providing Medicare telehealth appointments to patients for now.

"We're maintaining telehealth access because we know that's the best thing for our patients. We've got full confidence that reimbursement will follow, but patients can't wait for Congress to act at this point," Newman told Medscape Medical News. "They still need access to their specialists. They still need access to their primary care providers, and this is one of the only ways that a lot of our patients get access. For them, it's either virtual care or no care at all."

Newman said as the shutdown continues, Sanford may reconsidered whether it can keep providing these appointments without reimbursement.

Some health systems have stopped providing an Medicare telehealth appointments, said Alexis Apple, director of federal affairs at the American Telemedicine Association. That means patients must appear in person for their doctor's appointment or cancel.

NYU Langone Health system's website currently has a banner that reads: "Due to the federal government shutdown, Medicare and Medicaid patients are unable to schedule new telehealth/video visits. If you already have a visit scheduled, it will continue as planned. If not, contact your doctor's office to schedule an in-person appointment.

"It's creating lots of confusion in the industry from patients, providers, hospital systems. You know, what do we do next? How do we grapple with this shutdown?" said Apple. "Patients have been able to receive care within their homes over the past 5 years, and now, all of a sudden, they've been stripped of that access."

Medicare patients who continue telehealth after October 1 may find out they're on the hook for the bill, if Congress doesn't act, said Apple.

Some physicians worry that commercial insurance payers may follow suit and no longer cover virtual appointments. Medicare, which is the largest health care payer in the country, is often seen as the standard for what services should be covered.

Patients and doctors have come to rely on telehealth as an integral part of health care, said Richard Chou, an anesthesiologist at the US Department of Veterans Affairs (VA) in Sacramento, California.

"You're seeing that postpandemic, telehealth is kind of a new way of doing things. It's part of the day for us as doctors," said Chou. He said tha tmany of his VA patients do their preliminary surgery appointments via telehealth before coming into the facility.

"Telehealth is that bridge to making sure patients get the care they need, and when these patients don't get that preliminary care they need, this builds up and builds up," said Chou. "And next thing you know, you have people flooding the emergency rooms, and we can't have that."

Will Telehealth Reimbursement See a Permanent Fix?

With Congressional budget negotiations at an impasse, it remains unclear when the shutdown will end.

Health care spending disagreements weigh heavily in negotiations. Democrats are currently unwilling to give the votes to pass the 60-vote threshold in the Senate unless Republicans agree to extend Affordable Care Act subsidies that expire at the end of the year. Democrats also want to reverse the Medicaid cuts that were part of the large Republican domestic tax and spending bill passed by Congress earlier this year.

When lawmakers do reach an agreement and reopen the government, it's likely telehealth flexibilities will be included in any package but for how long remains in question.

A newly introduced bipartisan bill would permanently allow Medicare patients to access telehealth appointments in their homes. But the legislation has been estimated to be very costly.

Federal data does show that telehealth appointments have been popular with Medicare recipients and increased over time since telehealth became more accessible.

"I used to say that virtual care was the future of medicine, and now it's just kind of the present of medicine. It used to be like a cool technology that we used to advertise, now it's just the standard of care," said Newman. "We think that permanent coverage would mean stability for both patients and providers."

Victoria Knight is a freelance reporter based in Washington, DC.

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

The ongoing US government partial shutdown has unintended consequences for seniors and their doctors as most telehealth appointments are now no longer being covered by Medicare.

That's because without a budget deal, federal lawmakers did not renew some pandemic-era telehealth flexibilities allowing Medicare beneficiaries to have medical appointments with doctors over audio or video at home.

This policy was first put into place under the first Trump Administration in 2020 during the COVID-19 pandemic. Previously, Medicare covered very limited telehealth services for rural patients.

For the past 5 years, lawmakers have always managed to renew the telehealth flexibilities in every government funding bill before the expiration date. This year, however, they expired for the first time on October 1.

Federal lawmakers remain at odds on the 2026 federal funding bill, meaning the shutdown could last into more days and even weeks.

But with Congress in a standoff, clinicians and patients outside Washington, DC, are already grappling with the consequences of the funding impasse.

Clinicians, Patients Already Feeling Effects

For the South Dakota-based Sanford Health System, which is the largest rural health system in the country, the past week without the Medicare telehealth waivers being in place has caused a lot of anxiety and uncertainty for both patients and clinicians.

Dave Newman, an endocrinologist and chief medical officer of virtual care at Sanford, said the health system decided to keep providing Medicare telehealth appointments to patients for now.

"We're maintaining telehealth access because we know that's the best thing for our patients. We've got full confidence that reimbursement will follow, but patients can't wait for Congress to act at this point," Newman told Medscape Medical News. "They still need access to their specialists. They still need access to their primary care providers, and this is one of the only ways that a lot of our patients get access. For them, it's either virtual care or no care at all."

Newman said as the shutdown continues, Sanford may reconsidered whether it can keep providing these appointments without reimbursement.

Some health systems have stopped providing an Medicare telehealth appointments, said Alexis Apple, director of federal affairs at the American Telemedicine Association. That means patients must appear in person for their doctor's appointment or cancel.

NYU Langone Health system's website currently has a banner that reads: "Due to the federal government shutdown, Medicare and Medicaid patients are unable to schedule new telehealth/video visits. If you already have a visit scheduled, it will continue as planned. If not, contact your doctor's office to schedule an in-person appointment.

"It's creating lots of confusion in the industry from patients, providers, hospital systems. You know, what do we do next? How do we grapple with this shutdown?" said Apple. "Patients have been able to receive care within their homes over the past 5 years, and now, all of a sudden, they've been stripped of that access."

Medicare patients who continue telehealth after October 1 may find out they're on the hook for the bill, if Congress doesn't act, said Apple.

Some physicians worry that commercial insurance payers may follow suit and no longer cover virtual appointments. Medicare, which is the largest health care payer in the country, is often seen as the standard for what services should be covered.

Patients and doctors have come to rely on telehealth as an integral part of health care, said Richard Chou, an anesthesiologist at the US Department of Veterans Affairs (VA) in Sacramento, California.

"You're seeing that postpandemic, telehealth is kind of a new way of doing things. It's part of the day for us as doctors," said Chou. He said tha tmany of his VA patients do their preliminary surgery appointments via telehealth before coming into the facility.

"Telehealth is that bridge to making sure patients get the care they need, and when these patients don't get that preliminary care they need, this builds up and builds up," said Chou. "And next thing you know, you have people flooding the emergency rooms, and we can't have that."

Will Telehealth Reimbursement See a Permanent Fix?

With Congressional budget negotiations at an impasse, it remains unclear when the shutdown will end.

Health care spending disagreements weigh heavily in negotiations. Democrats are currently unwilling to give the votes to pass the 60-vote threshold in the Senate unless Republicans agree to extend Affordable Care Act subsidies that expire at the end of the year. Democrats also want to reverse the Medicaid cuts that were part of the large Republican domestic tax and spending bill passed by Congress earlier this year.

When lawmakers do reach an agreement and reopen the government, it's likely telehealth flexibilities will be included in any package but for how long remains in question.

A newly introduced bipartisan bill would permanently allow Medicare patients to access telehealth appointments in their homes. But the legislation has been estimated to be very costly.

Federal data does show that telehealth appointments have been popular with Medicare recipients and increased over time since telehealth became more accessible.

"I used to say that virtual care was the future of medicine, and now it's just kind of the present of medicine. It used to be like a cool technology that we used to advertise, now it's just the standard of care," said Newman. "We think that permanent coverage would mean stability for both patients and providers."

Victoria Knight is a freelance reporter based in Washington, DC.

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

PHOENIX – Medications used in oncology clinical trials pose unique challenges in areas such as labeling, packaging, and administration, a US Department of Veterans Affairs (VA) pharmacist cautioned colleagues, and placebos have special needs too.

Even basic safety protections can be lacking when a drug is investigational, said Emily Hennes, PharmD, BCOP, clinical pharmacy specialist for research at William S. Middleton Memorial Veterans Hospital in Shorewood Hills, Wisconsin, in a presentation at the annual meeting of the Association of VA Hematology/Oncology.

“All of the safety features that we have come to know and love in dispensing commercial drugs are absent. There’s no Tall Man lettering, there's no color differentiation, and there's no barcoding, because these are not registered drugs," she said.

A 2017 report found that 81% of pharmacists surveyed indicated some level of concern regarding the safety risk in using  investigational drugs. At the same time, Hennes noted, the Joint Commission has mandated that pharmacists must control the storage, dispensing, labeling, and distribution of investigational medications.

Here are things to know about the use of investigational cancer drugs:

Drug Interactions Are Common

Hennes highlighted a 2023 study of medication reconciliation of 501 patients in 79 clinical trials that found alarming levels of drug interactions: 

• 360 clinically relevant drug-drug interactions were identified among 189 patients, including 158 therapies that were prohibited by protocols. Of these, 57.7% involved cytochrome P450 enzymes, which are involved in metabolism. 

• Reconciliation revealed that 35.2% of medications were not otherwise known or documented.

• A median of 2 previously unknown therapies per patient was discovered in 74% of patients.

• Alternative medicine products such as supplements and over-the-counter drugs were implicated in 60% of identified drug interactions.

• Only 41% of oncologists discussed alternative medicine use with patients, which Hennes attributed to “lack of familiarity with many alternative medicine products or insufficient training.”

To make things more complicated, “We sometimes don’t know the full pharmacokinetic and pharmacodynamic profile of an investigational agent,” she said. 

Naming and Labeling May Not Be Standard

Investigational products may not have genetic names and instead have an alphanumeric identifier such as INV54826 that can be quite similar to other products, she said. Investigational drugs may even go through name changes, forcing pharmacists to be alerted to protect patients. 

In addition, labeling may not be standardized. Drugs may arrive unlabeled, with the wrong volume and size, and lack of barcoding. In some cases, pharmacists choose to put new, patient-friendly labels on these products, Hennes said. 

Information Distribution is Key

“Something that comes up in our practice quite a bit is that there’s no standard drug reference regarding investigational drugs,” Hennes said. “Finding ways to get key information to staff at the point of care is really critical to make sure we’re able to safely treat our patients.”

Precautions May Be Needed to Maintain Blinding Protocols 

Hennes explained that pharmacists must use opaque brown bag covers to maintain blinding when parenteral products have distinctive colors. Lines may have to be covered too, which can create challenges during administration. 

“Pumps aren’t meant to run lines that are covered,” she said, which can lead to jams. “If you don’t do education with your point of care staff, it can cause a lot of confusion.” 

It’s also important for blinding purposes to keep an eye on how long it takes to prepare a treatment, she said. A study’s integrity, for example, could be violated if a complex investigational product takes an hour to equilibrate to room temperature and 20-30 minutes to prepare, while a placebo only requires “drawing a few mils of saline out of a bag and labeling it.”

Education for Patients Can Be Useful 

Hennes urged colleagues to remind patients to save investigational medication at the end of each cycle and return it to the clinic site for accountability.

She also suggested creating treatment calendars/reminders for patients and discussing adherence strategies with them. 

Hennes reported no disclosures. 

PHOENIX – Medications used in oncology clinical trials pose unique challenges in areas such as labeling, packaging, and administration, a US Department of Veterans Affairs (VA) pharmacist cautioned colleagues, and placebos have special needs too.

Even basic safety protections can be lacking when a drug is investigational, said Emily Hennes, PharmD, BCOP, clinical pharmacy specialist for research at William S. Middleton Memorial Veterans Hospital in Shorewood Hills, Wisconsin, in a presentation at the annual meeting of the Association of VA Hematology/Oncology.

“All of the safety features that we have come to know and love in dispensing commercial drugs are absent. There’s no Tall Man lettering, there's no color differentiation, and there's no barcoding, because these are not registered drugs," she said.

A 2017 report found that 81% of pharmacists surveyed indicated some level of concern regarding the safety risk in using  investigational drugs. At the same time, Hennes noted, the Joint Commission has mandated that pharmacists must control the storage, dispensing, labeling, and distribution of investigational medications.

Here are things to know about the use of investigational cancer drugs:

Drug Interactions Are Common

Hennes highlighted a 2023 study of medication reconciliation of 501 patients in 79 clinical trials that found alarming levels of drug interactions: 

• 360 clinically relevant drug-drug interactions were identified among 189 patients, including 158 therapies that were prohibited by protocols. Of these, 57.7% involved cytochrome P450 enzymes, which are involved in metabolism. 

• Reconciliation revealed that 35.2% of medications were not otherwise known or documented.

• A median of 2 previously unknown therapies per patient was discovered in 74% of patients.

• Alternative medicine products such as supplements and over-the-counter drugs were implicated in 60% of identified drug interactions.

• Only 41% of oncologists discussed alternative medicine use with patients, which Hennes attributed to “lack of familiarity with many alternative medicine products or insufficient training.”

To make things more complicated, “We sometimes don’t know the full pharmacokinetic and pharmacodynamic profile of an investigational agent,” she said. 

Naming and Labeling May Not Be Standard

Investigational products may not have genetic names and instead have an alphanumeric identifier such as INV54826 that can be quite similar to other products, she said. Investigational drugs may even go through name changes, forcing pharmacists to be alerted to protect patients. 

In addition, labeling may not be standardized. Drugs may arrive unlabeled, with the wrong volume and size, and lack of barcoding. In some cases, pharmacists choose to put new, patient-friendly labels on these products, Hennes said. 

Information Distribution is Key

“Something that comes up in our practice quite a bit is that there’s no standard drug reference regarding investigational drugs,” Hennes said. “Finding ways to get key information to staff at the point of care is really critical to make sure we’re able to safely treat our patients.”

Precautions May Be Needed to Maintain Blinding Protocols 

Hennes explained that pharmacists must use opaque brown bag covers to maintain blinding when parenteral products have distinctive colors. Lines may have to be covered too, which can create challenges during administration. 

“Pumps aren’t meant to run lines that are covered,” she said, which can lead to jams. “If you don’t do education with your point of care staff, it can cause a lot of confusion.” 

It’s also important for blinding purposes to keep an eye on how long it takes to prepare a treatment, she said. A study’s integrity, for example, could be violated if a complex investigational product takes an hour to equilibrate to room temperature and 20-30 minutes to prepare, while a placebo only requires “drawing a few mils of saline out of a bag and labeling it.”

Education for Patients Can Be Useful 

Hennes urged colleagues to remind patients to save investigational medication at the end of each cycle and return it to the clinic site for accountability.

She also suggested creating treatment calendars/reminders for patients and discussing adherence strategies with them. 

Hennes reported no disclosures. 

PHOENIX – Medications used in oncology clinical trials pose unique challenges in areas such as labeling, packaging, and administration, a US Department of Veterans Affairs (VA) pharmacist cautioned colleagues, and placebos have special needs too.

Even basic safety protections can be lacking when a drug is investigational, said Emily Hennes, PharmD, BCOP, clinical pharmacy specialist for research at William S. Middleton Memorial Veterans Hospital in Shorewood Hills, Wisconsin, in a presentation at the annual meeting of the Association of VA Hematology/Oncology.

“All of the safety features that we have come to know and love in dispensing commercial drugs are absent. There’s no Tall Man lettering, there's no color differentiation, and there's no barcoding, because these are not registered drugs," she said.

A 2017 report found that 81% of pharmacists surveyed indicated some level of concern regarding the safety risk in using  investigational drugs. At the same time, Hennes noted, the Joint Commission has mandated that pharmacists must control the storage, dispensing, labeling, and distribution of investigational medications.

Here are things to know about the use of investigational cancer drugs:

Drug Interactions Are Common

Hennes highlighted a 2023 study of medication reconciliation of 501 patients in 79 clinical trials that found alarming levels of drug interactions: 

• 360 clinically relevant drug-drug interactions were identified among 189 patients, including 158 therapies that were prohibited by protocols. Of these, 57.7% involved cytochrome P450 enzymes, which are involved in metabolism. 

• Reconciliation revealed that 35.2% of medications were not otherwise known or documented.

• A median of 2 previously unknown therapies per patient was discovered in 74% of patients.

• Alternative medicine products such as supplements and over-the-counter drugs were implicated in 60% of identified drug interactions.

• Only 41% of oncologists discussed alternative medicine use with patients, which Hennes attributed to “lack of familiarity with many alternative medicine products or insufficient training.”

To make things more complicated, “We sometimes don’t know the full pharmacokinetic and pharmacodynamic profile of an investigational agent,” she said. 

Naming and Labeling May Not Be Standard

Investigational products may not have genetic names and instead have an alphanumeric identifier such as INV54826 that can be quite similar to other products, she said. Investigational drugs may even go through name changes, forcing pharmacists to be alerted to protect patients. 

In addition, labeling may not be standardized. Drugs may arrive unlabeled, with the wrong volume and size, and lack of barcoding. In some cases, pharmacists choose to put new, patient-friendly labels on these products, Hennes said. 

Information Distribution is Key

“Something that comes up in our practice quite a bit is that there’s no standard drug reference regarding investigational drugs,” Hennes said. “Finding ways to get key information to staff at the point of care is really critical to make sure we’re able to safely treat our patients.”

Precautions May Be Needed to Maintain Blinding Protocols 

Hennes explained that pharmacists must use opaque brown bag covers to maintain blinding when parenteral products have distinctive colors. Lines may have to be covered too, which can create challenges during administration. 

“Pumps aren’t meant to run lines that are covered,” she said, which can lead to jams. “If you don’t do education with your point of care staff, it can cause a lot of confusion.” 

It’s also important for blinding purposes to keep an eye on how long it takes to prepare a treatment, she said. A study’s integrity, for example, could be violated if a complex investigational product takes an hour to equilibrate to room temperature and 20-30 minutes to prepare, while a placebo only requires “drawing a few mils of saline out of a bag and labeling it.”

Education for Patients Can Be Useful 

Hennes urged colleagues to remind patients to save investigational medication at the end of each cycle and return it to the clinic site for accountability.

She also suggested creating treatment calendars/reminders for patients and discussing adherence strategies with them. 

Hennes reported no disclosures. 

TOPLINE:

High-risk medications defined by the National Comprehensive Cancer Network (NCCN) and captured by the Geriatric Oncology Potentially Inappropriate Medication (GO-PIM) scale were prevalent in > one-third of veterans with solid and hematologic malignancies. Each additional GO-PIM was independently associated with higher risks for frailty at diagnosis, unplanned hospitalizations during follow-up, and death.

METHODOLOGY:

• Patients with cancer often use multiple chronic medications, raising risks for adverse events. Although several tools that identify PIMs have been developed that correlate with adverse cancer outcomes, their use is limited in busy oncology clinics. To improve implementation, researchers developed the GO-PIM scale using the NCCN’s list of high-risk medications.
• Researchers conducted a retrospective cohort study using data from the national Veterans Affairs Cancer Registry and electronic health records, which included 388,113 veterans newly diagnosed with solid or hematologic malignancies (median age, 69.3 years; 97.9% men; 76.1% non-Hispanic White and 17.3% Black individuals) between 2000 and 2022.
• They identified GO-PIMs using outpatient pharmacy records in the 90 days preceding cancer diagnosis. Each prescription for a specific GO-PIM was counted as one, including both individual drugs and drug classes listed in the GO-PIM scale.
• Study outcomes were frailty, hospitalizations, and overall survival. Baseline frailty at diagnosis was measured using the Veterans Affairs Frailty Index. The score ranged from 0 to 1, and higher scores indicated greater frailty. Patients were classified as nonfrail (score, ≤ 0.2), mildly frail (score, > 0.2 to 0.3), or moderate-to-severely frail (score, > 0.3).
• Lung (23.7%), prostate (21.5%), and gastrointestinal (20.5%) cancers were the most common, and the most frequent stages were IV (25.4%) and II (24.4%).

TAKEAWAY:

• Overall, 38.0% of veterans were prescribed ≥ 1 GO-PIMs at the time of cancer diagnosis, and the proportion increased to 56.1% among those with moderate-to-severe frailty.
• The most commonly prescribed classes of PIMs were selective serotonin reuptake inhibitors (SSRIs; 12.0%), opioids (10.4%), benzodiazepines (9.2%), and corticosteroids (9.2%). Among individual drugs, sertraline was the most common SSRI (4.3%), tramadol the most common opioid (5.3%), lorazepam the most common benzodiazepine (2.5%), and prednisone the most common corticosteroid (4.9%). Trends over time showed a steady increase in opioid prescriptions, peaking in 2014, followed by a subsequent decline, while prescriptions of benzodiazepines declined during the later years.
• After adjusting for age, cancer type and stage, and other covariates, each additional GO-PIM was associated with a 66% higher odds of mild or moderate-to-severe frailty at diagnosis (adjusted odds ratio, 1.66).
• After adjusting for frailty and covariates, each additional GO-PIM at diagnosis was associated with increased risks for unplanned hospitalizations and death (adjusted hazard ratios, 1.08 and 1.07, respectively). These associations remained stable in sensitivity analyses that restricted GO-PIMs to scheduled medications only, focused on patients who had initiated cancer treatment, and included only those aged ≥ 65 years.

IN PRACTICE:

“Whether prescribed for supportive oncology care or for coexisting medical conditions, high-risk medications identified as PIMs should be reviewed and optimized in patients with cancer,” the authors of the study wrote.

“GO-PIMs offers a streamlined, oncology-specific approach to identifying high-risk prescribing, and complements existing efforts to improve supportive care, especially for older, frail patients,” remarked Mostafa R. Mohamed, MBBCH, PhD, MSc, and Erika E. Ramsdale, MD, University of Rochester Medical Center, Rochester, New York in an invited commentary. “The next step lies in integrating tools such as GO-PIMs into everyday practice not only to flag high risk medications but also to support actionable changes in treatment planning and patient management, such as deprescribing,” they concluded.

SOURCE:

This study, led by Jennifer La, PhD, Harvard Medical School, Boston, was published online in Journal of the National Comprehensive Cancer Network.

LIMITATIONS:

Prescription chronicity before or after follow-up was not measured and actual medication adherence could not be confirmed. Residual confounding by comorbidity could have existed, and the cross-sectional nature of linking GO-PIMs with frailty might have limited causal inference. Additionally, prescriptions were measured within Veterans Affairs pharmacy data, potentially underestimating GO-PIM prevalence, and the predominantly male population limited generalizability to gynecologic cancers.

DISCLOSURES:

This study was supported by grants and rewards from the Veterans Affairs Office of Research and Development, Cooperative Studies Program, National Institutes of Health, and American Heart Association. Some authors declared serving as consultants or receiving grants and having other ties with various sources. Additional disclosures are noted in the original article.

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

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

TOPLINE:

High-risk medications defined by the National Comprehensive Cancer Network (NCCN) and captured by the Geriatric Oncology Potentially Inappropriate Medication (GO-PIM) scale were prevalent in > one-third of veterans with solid and hematologic malignancies. Each additional GO-PIM was independently associated with higher risks for frailty at diagnosis, unplanned hospitalizations during follow-up, and death.

METHODOLOGY:

• Patients with cancer often use multiple chronic medications, raising risks for adverse events. Although several tools that identify PIMs have been developed that correlate with adverse cancer outcomes, their use is limited in busy oncology clinics. To improve implementation, researchers developed the GO-PIM scale using the NCCN’s list of high-risk medications.
• Researchers conducted a retrospective cohort study using data from the national Veterans Affairs Cancer Registry and electronic health records, which included 388,113 veterans newly diagnosed with solid or hematologic malignancies (median age, 69.3 years; 97.9% men; 76.1% non-Hispanic White and 17.3% Black individuals) between 2000 and 2022.
• They identified GO-PIMs using outpatient pharmacy records in the 90 days preceding cancer diagnosis. Each prescription for a specific GO-PIM was counted as one, including both individual drugs and drug classes listed in the GO-PIM scale.
• Study outcomes were frailty, hospitalizations, and overall survival. Baseline frailty at diagnosis was measured using the Veterans Affairs Frailty Index. The score ranged from 0 to 1, and higher scores indicated greater frailty. Patients were classified as nonfrail (score, ≤ 0.2), mildly frail (score, > 0.2 to 0.3), or moderate-to-severely frail (score, > 0.3).
• Lung (23.7%), prostate (21.5%), and gastrointestinal (20.5%) cancers were the most common, and the most frequent stages were IV (25.4%) and II (24.4%).

TAKEAWAY:

• Overall, 38.0% of veterans were prescribed ≥ 1 GO-PIMs at the time of cancer diagnosis, and the proportion increased to 56.1% among those with moderate-to-severe frailty.
• The most commonly prescribed classes of PIMs were selective serotonin reuptake inhibitors (SSRIs; 12.0%), opioids (10.4%), benzodiazepines (9.2%), and corticosteroids (9.2%). Among individual drugs, sertraline was the most common SSRI (4.3%), tramadol the most common opioid (5.3%), lorazepam the most common benzodiazepine (2.5%), and prednisone the most common corticosteroid (4.9%). Trends over time showed a steady increase in opioid prescriptions, peaking in 2014, followed by a subsequent decline, while prescriptions of benzodiazepines declined during the later years.
• After adjusting for age, cancer type and stage, and other covariates, each additional GO-PIM was associated with a 66% higher odds of mild or moderate-to-severe frailty at diagnosis (adjusted odds ratio, 1.66).
• After adjusting for frailty and covariates, each additional GO-PIM at diagnosis was associated with increased risks for unplanned hospitalizations and death (adjusted hazard ratios, 1.08 and 1.07, respectively). These associations remained stable in sensitivity analyses that restricted GO-PIMs to scheduled medications only, focused on patients who had initiated cancer treatment, and included only those aged ≥ 65 years.

IN PRACTICE:

“Whether prescribed for supportive oncology care or for coexisting medical conditions, high-risk medications identified as PIMs should be reviewed and optimized in patients with cancer,” the authors of the study wrote.

“GO-PIMs offers a streamlined, oncology-specific approach to identifying high-risk prescribing, and complements existing efforts to improve supportive care, especially for older, frail patients,” remarked Mostafa R. Mohamed, MBBCH, PhD, MSc, and Erika E. Ramsdale, MD, University of Rochester Medical Center, Rochester, New York in an invited commentary. “The next step lies in integrating tools such as GO-PIMs into everyday practice not only to flag high risk medications but also to support actionable changes in treatment planning and patient management, such as deprescribing,” they concluded.

SOURCE:

This study, led by Jennifer La, PhD, Harvard Medical School, Boston, was published online in Journal of the National Comprehensive Cancer Network.

LIMITATIONS:

Prescription chronicity before or after follow-up was not measured and actual medication adherence could not be confirmed. Residual confounding by comorbidity could have existed, and the cross-sectional nature of linking GO-PIMs with frailty might have limited causal inference. Additionally, prescriptions were measured within Veterans Affairs pharmacy data, potentially underestimating GO-PIM prevalence, and the predominantly male population limited generalizability to gynecologic cancers.

DISCLOSURES:

This study was supported by grants and rewards from the Veterans Affairs Office of Research and Development, Cooperative Studies Program, National Institutes of Health, and American Heart Association. Some authors declared serving as consultants or receiving grants and having other ties with various sources. Additional disclosures are noted in the original article.

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

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

TOPLINE:

High-risk medications defined by the National Comprehensive Cancer Network (NCCN) and captured by the Geriatric Oncology Potentially Inappropriate Medication (GO-PIM) scale were prevalent in > one-third of veterans with solid and hematologic malignancies. Each additional GO-PIM was independently associated with higher risks for frailty at diagnosis, unplanned hospitalizations during follow-up, and death.

METHODOLOGY:

• Patients with cancer often use multiple chronic medications, raising risks for adverse events. Although several tools that identify PIMs have been developed that correlate with adverse cancer outcomes, their use is limited in busy oncology clinics. To improve implementation, researchers developed the GO-PIM scale using the NCCN’s list of high-risk medications.
• Researchers conducted a retrospective cohort study using data from the national Veterans Affairs Cancer Registry and electronic health records, which included 388,113 veterans newly diagnosed with solid or hematologic malignancies (median age, 69.3 years; 97.9% men; 76.1% non-Hispanic White and 17.3% Black individuals) between 2000 and 2022.
• They identified GO-PIMs using outpatient pharmacy records in the 90 days preceding cancer diagnosis. Each prescription for a specific GO-PIM was counted as one, including both individual drugs and drug classes listed in the GO-PIM scale.
• Study outcomes were frailty, hospitalizations, and overall survival. Baseline frailty at diagnosis was measured using the Veterans Affairs Frailty Index. The score ranged from 0 to 1, and higher scores indicated greater frailty. Patients were classified as nonfrail (score, ≤ 0.2), mildly frail (score, > 0.2 to 0.3), or moderate-to-severely frail (score, > 0.3).
• Lung (23.7%), prostate (21.5%), and gastrointestinal (20.5%) cancers were the most common, and the most frequent stages were IV (25.4%) and II (24.4%).

TAKEAWAY:

• Overall, 38.0% of veterans were prescribed ≥ 1 GO-PIMs at the time of cancer diagnosis, and the proportion increased to 56.1% among those with moderate-to-severe frailty.
• The most commonly prescribed classes of PIMs were selective serotonin reuptake inhibitors (SSRIs; 12.0%), opioids (10.4%), benzodiazepines (9.2%), and corticosteroids (9.2%). Among individual drugs, sertraline was the most common SSRI (4.3%), tramadol the most common opioid (5.3%), lorazepam the most common benzodiazepine (2.5%), and prednisone the most common corticosteroid (4.9%). Trends over time showed a steady increase in opioid prescriptions, peaking in 2014, followed by a subsequent decline, while prescriptions of benzodiazepines declined during the later years.
• After adjusting for age, cancer type and stage, and other covariates, each additional GO-PIM was associated with a 66% higher odds of mild or moderate-to-severe frailty at diagnosis (adjusted odds ratio, 1.66).
• After adjusting for frailty and covariates, each additional GO-PIM at diagnosis was associated with increased risks for unplanned hospitalizations and death (adjusted hazard ratios, 1.08 and 1.07, respectively). These associations remained stable in sensitivity analyses that restricted GO-PIMs to scheduled medications only, focused on patients who had initiated cancer treatment, and included only those aged ≥ 65 years.

IN PRACTICE:

“Whether prescribed for supportive oncology care or for coexisting medical conditions, high-risk medications identified as PIMs should be reviewed and optimized in patients with cancer,” the authors of the study wrote.

“GO-PIMs offers a streamlined, oncology-specific approach to identifying high-risk prescribing, and complements existing efforts to improve supportive care, especially for older, frail patients,” remarked Mostafa R. Mohamed, MBBCH, PhD, MSc, and Erika E. Ramsdale, MD, University of Rochester Medical Center, Rochester, New York in an invited commentary. “The next step lies in integrating tools such as GO-PIMs into everyday practice not only to flag high risk medications but also to support actionable changes in treatment planning and patient management, such as deprescribing,” they concluded.

SOURCE:

This study, led by Jennifer La, PhD, Harvard Medical School, Boston, was published online in Journal of the National Comprehensive Cancer Network.

LIMITATIONS:

Prescription chronicity before or after follow-up was not measured and actual medication adherence could not be confirmed. Residual confounding by comorbidity could have existed, and the cross-sectional nature of linking GO-PIMs with frailty might have limited causal inference. Additionally, prescriptions were measured within Veterans Affairs pharmacy data, potentially underestimating GO-PIM prevalence, and the predominantly male population limited generalizability to gynecologic cancers.

DISCLOSURES:

This study was supported by grants and rewards from the Veterans Affairs Office of Research and Development, Cooperative Studies Program, National Institutes of Health, and American Heart Association. Some authors declared serving as consultants or receiving grants and having other ties with various sources. Additional disclosures are noted in the original article.

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

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

TOPLINE:

About 1 in 10 veterans with early-stage cancer developed new persistent opioid use after curative‐intent surgery, though < 1% were diagnosed with opioid use disorder.

METHODOLOGY:

Although effective pain control during cancer treatment is vital, prescribing opioids in this context may contribute to unsafe, long-term use and related adverse outcomes. Veterans, who have higher-than-average rates of mental health and substance use disorders, may be at particular risk for adverse events from opioid use related to cancer treatment.

Researchers conducted a national retrospective cohort study of 9213 US veterans (98% men) with stage 0-III cancer who were opioid-naive and underwent curative-intent surgery at Veterans Affairs medical centers between 2015 and 2016. Prostate (n = 2594; 28%), colorectal (n = 2393; 26%), bladder (n = 2302; 25%), and lung (n = 1252; 14%) cancers were the most common.

Primary outcomes were the number of days of co-prescription of benzodiazepines and opioids (an indicator of unsafe opioid prescribing) and new persistent opioid use, defined as receiving ≥ 1 opioid prescription at 90-180 days postsurgery. Opioid‐related adverse effects, including opioid use disorder and opioid overdose, were also reported.

Overall, 6970 (76%) of the participants were prescribed opioids at some point during the baseline treatment period (30 days before through 14 days after surgery). The mean morphine milligram equivalent (MME) was 172.5.

 

TAKEAWAY:

Overall, 4% of patients received co-prescriptions of benzodiazepines and opioids. The mean number of days of coprescription rose in tandem with opioid doses during the treatment period: from 0.48 days in the lowest MME quartile to 2.1 days in the highest quartile (P < .0001).

Over 1 in 10 patients (10.6%) developed new persistent opioid use. Those in the highest MME quartile had a 1.6-fold greater risk of developing new persistent opioid use than those with no opioid exposure during the treatment period (hazard ratio [HR], 1.6; P < .001). The percentage of patients with opioid prescriptions did decline over the 13-month follow-up, but among those who continued on opioids, the daily MME remained stable (median, 20 for month 1 and 30 for month 12).

Treatment with adjuvant chemotherapy increased the risk for new persistent opioid use (HR, 1.5; 95% CI, 1.2-1.8; P < .001). Additional risk factors included having bladder, colorectal, lung, or other types of cancer (vs prostate cancer); stage I-III disease (vs stage 0); age 45-64 years (vs older); lower socioeconomic status; preoperative use of nonopioid pain medication; and a baseline history of anxiety, depression, or posttraumatic stress disorder.

Over 13 months, 72 patients (0.78%) developed opioid use disorder, 3 (0.03%) experienced nonoverdose adverse events, and no opioid overdose occurred.

 

IN PRACTICE:

“Although a cancer diagnosis, treatment, and associated pain syndromes will require specific pain management strategies,” the authors wrote, “efforts should be taken to mitigate long‐term opioid use and its potential adverse effects in this population. They added that “both system‐level changes that involve preoperative evaluation planning as well as increased knowledge, awareness, and education among providers and patients about the risk of long‐term opioid use can guide strategies for effective and safe pain management.”

SOURCE:

The study, led by Marilyn M. Schapira, MD, MPH, Center for Healthcare Evaluation, Research, and Promotion, Corporal Michael J. Crescenz Veterans Affairs Medical Center, Philadelphia, was published online in Cancer.

LIMITATIONS:

Opioid prescriptions outside the Veterans Affairs system were not captured. The study was based on filled opioid prescriptions, and actual patient consumption was unknown. Outpatient methadone prescriptions were not included. The study also excluded patients with breast cancer, limiting generalizability.

DISCLOSURES:

The study was funded by grant from the Department of Veterans Affairs. One author reported consulting for Moderna and TriNetX. Another author reported consulting for Genetic Chemistry, Thyme Care, Biofourmis, Onc.Al, Credit Suisse, Main Street Health, ConcertAI, Medscape, and G1 Therapeutics. The other authors declared having no conflicts of interest.

This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication. A version of this article first appeared on Medscape.com.

TOPLINE:

About 1 in 10 veterans with early-stage cancer developed new persistent opioid use after curative‐intent surgery, though < 1% were diagnosed with opioid use disorder.

METHODOLOGY:

Although effective pain control during cancer treatment is vital, prescribing opioids in this context may contribute to unsafe, long-term use and related adverse outcomes. Veterans, who have higher-than-average rates of mental health and substance use disorders, may be at particular risk for adverse events from opioid use related to cancer treatment.

Researchers conducted a national retrospective cohort study of 9213 US veterans (98% men) with stage 0-III cancer who were opioid-naive and underwent curative-intent surgery at Veterans Affairs medical centers between 2015 and 2016. Prostate (n = 2594; 28%), colorectal (n = 2393; 26%), bladder (n = 2302; 25%), and lung (n = 1252; 14%) cancers were the most common.

Primary outcomes were the number of days of co-prescription of benzodiazepines and opioids (an indicator of unsafe opioid prescribing) and new persistent opioid use, defined as receiving ≥ 1 opioid prescription at 90-180 days postsurgery. Opioid‐related adverse effects, including opioid use disorder and opioid overdose, were also reported.

Overall, 6970 (76%) of the participants were prescribed opioids at some point during the baseline treatment period (30 days before through 14 days after surgery). The mean morphine milligram equivalent (MME) was 172.5.

 

TAKEAWAY:

Overall, 4% of patients received co-prescriptions of benzodiazepines and opioids. The mean number of days of coprescription rose in tandem with opioid doses during the treatment period: from 0.48 days in the lowest MME quartile to 2.1 days in the highest quartile (P < .0001).

Over 1 in 10 patients (10.6%) developed new persistent opioid use. Those in the highest MME quartile had a 1.6-fold greater risk of developing new persistent opioid use than those with no opioid exposure during the treatment period (hazard ratio [HR], 1.6; P < .001). The percentage of patients with opioid prescriptions did decline over the 13-month follow-up, but among those who continued on opioids, the daily MME remained stable (median, 20 for month 1 and 30 for month 12).

Treatment with adjuvant chemotherapy increased the risk for new persistent opioid use (HR, 1.5; 95% CI, 1.2-1.8; P < .001). Additional risk factors included having bladder, colorectal, lung, or other types of cancer (vs prostate cancer); stage I-III disease (vs stage 0); age 45-64 years (vs older); lower socioeconomic status; preoperative use of nonopioid pain medication; and a baseline history of anxiety, depression, or posttraumatic stress disorder.

Over 13 months, 72 patients (0.78%) developed opioid use disorder, 3 (0.03%) experienced nonoverdose adverse events, and no opioid overdose occurred.

 

IN PRACTICE:

“Although a cancer diagnosis, treatment, and associated pain syndromes will require specific pain management strategies,” the authors wrote, “efforts should be taken to mitigate long‐term opioid use and its potential adverse effects in this population. They added that “both system‐level changes that involve preoperative evaluation planning as well as increased knowledge, awareness, and education among providers and patients about the risk of long‐term opioid use can guide strategies for effective and safe pain management.”

SOURCE:

The study, led by Marilyn M. Schapira, MD, MPH, Center for Healthcare Evaluation, Research, and Promotion, Corporal Michael J. Crescenz Veterans Affairs Medical Center, Philadelphia, was published online in Cancer.

LIMITATIONS:

Opioid prescriptions outside the Veterans Affairs system were not captured. The study was based on filled opioid prescriptions, and actual patient consumption was unknown. Outpatient methadone prescriptions were not included. The study also excluded patients with breast cancer, limiting generalizability.

DISCLOSURES:

The study was funded by grant from the Department of Veterans Affairs. One author reported consulting for Moderna and TriNetX. Another author reported consulting for Genetic Chemistry, Thyme Care, Biofourmis, Onc.Al, Credit Suisse, Main Street Health, ConcertAI, Medscape, and G1 Therapeutics. The other authors declared having no conflicts of interest.

This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication. A version of this article first appeared on Medscape.com.

TOPLINE:

About 1 in 10 veterans with early-stage cancer developed new persistent opioid use after curative‐intent surgery, though < 1% were diagnosed with opioid use disorder.

METHODOLOGY:

Although effective pain control during cancer treatment is vital, prescribing opioids in this context may contribute to unsafe, long-term use and related adverse outcomes. Veterans, who have higher-than-average rates of mental health and substance use disorders, may be at particular risk for adverse events from opioid use related to cancer treatment.

Researchers conducted a national retrospective cohort study of 9213 US veterans (98% men) with stage 0-III cancer who were opioid-naive and underwent curative-intent surgery at Veterans Affairs medical centers between 2015 and 2016. Prostate (n = 2594; 28%), colorectal (n = 2393; 26%), bladder (n = 2302; 25%), and lung (n = 1252; 14%) cancers were the most common.

Primary outcomes were the number of days of co-prescription of benzodiazepines and opioids (an indicator of unsafe opioid prescribing) and new persistent opioid use, defined as receiving ≥ 1 opioid prescription at 90-180 days postsurgery. Opioid‐related adverse effects, including opioid use disorder and opioid overdose, were also reported.

Overall, 6970 (76%) of the participants were prescribed opioids at some point during the baseline treatment period (30 days before through 14 days after surgery). The mean morphine milligram equivalent (MME) was 172.5.

 

TAKEAWAY:

Overall, 4% of patients received co-prescriptions of benzodiazepines and opioids. The mean number of days of coprescription rose in tandem with opioid doses during the treatment period: from 0.48 days in the lowest MME quartile to 2.1 days in the highest quartile (P < .0001).

Over 1 in 10 patients (10.6%) developed new persistent opioid use. Those in the highest MME quartile had a 1.6-fold greater risk of developing new persistent opioid use than those with no opioid exposure during the treatment period (hazard ratio [HR], 1.6; P < .001). The percentage of patients with opioid prescriptions did decline over the 13-month follow-up, but among those who continued on opioids, the daily MME remained stable (median, 20 for month 1 and 30 for month 12).

Treatment with adjuvant chemotherapy increased the risk for new persistent opioid use (HR, 1.5; 95% CI, 1.2-1.8; P < .001). Additional risk factors included having bladder, colorectal, lung, or other types of cancer (vs prostate cancer); stage I-III disease (vs stage 0); age 45-64 years (vs older); lower socioeconomic status; preoperative use of nonopioid pain medication; and a baseline history of anxiety, depression, or posttraumatic stress disorder.

Over 13 months, 72 patients (0.78%) developed opioid use disorder, 3 (0.03%) experienced nonoverdose adverse events, and no opioid overdose occurred.

 

IN PRACTICE:

“Although a cancer diagnosis, treatment, and associated pain syndromes will require specific pain management strategies,” the authors wrote, “efforts should be taken to mitigate long‐term opioid use and its potential adverse effects in this population. They added that “both system‐level changes that involve preoperative evaluation planning as well as increased knowledge, awareness, and education among providers and patients about the risk of long‐term opioid use can guide strategies for effective and safe pain management.”

SOURCE:

The study, led by Marilyn M. Schapira, MD, MPH, Center for Healthcare Evaluation, Research, and Promotion, Corporal Michael J. Crescenz Veterans Affairs Medical Center, Philadelphia, was published online in Cancer.

LIMITATIONS:

Opioid prescriptions outside the Veterans Affairs system were not captured. The study was based on filled opioid prescriptions, and actual patient consumption was unknown. Outpatient methadone prescriptions were not included. The study also excluded patients with breast cancer, limiting generalizability.

DISCLOSURES:

The study was funded by grant from the Department of Veterans Affairs. One author reported consulting for Moderna and TriNetX. Another author reported consulting for Genetic Chemistry, Thyme Care, Biofourmis, Onc.Al, Credit Suisse, Main Street Health, ConcertAI, Medscape, and G1 Therapeutics. The other authors declared having no conflicts of interest.

This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication. A version of this article first appeared on Medscape.com.

TOPLINE:

The incidence of skin cancer in England varied by ethnicity: White individuals had higher rates of melanoma, cutaneous squamous cell carcinoma, and basal cell carcinoma than Asian or Black individuals. In contrast, acral lentiginous melanoma was most common among Black individuals, whereas cutaneous T-cell lymphoma and Kaposi sarcoma were highest among those in the "Other" ethnic group.

METHODOLOGY:

• Researchers analysed all cases of cutaneous melanoma (melanoma and acral lentiginous melanoma), basal cell carcinoma, cutaneous squamous cell carcinoma, cutaneous T-cell lymphoma, and Kaposi sarcoma using data from the NHS National Disease Registration Service cancer registry between 2013 and 2020.
• Data collection incorporated ethnicity information from multiple health care datasets, including Clinical Outcomes and Services Dataset, Patient Administration System, Radiotherapy Dataset, Diagnostic Imaging Dataset, and Hospital Episode Statistics.
• A population analysis categorised patients into 7 standardised ethnic groups (on the basis of Office for National Statistics classifications): White, Asian, Chinese, Black, mixed, other, and unknown groups, with ethnicity data being self-reported by patients.
• Outcomes included European age-standardised rates calculated using the 2013 European Standard Population and reported per 100,000 person-years (PYs).

TAKEAWAY:

• White Individuals had 13-fold higher rates of cutaneous squamous cell carcinoma (61.75 per 100,000 PYs), 26-fold and 27-fold higher rates of basal cell carcinoma (153.69 per 100,000 PYs), and 33-fold and 16-fold higher rates of cutaneous melanoma (27.29 per 100,000 PYs) than Asian and Black individuals, respectively.
• Black individuals had the highest incidence of acral lentiginous melanoma (0.85 per 100,000 PYs), and those in the other ethnic group had the highest incidence of cutaneous T-cell lymphoma (1.74 per 100,000 PYs) and Kaposi sarcoma (1.57 per 100,000 PYs).
• The presentation of early-stage melanoma was low among Asian (53.5%), Black (62.4%), mixed (62.5%), and other (76.4%) ethnic groups compared to that among White ethnicities (79.8%).
• Acral lentiginous melanomas were less likely to get urgent suspected cancer pathway referrals than overall melanoma (40.1% vs 44.6%; P < .001) and more likely to be diagnosed late than overall melanoma (stage I/II at diagnosis; 72% vs 80%; P < .0001).

IN PRACTICE:

"The findings emphasise the need for better, targeted ethnicity data collection strategies to address incidence, outcomes and health care equity for not just skin cancer but all health conditions in underserved populations," the authors wrote. "While projects like the Global Burden of Disease have improved global health care reporting, continuous audit and improvement of collected data are essential to provide better care across people of all ethnicities."

SOURCE:

This study was led by Shehnaz Ahmed, British Association of Dermatologists, London, England. It was published online on September 10, 2025, in the British Journal of Dermatology.

LIMITATIONS:

Census data collection after every 10 years could have contributed to inaccurate population estimates and incidence rates. Small sample sizes in certain ethnic groups could have led to potential confounders, requiring a cautious interpretation of relative incidence. The NHS data included only self-reported ethnicity data with no available details of skin phototypes, skin tones, or racial ancestry. This study lacked granular ethnicity census data and stage data for basal cell carcinoma, cutaneous small cell carcinoma, and Kaposi sarcoma.

DISCLOSURES:

This research was supported through a partnership between the British Association of Dermatologists and NHS England's National Disease Registration Service. Two authors reported being employees of the British Association of Dermatologists.

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

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

TOPLINE:

The incidence of skin cancer in England varied by ethnicity: White individuals had higher rates of melanoma, cutaneous squamous cell carcinoma, and basal cell carcinoma than Asian or Black individuals. In contrast, acral lentiginous melanoma was most common among Black individuals, whereas cutaneous T-cell lymphoma and Kaposi sarcoma were highest among those in the "Other" ethnic group.

METHODOLOGY:

• Researchers analysed all cases of cutaneous melanoma (melanoma and acral lentiginous melanoma), basal cell carcinoma, cutaneous squamous cell carcinoma, cutaneous T-cell lymphoma, and Kaposi sarcoma using data from the NHS National Disease Registration Service cancer registry between 2013 and 2020.
• Data collection incorporated ethnicity information from multiple health care datasets, including Clinical Outcomes and Services Dataset, Patient Administration System, Radiotherapy Dataset, Diagnostic Imaging Dataset, and Hospital Episode Statistics.
• A population analysis categorised patients into 7 standardised ethnic groups (on the basis of Office for National Statistics classifications): White, Asian, Chinese, Black, mixed, other, and unknown groups, with ethnicity data being self-reported by patients.
• Outcomes included European age-standardised rates calculated using the 2013 European Standard Population and reported per 100,000 person-years (PYs).

TAKEAWAY:

• White Individuals had 13-fold higher rates of cutaneous squamous cell carcinoma (61.75 per 100,000 PYs), 26-fold and 27-fold higher rates of basal cell carcinoma (153.69 per 100,000 PYs), and 33-fold and 16-fold higher rates of cutaneous melanoma (27.29 per 100,000 PYs) than Asian and Black individuals, respectively.
• Black individuals had the highest incidence of acral lentiginous melanoma (0.85 per 100,000 PYs), and those in the other ethnic group had the highest incidence of cutaneous T-cell lymphoma (1.74 per 100,000 PYs) and Kaposi sarcoma (1.57 per 100,000 PYs).
• The presentation of early-stage melanoma was low among Asian (53.5%), Black (62.4%), mixed (62.5%), and other (76.4%) ethnic groups compared to that among White ethnicities (79.8%).
• Acral lentiginous melanomas were less likely to get urgent suspected cancer pathway referrals than overall melanoma (40.1% vs 44.6%; P < .001) and more likely to be diagnosed late than overall melanoma (stage I/II at diagnosis; 72% vs 80%; P < .0001).

IN PRACTICE:

"The findings emphasise the need for better, targeted ethnicity data collection strategies to address incidence, outcomes and health care equity for not just skin cancer but all health conditions in underserved populations," the authors wrote. "While projects like the Global Burden of Disease have improved global health care reporting, continuous audit and improvement of collected data are essential to provide better care across people of all ethnicities."

SOURCE:

This study was led by Shehnaz Ahmed, British Association of Dermatologists, London, England. It was published online on September 10, 2025, in the British Journal of Dermatology.

LIMITATIONS:

Census data collection after every 10 years could have contributed to inaccurate population estimates and incidence rates. Small sample sizes in certain ethnic groups could have led to potential confounders, requiring a cautious interpretation of relative incidence. The NHS data included only self-reported ethnicity data with no available details of skin phototypes, skin tones, or racial ancestry. This study lacked granular ethnicity census data and stage data for basal cell carcinoma, cutaneous small cell carcinoma, and Kaposi sarcoma.

DISCLOSURES:

This research was supported through a partnership between the British Association of Dermatologists and NHS England's National Disease Registration Service. Two authors reported being employees of the British Association of Dermatologists.

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

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

TOPLINE:

The incidence of skin cancer in England varied by ethnicity: White individuals had higher rates of melanoma, cutaneous squamous cell carcinoma, and basal cell carcinoma than Asian or Black individuals. In contrast, acral lentiginous melanoma was most common among Black individuals, whereas cutaneous T-cell lymphoma and Kaposi sarcoma were highest among those in the "Other" ethnic group.

METHODOLOGY:

• Researchers analysed all cases of cutaneous melanoma (melanoma and acral lentiginous melanoma), basal cell carcinoma, cutaneous squamous cell carcinoma, cutaneous T-cell lymphoma, and Kaposi sarcoma using data from the NHS National Disease Registration Service cancer registry between 2013 and 2020.
• Data collection incorporated ethnicity information from multiple health care datasets, including Clinical Outcomes and Services Dataset, Patient Administration System, Radiotherapy Dataset, Diagnostic Imaging Dataset, and Hospital Episode Statistics.
• A population analysis categorised patients into 7 standardised ethnic groups (on the basis of Office for National Statistics classifications): White, Asian, Chinese, Black, mixed, other, and unknown groups, with ethnicity data being self-reported by patients.
• Outcomes included European age-standardised rates calculated using the 2013 European Standard Population and reported per 100,000 person-years (PYs).

TAKEAWAY:

• White Individuals had 13-fold higher rates of cutaneous squamous cell carcinoma (61.75 per 100,000 PYs), 26-fold and 27-fold higher rates of basal cell carcinoma (153.69 per 100,000 PYs), and 33-fold and 16-fold higher rates of cutaneous melanoma (27.29 per 100,000 PYs) than Asian and Black individuals, respectively.
• Black individuals had the highest incidence of acral lentiginous melanoma (0.85 per 100,000 PYs), and those in the other ethnic group had the highest incidence of cutaneous T-cell lymphoma (1.74 per 100,000 PYs) and Kaposi sarcoma (1.57 per 100,000 PYs).
• The presentation of early-stage melanoma was low among Asian (53.5%), Black (62.4%), mixed (62.5%), and other (76.4%) ethnic groups compared to that among White ethnicities (79.8%).
• Acral lentiginous melanomas were less likely to get urgent suspected cancer pathway referrals than overall melanoma (40.1% vs 44.6%; P < .001) and more likely to be diagnosed late than overall melanoma (stage I/II at diagnosis; 72% vs 80%; P < .0001).

IN PRACTICE:

"The findings emphasise the need for better, targeted ethnicity data collection strategies to address incidence, outcomes and health care equity for not just skin cancer but all health conditions in underserved populations," the authors wrote. "While projects like the Global Burden of Disease have improved global health care reporting, continuous audit and improvement of collected data are essential to provide better care across people of all ethnicities."

SOURCE:

This study was led by Shehnaz Ahmed, British Association of Dermatologists, London, England. It was published online on September 10, 2025, in the British Journal of Dermatology.

LIMITATIONS:

Census data collection after every 10 years could have contributed to inaccurate population estimates and incidence rates. Small sample sizes in certain ethnic groups could have led to potential confounders, requiring a cautious interpretation of relative incidence. The NHS data included only self-reported ethnicity data with no available details of skin phototypes, skin tones, or racial ancestry. This study lacked granular ethnicity census data and stage data for basal cell carcinoma, cutaneous small cell carcinoma, and Kaposi sarcoma.

DISCLOSURES:

This research was supported through a partnership between the British Association of Dermatologists and NHS England's National Disease Registration Service. Two authors reported being employees of the British Association of Dermatologists.

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

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

TOPLINE:

Compared with inactive patterns, weekend warrior (moderate-to-vigorous physical activity [MVPA] condensed into 1-2 days per week) and regular physical activity patterns were found to be equally effective at reducing the risk for lung cancer. Neither pattern showed significant associations with the overall risk for cancer or specific risks for prostate, breast, and colorectal cancers.

METHODOLOGY:

• This analysis included 80,896 participants (mean age, 55.5 years; 56% women) with valid accelerometer data collected between June 2013 and December 2015.
• Participants were classified into three groups: 32,213 active weekend warriors (≥ 150 minutes of weekly MVPA with ≥ 50% achieved in 1-2 days), 22,162 active regular participants (≥ 150 minutes of MVPA but not meeting a weekend warrior pattern), and 26,521 inactive participants (< 150 minutes of MVPA).
• Researchers tracked associations between physical activity patterns and incident cases of all types of cancer plus specific cases of prostate, breast, colorectal, and lung cancer over a median follow-up duration of 6 years.

TAKEAWAY:

• Compared with inactive patterns, active weekend warrior patterns showed a significant inverse association with the risk for lung cancer (hazard ratio [HR], 0.77; 95% CI, 0.61-0.98).
• Active regular activity patterns demonstrated similar protective effects against lung cancer as inactive patterns (HR, 0.73; 95% CI, 0.56-0.96).
• Neither of the physical activity patterns showed any significant association with the overall risk for cancer or specific risks for prostate, breast, and colorectal cancers.

IN PRACTICE:

"Physical activity condensed into one to two days per week compared with a more balanced weekly distribution was associated with similar risk reductions of incident lung cancer, while neither pattern was associated with reduced overall, prostate, breast, and colorectal cancers," the authors of the study wrote.

SOURCE:

This study was led by Rubén López-Bueno, Department of Physical Medicine and Nursing, University of Zaragoza, Zaragoza, Spain. It was published online on September 06, 2025, in Annals of Medicine.

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

TOPLINE:

Compared with inactive patterns, weekend warrior (moderate-to-vigorous physical activity [MVPA] condensed into 1-2 days per week) and regular physical activity patterns were found to be equally effective at reducing the risk for lung cancer. Neither pattern showed significant associations with the overall risk for cancer or specific risks for prostate, breast, and colorectal cancers.

METHODOLOGY:

• This analysis included 80,896 participants (mean age, 55.5 years; 56% women) with valid accelerometer data collected between June 2013 and December 2015.
• Participants were classified into three groups: 32,213 active weekend warriors (≥ 150 minutes of weekly MVPA with ≥ 50% achieved in 1-2 days), 22,162 active regular participants (≥ 150 minutes of MVPA but not meeting a weekend warrior pattern), and 26,521 inactive participants (< 150 minutes of MVPA).
• Researchers tracked associations between physical activity patterns and incident cases of all types of cancer plus specific cases of prostate, breast, colorectal, and lung cancer over a median follow-up duration of 6 years.

TAKEAWAY:

• Compared with inactive patterns, active weekend warrior patterns showed a significant inverse association with the risk for lung cancer (hazard ratio [HR], 0.77; 95% CI, 0.61-0.98).
• Active regular activity patterns demonstrated similar protective effects against lung cancer as inactive patterns (HR, 0.73; 95% CI, 0.56-0.96).
• Neither of the physical activity patterns showed any significant association with the overall risk for cancer or specific risks for prostate, breast, and colorectal cancers.

IN PRACTICE:

"Physical activity condensed into one to two days per week compared with a more balanced weekly distribution was associated with similar risk reductions of incident lung cancer, while neither pattern was associated with reduced overall, prostate, breast, and colorectal cancers," the authors of the study wrote.

SOURCE:

This study was led by Rubén López-Bueno, Department of Physical Medicine and Nursing, University of Zaragoza, Zaragoza, Spain. It was published online on September 06, 2025, in Annals of Medicine.

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

TOPLINE:

Compared with inactive patterns, weekend warrior (moderate-to-vigorous physical activity [MVPA] condensed into 1-2 days per week) and regular physical activity patterns were found to be equally effective at reducing the risk for lung cancer. Neither pattern showed significant associations with the overall risk for cancer or specific risks for prostate, breast, and colorectal cancers.

METHODOLOGY:

• This analysis included 80,896 participants (mean age, 55.5 years; 56% women) with valid accelerometer data collected between June 2013 and December 2015.
• Participants were classified into three groups: 32,213 active weekend warriors (≥ 150 minutes of weekly MVPA with ≥ 50% achieved in 1-2 days), 22,162 active regular participants (≥ 150 minutes of MVPA but not meeting a weekend warrior pattern), and 26,521 inactive participants (< 150 minutes of MVPA).
• Researchers tracked associations between physical activity patterns and incident cases of all types of cancer plus specific cases of prostate, breast, colorectal, and lung cancer over a median follow-up duration of 6 years.

TAKEAWAY:

• Compared with inactive patterns, active weekend warrior patterns showed a significant inverse association with the risk for lung cancer (hazard ratio [HR], 0.77; 95% CI, 0.61-0.98).
• Active regular activity patterns demonstrated similar protective effects against lung cancer as inactive patterns (HR, 0.73; 95% CI, 0.56-0.96).
• Neither of the physical activity patterns showed any significant association with the overall risk for cancer or specific risks for prostate, breast, and colorectal cancers.

IN PRACTICE:

"Physical activity condensed into one to two days per week compared with a more balanced weekly distribution was associated with similar risk reductions of incident lung cancer, while neither pattern was associated with reduced overall, prostate, breast, and colorectal cancers," the authors of the study wrote.

SOURCE:

This study was led by Rubén López-Bueno, Department of Physical Medicine and Nursing, University of Zaragoza, Zaragoza, Spain. It was published online on September 06, 2025, in Annals of Medicine.

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

The size of the Veterans Health Administration (VHA) workforce continues to contract according to the latest data released by the US Department of Veterans Affairs (VA). Applications for employment are down 44% in fiscal year (FY) 2025 with just 14,485 cumulative new hires and 28,969 losses. In 2024, the VHA had 416,667 workers—it now has 401,224. 

The reductions align with VA Secretary Doug Collins’ goal of downsizing the VA’s workforce by 30,000 employees by the end of 2025. In August, Collins outlined how a federal hiring freeze, deferred resignations, retirements, and normal attrition have eliminated the need for the "large-scale" reduction-in-force he proposed earlier this year.

Compared with July’s numbers, the VHA now employs 139 fewer medical officers/physicians, 418 fewer registered nurses, 107 fewer social workers, and 65 fewer psychologists. Staffing of licensed practical nurses, medical support assistants, and nursing assistants is also down (reduced by 77, 129, and 29, respectively). 

Retention rates for the first 2 years of onboarding hover around 80% for physicians and nurses. However, retention incentives have dropped from 19,484 to 8982 and recruitment incentives from 6069 to 1299.

In voluntary exit surveys, 78% of 6762 medical and dental staff who left said they would work again for the VA, while 79% said they would recommend the VA as an employer. These rates are down from a similar survey in May 2023 when 81% noted that they would work again for the VA and 82% would recommend the VA to others. Personal matters, geographic relocation, and poor working relationships with supervisors or colleagues were among the reasons cited for leaving in August 2025. 

Of 435 psychologists, 69% said they would work again for the VA, and 62% said they would recommend the VA as an employer (71% and 67%, respectively in May 2023). Their reasons for leaving in August 2025 included a lack of trust in senior leaders and policy or technology barriers to getting the work done.

An August survey from the Office of the Inspector General found that VHA facilities reported 4434 staffing shortages this fiscal year—a 50% increase from fiscal year 2024. Most (94%) of the 139 facilities reported severe shortages for medical officers, and 79% of facilities reported severe shortages for nurses. Due to the timing of the questionnaire, the responses did not yet reflect the full impact from workforce reshaping efforts.

The size of the Veterans Health Administration (VHA) workforce continues to contract according to the latest data released by the US Department of Veterans Affairs (VA). Applications for employment are down 44% in fiscal year (FY) 2025 with just 14,485 cumulative new hires and 28,969 losses. In 2024, the VHA had 416,667 workers—it now has 401,224. 

The reductions align with VA Secretary Doug Collins’ goal of downsizing the VA’s workforce by 30,000 employees by the end of 2025. In August, Collins outlined how a federal hiring freeze, deferred resignations, retirements, and normal attrition have eliminated the need for the "large-scale" reduction-in-force he proposed earlier this year.

Compared with July’s numbers, the VHA now employs 139 fewer medical officers/physicians, 418 fewer registered nurses, 107 fewer social workers, and 65 fewer psychologists. Staffing of licensed practical nurses, medical support assistants, and nursing assistants is also down (reduced by 77, 129, and 29, respectively). 

Retention rates for the first 2 years of onboarding hover around 80% for physicians and nurses. However, retention incentives have dropped from 19,484 to 8982 and recruitment incentives from 6069 to 1299.

In voluntary exit surveys, 78% of 6762 medical and dental staff who left said they would work again for the VA, while 79% said they would recommend the VA as an employer. These rates are down from a similar survey in May 2023 when 81% noted that they would work again for the VA and 82% would recommend the VA to others. Personal matters, geographic relocation, and poor working relationships with supervisors or colleagues were among the reasons cited for leaving in August 2025. 

Of 435 psychologists, 69% said they would work again for the VA, and 62% said they would recommend the VA as an employer (71% and 67%, respectively in May 2023). Their reasons for leaving in August 2025 included a lack of trust in senior leaders and policy or technology barriers to getting the work done.

An August survey from the Office of the Inspector General found that VHA facilities reported 4434 staffing shortages this fiscal year—a 50% increase from fiscal year 2024. Most (94%) of the 139 facilities reported severe shortages for medical officers, and 79% of facilities reported severe shortages for nurses. Due to the timing of the questionnaire, the responses did not yet reflect the full impact from workforce reshaping efforts.

The size of the Veterans Health Administration (VHA) workforce continues to contract according to the latest data released by the US Department of Veterans Affairs (VA). Applications for employment are down 44% in fiscal year (FY) 2025 with just 14,485 cumulative new hires and 28,969 losses. In 2024, the VHA had 416,667 workers—it now has 401,224. 

The reductions align with VA Secretary Doug Collins’ goal of downsizing the VA’s workforce by 30,000 employees by the end of 2025. In August, Collins outlined how a federal hiring freeze, deferred resignations, retirements, and normal attrition have eliminated the need for the "large-scale" reduction-in-force he proposed earlier this year.

Compared with July’s numbers, the VHA now employs 139 fewer medical officers/physicians, 418 fewer registered nurses, 107 fewer social workers, and 65 fewer psychologists. Staffing of licensed practical nurses, medical support assistants, and nursing assistants is also down (reduced by 77, 129, and 29, respectively). 

Retention rates for the first 2 years of onboarding hover around 80% for physicians and nurses. However, retention incentives have dropped from 19,484 to 8982 and recruitment incentives from 6069 to 1299.

In voluntary exit surveys, 78% of 6762 medical and dental staff who left said they would work again for the VA, while 79% said they would recommend the VA as an employer. These rates are down from a similar survey in May 2023 when 81% noted that they would work again for the VA and 82% would recommend the VA to others. Personal matters, geographic relocation, and poor working relationships with supervisors or colleagues were among the reasons cited for leaving in August 2025. 

Of 435 psychologists, 69% said they would work again for the VA, and 62% said they would recommend the VA as an employer (71% and 67%, respectively in May 2023). Their reasons for leaving in August 2025 included a lack of trust in senior leaders and policy or technology barriers to getting the work done.

An August survey from the Office of the Inspector General found that VHA facilities reported 4434 staffing shortages this fiscal year—a 50% increase from fiscal year 2024. Most (94%) of the 139 facilities reported severe shortages for medical officers, and 79% of facilities reported severe shortages for nurses. Due to the timing of the questionnaire, the responses did not yet reflect the full impact from workforce reshaping efforts.