Oncology

Results from the British COLO-DETECT trial add to the growing body of evidence supporting the use of artificial intelligence (AI)–aided colonoscopy to increase premalignant colorectal polyp detection in routine colonoscopy practice.

Colin J. Rees, a professor of gastroenterology in the Faculty of Medical Sciences at Newcastle University in Newcastle upon Tyne, England, and colleagues compared the real-world clinical effectiveness of computer-aided detection (CADe)–assisted colonoscopy using an “intelligent” module with that of standard colonoscopy in a study in The Lancet Gastroenterology & Hepatology.

They found the GI Genius Intelligent Endoscopy Module (Medtronic) increased the mean number of adenomas detected per procedure and the adenoma detection rate, especially for small, flat (type 0-IIa) polyps, and sessile serrated lesions, which are more likely to be missed.

“Missed sessile serrated lesions disproportionately increase the risk of post-colonoscopy colorectal cancer, thus the adoption of GI Genius into routine colonoscopy practice could not only increase polyp detection but also reduce the incidence of post-colonoscopy colorectal cancer,” the investigators wrote.

“AI is going to have a major impact upon most aspects of healthcare. Some areas of medical practice are now well established, and some are still in evolution,” Rees, who is also president of the British Society of Gastroenterology, said in an interview. “Within gastroenterology, the role of AI in endoscopic diagnostics is also evolving. The COLO-DETECT trial demonstrates that AI increases detection of lesions, and work is ongoing to see how AI might help with characterization and other elements of endoscopic practice.”

 

Study Details

The multicenter, open-label, parallel-arm, pragmatic randomized controlled trial was conducted at 12 National Health Service hospitals in England. The study cohort consisted of adults ≥ 18 years undergoing colorectal cancer (CRC) screening or colonoscopy for gastrointestinal symptom surveillance owing to personal or family history.

Recruiting staff, participants, and colonoscopists were unmasked to allocation, whereas histopathologists, cochief investigators, and trial statisticians were masked.

CADe-assisted colonoscopy consisted of standard colonoscopy plus the GI Genius module active for at least the entire inspection phase of colonoscope withdrawal.

The primary outcome was mean adenomas per procedure (total number of adenomas detected divided by total number of procedures). The key secondary outcome was adenoma detection rate (proportion of colonoscopies with at least one adenoma).

From March 2021 to April 2023, the investigators recruited 2032 participants, 55.7% men, with a mean cohort age of 62.4 years and randomly assigned them to CADe-assisted colonoscopy (n = 1015) or to standard colonoscopy (n = 1017). Of these, 60.6% were undergoing screening and 39.4% had symptomatic indications.

Mean adenomas per procedure were 1.56 (SD, 2.82; n = 1001 participants with data) in the CADe-assisted group vs 1.21 (n = 1009) in the standard group, for an adjusted mean difference of 0.36 (95% CI, 0.14-0.57; adjusted incidence rate ratio, 1.30; 95% CI, 1.15-1.47; P < .0001).

Adenomas were detected in 555 (56.6%) of 980 participants in the CADe-assisted group vs 477 (48.4%) of 986 in the standard group, representing a proportion difference of 8.3% (95% CI, 3.9-12.7; adjusted odds ratio, 1.47; 95% CI, 1.21-1.78; P < .0001).

As to safety, adverse events were numerically comparable in both the intervention and control groups, with overall events 25 vs 19 and serious events 4 vs 6. On independent review, no adverse events in the CADe-assisted colonoscopy group were related to GI Genius.

 

Offering a US perspective on the study, Nabil M. Mansour, MD, an associate professor and director of the McNair General GI Clinic at Baylor College of Medicine in Houston, Texas, said GI Genius and other CADe systems represent a significant advance over standard colonoscopy for identifying premalignant polyps. “While the data have been mixed, most studies, particularly randomized controlled trials have shown significant improvements with CADe in detection both terms of in adenomas per colonoscopy and reductions in adenoma miss rate,” he said in an interview.

He added that the main utility of CADe is for asymptomatic patients undergoing average-risk screening and surveillance colonoscopy for CRC screening and prevention, as well as for those with positive stool-based screening tests, “though there is no downside to using it in symptomatic patients as well.” Though AI colonoscopy likely still stands at < 50% of endoscopy centers overall, and is used mainly at academic centers, his clinic has been using it for the past year.

The main question, Mansour cautioned, is whether increased detection of small polyps will actually reduce CRC incidence or mortality, and it will likely be several years before clear, concrete data can answer that.

“Most studies have shown the improvement in adenoma detection is mainly for diminutive polyps < 5 mm in diameter, but whether that will actually translate to substantive improvements in hard outcomes is as yet unknown,” he said. “But if gastroenterologists are interested in doing everything they can today to help improve detection rates and lower miss rates of premalignant polyps, serious consideration should be given to adopting the use of CADe in practice.”

This study was supported by Medtronic. Rees reported receiving grant funding from ARC Medical, Norgine, Medtronic, 3-D Matrix, and Olympus Medical, and has been an expert witness for ARC Medical. Other authors disclosed receiving research funding, honoraria, or travel expenses from Medtronic or other private companies. Mansour had no competing interests to declare.

A version of this article appeared on Medscape.com.

Results from the British COLO-DETECT trial add to the growing body of evidence supporting the use of artificial intelligence (AI)–aided colonoscopy to increase premalignant colorectal polyp detection in routine colonoscopy practice.

Colin J. Rees, a professor of gastroenterology in the Faculty of Medical Sciences at Newcastle University in Newcastle upon Tyne, England, and colleagues compared the real-world clinical effectiveness of computer-aided detection (CADe)–assisted colonoscopy using an “intelligent” module with that of standard colonoscopy in a study in The Lancet Gastroenterology & Hepatology.

They found the GI Genius Intelligent Endoscopy Module (Medtronic) increased the mean number of adenomas detected per procedure and the adenoma detection rate, especially for small, flat (type 0-IIa) polyps, and sessile serrated lesions, which are more likely to be missed.

“Missed sessile serrated lesions disproportionately increase the risk of post-colonoscopy colorectal cancer, thus the adoption of GI Genius into routine colonoscopy practice could not only increase polyp detection but also reduce the incidence of post-colonoscopy colorectal cancer,” the investigators wrote.

“AI is going to have a major impact upon most aspects of healthcare. Some areas of medical practice are now well established, and some are still in evolution,” Rees, who is also president of the British Society of Gastroenterology, said in an interview. “Within gastroenterology, the role of AI in endoscopic diagnostics is also evolving. The COLO-DETECT trial demonstrates that AI increases detection of lesions, and work is ongoing to see how AI might help with characterization and other elements of endoscopic practice.”

 

Study Details

The multicenter, open-label, parallel-arm, pragmatic randomized controlled trial was conducted at 12 National Health Service hospitals in England. The study cohort consisted of adults ≥ 18 years undergoing colorectal cancer (CRC) screening or colonoscopy for gastrointestinal symptom surveillance owing to personal or family history.

Recruiting staff, participants, and colonoscopists were unmasked to allocation, whereas histopathologists, cochief investigators, and trial statisticians were masked.

CADe-assisted colonoscopy consisted of standard colonoscopy plus the GI Genius module active for at least the entire inspection phase of colonoscope withdrawal.

The primary outcome was mean adenomas per procedure (total number of adenomas detected divided by total number of procedures). The key secondary outcome was adenoma detection rate (proportion of colonoscopies with at least one adenoma).

From March 2021 to April 2023, the investigators recruited 2032 participants, 55.7% men, with a mean cohort age of 62.4 years and randomly assigned them to CADe-assisted colonoscopy (n = 1015) or to standard colonoscopy (n = 1017). Of these, 60.6% were undergoing screening and 39.4% had symptomatic indications.

Mean adenomas per procedure were 1.56 (SD, 2.82; n = 1001 participants with data) in the CADe-assisted group vs 1.21 (n = 1009) in the standard group, for an adjusted mean difference of 0.36 (95% CI, 0.14-0.57; adjusted incidence rate ratio, 1.30; 95% CI, 1.15-1.47; P < .0001).

Adenomas were detected in 555 (56.6%) of 980 participants in the CADe-assisted group vs 477 (48.4%) of 986 in the standard group, representing a proportion difference of 8.3% (95% CI, 3.9-12.7; adjusted odds ratio, 1.47; 95% CI, 1.21-1.78; P < .0001).

As to safety, adverse events were numerically comparable in both the intervention and control groups, with overall events 25 vs 19 and serious events 4 vs 6. On independent review, no adverse events in the CADe-assisted colonoscopy group were related to GI Genius.

 

Offering a US perspective on the study, Nabil M. Mansour, MD, an associate professor and director of the McNair General GI Clinic at Baylor College of Medicine in Houston, Texas, said GI Genius and other CADe systems represent a significant advance over standard colonoscopy for identifying premalignant polyps. “While the data have been mixed, most studies, particularly randomized controlled trials have shown significant improvements with CADe in detection both terms of in adenomas per colonoscopy and reductions in adenoma miss rate,” he said in an interview.

He added that the main utility of CADe is for asymptomatic patients undergoing average-risk screening and surveillance colonoscopy for CRC screening and prevention, as well as for those with positive stool-based screening tests, “though there is no downside to using it in symptomatic patients as well.” Though AI colonoscopy likely still stands at < 50% of endoscopy centers overall, and is used mainly at academic centers, his clinic has been using it for the past year.

The main question, Mansour cautioned, is whether increased detection of small polyps will actually reduce CRC incidence or mortality, and it will likely be several years before clear, concrete data can answer that.

“Most studies have shown the improvement in adenoma detection is mainly for diminutive polyps < 5 mm in diameter, but whether that will actually translate to substantive improvements in hard outcomes is as yet unknown,” he said. “But if gastroenterologists are interested in doing everything they can today to help improve detection rates and lower miss rates of premalignant polyps, serious consideration should be given to adopting the use of CADe in practice.”

This study was supported by Medtronic. Rees reported receiving grant funding from ARC Medical, Norgine, Medtronic, 3-D Matrix, and Olympus Medical, and has been an expert witness for ARC Medical. Other authors disclosed receiving research funding, honoraria, or travel expenses from Medtronic or other private companies. Mansour had no competing interests to declare.

A version of this article appeared on Medscape.com.

Results from the British COLO-DETECT trial add to the growing body of evidence supporting the use of artificial intelligence (AI)–aided colonoscopy to increase premalignant colorectal polyp detection in routine colonoscopy practice.

Colin J. Rees, a professor of gastroenterology in the Faculty of Medical Sciences at Newcastle University in Newcastle upon Tyne, England, and colleagues compared the real-world clinical effectiveness of computer-aided detection (CADe)–assisted colonoscopy using an “intelligent” module with that of standard colonoscopy in a study in The Lancet Gastroenterology & Hepatology.

They found the GI Genius Intelligent Endoscopy Module (Medtronic) increased the mean number of adenomas detected per procedure and the adenoma detection rate, especially for small, flat (type 0-IIa) polyps, and sessile serrated lesions, which are more likely to be missed.

“Missed sessile serrated lesions disproportionately increase the risk of post-colonoscopy colorectal cancer, thus the adoption of GI Genius into routine colonoscopy practice could not only increase polyp detection but also reduce the incidence of post-colonoscopy colorectal cancer,” the investigators wrote.

“AI is going to have a major impact upon most aspects of healthcare. Some areas of medical practice are now well established, and some are still in evolution,” Rees, who is also president of the British Society of Gastroenterology, said in an interview. “Within gastroenterology, the role of AI in endoscopic diagnostics is also evolving. The COLO-DETECT trial demonstrates that AI increases detection of lesions, and work is ongoing to see how AI might help with characterization and other elements of endoscopic practice.”

 

Study Details

The multicenter, open-label, parallel-arm, pragmatic randomized controlled trial was conducted at 12 National Health Service hospitals in England. The study cohort consisted of adults ≥ 18 years undergoing colorectal cancer (CRC) screening or colonoscopy for gastrointestinal symptom surveillance owing to personal or family history.

Recruiting staff, participants, and colonoscopists were unmasked to allocation, whereas histopathologists, cochief investigators, and trial statisticians were masked.

CADe-assisted colonoscopy consisted of standard colonoscopy plus the GI Genius module active for at least the entire inspection phase of colonoscope withdrawal.

The primary outcome was mean adenomas per procedure (total number of adenomas detected divided by total number of procedures). The key secondary outcome was adenoma detection rate (proportion of colonoscopies with at least one adenoma).

From March 2021 to April 2023, the investigators recruited 2032 participants, 55.7% men, with a mean cohort age of 62.4 years and randomly assigned them to CADe-assisted colonoscopy (n = 1015) or to standard colonoscopy (n = 1017). Of these, 60.6% were undergoing screening and 39.4% had symptomatic indications.

Mean adenomas per procedure were 1.56 (SD, 2.82; n = 1001 participants with data) in the CADe-assisted group vs 1.21 (n = 1009) in the standard group, for an adjusted mean difference of 0.36 (95% CI, 0.14-0.57; adjusted incidence rate ratio, 1.30; 95% CI, 1.15-1.47; P < .0001).

Adenomas were detected in 555 (56.6%) of 980 participants in the CADe-assisted group vs 477 (48.4%) of 986 in the standard group, representing a proportion difference of 8.3% (95% CI, 3.9-12.7; adjusted odds ratio, 1.47; 95% CI, 1.21-1.78; P < .0001).

As to safety, adverse events were numerically comparable in both the intervention and control groups, with overall events 25 vs 19 and serious events 4 vs 6. On independent review, no adverse events in the CADe-assisted colonoscopy group were related to GI Genius.

 

Offering a US perspective on the study, Nabil M. Mansour, MD, an associate professor and director of the McNair General GI Clinic at Baylor College of Medicine in Houston, Texas, said GI Genius and other CADe systems represent a significant advance over standard colonoscopy for identifying premalignant polyps. “While the data have been mixed, most studies, particularly randomized controlled trials have shown significant improvements with CADe in detection both terms of in adenomas per colonoscopy and reductions in adenoma miss rate,” he said in an interview.

He added that the main utility of CADe is for asymptomatic patients undergoing average-risk screening and surveillance colonoscopy for CRC screening and prevention, as well as for those with positive stool-based screening tests, “though there is no downside to using it in symptomatic patients as well.” Though AI colonoscopy likely still stands at < 50% of endoscopy centers overall, and is used mainly at academic centers, his clinic has been using it for the past year.

The main question, Mansour cautioned, is whether increased detection of small polyps will actually reduce CRC incidence or mortality, and it will likely be several years before clear, concrete data can answer that.

“Most studies have shown the improvement in adenoma detection is mainly for diminutive polyps < 5 mm in diameter, but whether that will actually translate to substantive improvements in hard outcomes is as yet unknown,” he said. “But if gastroenterologists are interested in doing everything they can today to help improve detection rates and lower miss rates of premalignant polyps, serious consideration should be given to adopting the use of CADe in practice.”

This study was supported by Medtronic. Rees reported receiving grant funding from ARC Medical, Norgine, Medtronic, 3-D Matrix, and Olympus Medical, and has been an expert witness for ARC Medical. Other authors disclosed receiving research funding, honoraria, or travel expenses from Medtronic or other private companies. Mansour had no competing interests to declare.

A version of this article appeared on Medscape.com.

Recently, a 40-year-old woman took to Facebook to announce that she had died.

Rachel Davies, of Wales, wrote: “If you’re reading this, then it means I’m no longer here. What a life I’ve had, and surprisingly, since cancer entered my life. When I look through my photos, I’ve done and seen so much since cancer, and probably some of my best memories are from this period. In so many ways, I have to thank it for learning how to live fully. What I wish is that everyone can experience the same but without needing cancer. Get out there, experience life fully, and wear that dress!!! I’m so sad to leave my family and friends, I wish I never had to go. I’m so grateful to have had Charlie young so that I’ve watched him grow into the man he is today. I’m unbelievably proud of him. I am thankful I had the opportunity to have Kacey and Jacob in my life. Lastly, I was blessed to meet the love of my life, my husband, and my best friend. I have no regrets, I have had a wonderful life. So to all of you, don’t be sad I’ve gone. Live your life and live it well. Love, Rachel x.”

 

I didn’t know Ms. Davies, but am likely among many who wish I had. In a terrible situation she kept trying.

She had HER2 metastatic breast cancer, which can respond to the drug Enhertu (trastuzumab). Unfortunately, she never had the chance, because it wasn’t available to her in Wales. In the United Kingdom it’s available only in Scotland.

I’m not saying it was a cure. Statistically, it likely would have bought her another 6 months of family time. But that’s still another half year.

I’m not blaming the Welsh NHS, though they made the decision not to cover it because of cost. The jobs of such committees is a thankless one, trying to decide where the limited money goes — vaccines for many children that are proven to lessen morbidity and mortality over the course of a lifetime, or to add 6 months to the lives of comparatively fewer women with HER2 metastatic breast cancer.

I’m not blaming the company that makes Enhertu, though it was the cost that kept her from getting it. Bringing a drug to market, with all the labs and clinical research behind it, ain’t cheap. If the company can’t keep the lights on they’re not going to able to develop future pharmaceuticals to help others, though I do wonder if a better price could have been negotiated. (I’m not trying to justify the salaries of insurance CEOs — don’t even get me started on those.)

Money is always limited, and human suffering is infinite. Every health care organization, public or private, has to face that simple fact. There is no right place to draw the line, so we use the greatest good for the greatest many as our best guess.

In her last post, though, Ms. Davies didn’t dwell on any of this. She reflected on her joys and blessings, and encouraged others to live life fully. Things we should all focus on.

In a world that often seems to have gone mad, it’s good to keep in mind that there is more good than bad out there. 

Thank you, Ms. Davies, for the reminder.

Allan M. Block, MD, has a solo neurology practice in Scottsdale, Arizona.

Recently, a 40-year-old woman took to Facebook to announce that she had died.

Rachel Davies, of Wales, wrote: “If you’re reading this, then it means I’m no longer here. What a life I’ve had, and surprisingly, since cancer entered my life. When I look through my photos, I’ve done and seen so much since cancer, and probably some of my best memories are from this period. In so many ways, I have to thank it for learning how to live fully. What I wish is that everyone can experience the same but without needing cancer. Get out there, experience life fully, and wear that dress!!! I’m so sad to leave my family and friends, I wish I never had to go. I’m so grateful to have had Charlie young so that I’ve watched him grow into the man he is today. I’m unbelievably proud of him. I am thankful I had the opportunity to have Kacey and Jacob in my life. Lastly, I was blessed to meet the love of my life, my husband, and my best friend. I have no regrets, I have had a wonderful life. So to all of you, don’t be sad I’ve gone. Live your life and live it well. Love, Rachel x.”

 

I didn’t know Ms. Davies, but am likely among many who wish I had. In a terrible situation she kept trying.

She had HER2 metastatic breast cancer, which can respond to the drug Enhertu (trastuzumab). Unfortunately, she never had the chance, because it wasn’t available to her in Wales. In the United Kingdom it’s available only in Scotland.

I’m not saying it was a cure. Statistically, it likely would have bought her another 6 months of family time. But that’s still another half year.

I’m not blaming the Welsh NHS, though they made the decision not to cover it because of cost. The jobs of such committees is a thankless one, trying to decide where the limited money goes — vaccines for many children that are proven to lessen morbidity and mortality over the course of a lifetime, or to add 6 months to the lives of comparatively fewer women with HER2 metastatic breast cancer.

I’m not blaming the company that makes Enhertu, though it was the cost that kept her from getting it. Bringing a drug to market, with all the labs and clinical research behind it, ain’t cheap. If the company can’t keep the lights on they’re not going to able to develop future pharmaceuticals to help others, though I do wonder if a better price could have been negotiated. (I’m not trying to justify the salaries of insurance CEOs — don’t even get me started on those.)

Money is always limited, and human suffering is infinite. Every health care organization, public or private, has to face that simple fact. There is no right place to draw the line, so we use the greatest good for the greatest many as our best guess.

In her last post, though, Ms. Davies didn’t dwell on any of this. She reflected on her joys and blessings, and encouraged others to live life fully. Things we should all focus on.

In a world that often seems to have gone mad, it’s good to keep in mind that there is more good than bad out there. 

Thank you, Ms. Davies, for the reminder.

Allan M. Block, MD, has a solo neurology practice in Scottsdale, Arizona.

Recently, a 40-year-old woman took to Facebook to announce that she had died.

Rachel Davies, of Wales, wrote: “If you’re reading this, then it means I’m no longer here. What a life I’ve had, and surprisingly, since cancer entered my life. When I look through my photos, I’ve done and seen so much since cancer, and probably some of my best memories are from this period. In so many ways, I have to thank it for learning how to live fully. What I wish is that everyone can experience the same but without needing cancer. Get out there, experience life fully, and wear that dress!!! I’m so sad to leave my family and friends, I wish I never had to go. I’m so grateful to have had Charlie young so that I’ve watched him grow into the man he is today. I’m unbelievably proud of him. I am thankful I had the opportunity to have Kacey and Jacob in my life. Lastly, I was blessed to meet the love of my life, my husband, and my best friend. I have no regrets, I have had a wonderful life. So to all of you, don’t be sad I’ve gone. Live your life and live it well. Love, Rachel x.”

 

I didn’t know Ms. Davies, but am likely among many who wish I had. In a terrible situation she kept trying.

She had HER2 metastatic breast cancer, which can respond to the drug Enhertu (trastuzumab). Unfortunately, she never had the chance, because it wasn’t available to her in Wales. In the United Kingdom it’s available only in Scotland.

I’m not saying it was a cure. Statistically, it likely would have bought her another 6 months of family time. But that’s still another half year.

I’m not blaming the Welsh NHS, though they made the decision not to cover it because of cost. The jobs of such committees is a thankless one, trying to decide where the limited money goes — vaccines for many children that are proven to lessen morbidity and mortality over the course of a lifetime, or to add 6 months to the lives of comparatively fewer women with HER2 metastatic breast cancer.

I’m not blaming the company that makes Enhertu, though it was the cost that kept her from getting it. Bringing a drug to market, with all the labs and clinical research behind it, ain’t cheap. If the company can’t keep the lights on they’re not going to able to develop future pharmaceuticals to help others, though I do wonder if a better price could have been negotiated. (I’m not trying to justify the salaries of insurance CEOs — don’t even get me started on those.)

Money is always limited, and human suffering is infinite. Every health care organization, public or private, has to face that simple fact. There is no right place to draw the line, so we use the greatest good for the greatest many as our best guess.

In her last post, though, Ms. Davies didn’t dwell on any of this. She reflected on her joys and blessings, and encouraged others to live life fully. Things we should all focus on.

In a world that often seems to have gone mad, it’s good to keep in mind that there is more good than bad out there. 

Thank you, Ms. Davies, for the reminder.

Allan M. Block, MD, has a solo neurology practice in Scottsdale, Arizona.

TOPLINE:

Aggressive margin reduction with MRI-guided stereotactic body radiotherapy (SBRT) led to a significantly lower incidence of late genitourinary and gastrointestinal toxicities at 2 years compared with CT-guided SBRT in men with localized prostate cancer, new data showed.

METHODOLOGY:

• MRI-guided SBRT is known to reduce planning margins in prostate cancer and lead to less acute toxicity compared with standard CT-guided SBRT. However, the long-term benefits of the MRI-guided approach remain unclear.
• To find out, researchers conducted the phase 3 MIRAGE trial, in which 156 patients with localized prostate cancer were randomly assigned to receive either MRI-guided SBRT with 2-mm margins or CT-guided SBRT with 4-mm margins.
• The MIRAGE trial initially reported the primary outcome of acute genitourinary grade ≥ 2 toxicity within 90 days of SBRT.
• In this secondary analysis, researchers evaluated physician-reported late genitourinary and gastrointestinal toxicity, along with changes in various patient-reported quality-of-life scores over a 2-year follow-up period.

TAKEAWAY:

• Over a period of 2 years, MRI-guided SBRT was associated with a significantly lower cumulative incidence of grade ≥ 2 genitourinary toxicities compared with CT-guided SBRT (27% vs 51%; P = .004). Similar outcomes were noted for grade ≥ 2 gastrointestinal toxicities (1.4% with MRI vs 9.5% with CT; P = .025).
• Fewer patients who received MRI-guided SBRT reported deterioration in urinary irritation between 6 and 24 months after radiotherapy — 14 of 73 patients (19.2%) in the MRI group vs 24 of 68 patients (35.3%) in the CT group (P = .031).
• Patients receiving MRI-guided SBRT were also less likely to experience clinically relevant deterioration in bowel function (odds ratio [OR], 0.444; P = .035) and sexual health score (OR, 0.366; P = .03).
• Between 6 and 24 months after radiotherapy, 26.4% of patients (19 of 72) in the MRI group vs 42.3% (30 of 71) in the CT group reported clinically relevant deterioration in bowel function.

IN PRACTICE:

“Our secondary analysis of a randomized trial revealed that aggressive planning for margin reduction with MRI guidance vs CT guidance for prostate SBRT led to lower physician-scored genitourinary and gastrointestinal toxicity and better bowel and sexual quality-of-life metrics over 2 years of follow-up,” the authors wrote.

SOURCE:

This study, led by Amar U. Kishan, University of California Los Angeles, was published online in European Urology.

LIMITATIONS:

The absence of blinding in this study may have influenced both physician-scored toxicity assessments and patient-reported quality-of-life outcomes. The MIRAGE trial was not specifically designed with sufficient statistical power to evaluate the secondary analyses presented in this study.

DISCLOSURES:

This study was supported by grants from the US Department of Defense. Several authors reported receiving grants or personal fees among other ties with various sources.

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:

Aggressive margin reduction with MRI-guided stereotactic body radiotherapy (SBRT) led to a significantly lower incidence of late genitourinary and gastrointestinal toxicities at 2 years compared with CT-guided SBRT in men with localized prostate cancer, new data showed.

METHODOLOGY:

• MRI-guided SBRT is known to reduce planning margins in prostate cancer and lead to less acute toxicity compared with standard CT-guided SBRT. However, the long-term benefits of the MRI-guided approach remain unclear.
• To find out, researchers conducted the phase 3 MIRAGE trial, in which 156 patients with localized prostate cancer were randomly assigned to receive either MRI-guided SBRT with 2-mm margins or CT-guided SBRT with 4-mm margins.
• The MIRAGE trial initially reported the primary outcome of acute genitourinary grade ≥ 2 toxicity within 90 days of SBRT.
• In this secondary analysis, researchers evaluated physician-reported late genitourinary and gastrointestinal toxicity, along with changes in various patient-reported quality-of-life scores over a 2-year follow-up period.

TAKEAWAY:

• Over a period of 2 years, MRI-guided SBRT was associated with a significantly lower cumulative incidence of grade ≥ 2 genitourinary toxicities compared with CT-guided SBRT (27% vs 51%; P = .004). Similar outcomes were noted for grade ≥ 2 gastrointestinal toxicities (1.4% with MRI vs 9.5% with CT; P = .025).
• Fewer patients who received MRI-guided SBRT reported deterioration in urinary irritation between 6 and 24 months after radiotherapy — 14 of 73 patients (19.2%) in the MRI group vs 24 of 68 patients (35.3%) in the CT group (P = .031).
• Patients receiving MRI-guided SBRT were also less likely to experience clinically relevant deterioration in bowel function (odds ratio [OR], 0.444; P = .035) and sexual health score (OR, 0.366; P = .03).
• Between 6 and 24 months after radiotherapy, 26.4% of patients (19 of 72) in the MRI group vs 42.3% (30 of 71) in the CT group reported clinically relevant deterioration in bowel function.

IN PRACTICE:

“Our secondary analysis of a randomized trial revealed that aggressive planning for margin reduction with MRI guidance vs CT guidance for prostate SBRT led to lower physician-scored genitourinary and gastrointestinal toxicity and better bowel and sexual quality-of-life metrics over 2 years of follow-up,” the authors wrote.

SOURCE:

This study, led by Amar U. Kishan, University of California Los Angeles, was published online in European Urology.

LIMITATIONS:

The absence of blinding in this study may have influenced both physician-scored toxicity assessments and patient-reported quality-of-life outcomes. The MIRAGE trial was not specifically designed with sufficient statistical power to evaluate the secondary analyses presented in this study.

DISCLOSURES:

This study was supported by grants from the US Department of Defense. Several authors reported receiving grants or personal fees among other ties with various sources.

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:

Aggressive margin reduction with MRI-guided stereotactic body radiotherapy (SBRT) led to a significantly lower incidence of late genitourinary and gastrointestinal toxicities at 2 years compared with CT-guided SBRT in men with localized prostate cancer, new data showed.

METHODOLOGY:

• MRI-guided SBRT is known to reduce planning margins in prostate cancer and lead to less acute toxicity compared with standard CT-guided SBRT. However, the long-term benefits of the MRI-guided approach remain unclear.
• To find out, researchers conducted the phase 3 MIRAGE trial, in which 156 patients with localized prostate cancer were randomly assigned to receive either MRI-guided SBRT with 2-mm margins or CT-guided SBRT with 4-mm margins.
• The MIRAGE trial initially reported the primary outcome of acute genitourinary grade ≥ 2 toxicity within 90 days of SBRT.
• In this secondary analysis, researchers evaluated physician-reported late genitourinary and gastrointestinal toxicity, along with changes in various patient-reported quality-of-life scores over a 2-year follow-up period.

TAKEAWAY:

• Over a period of 2 years, MRI-guided SBRT was associated with a significantly lower cumulative incidence of grade ≥ 2 genitourinary toxicities compared with CT-guided SBRT (27% vs 51%; P = .004). Similar outcomes were noted for grade ≥ 2 gastrointestinal toxicities (1.4% with MRI vs 9.5% with CT; P = .025).
• Fewer patients who received MRI-guided SBRT reported deterioration in urinary irritation between 6 and 24 months after radiotherapy — 14 of 73 patients (19.2%) in the MRI group vs 24 of 68 patients (35.3%) in the CT group (P = .031).
• Patients receiving MRI-guided SBRT were also less likely to experience clinically relevant deterioration in bowel function (odds ratio [OR], 0.444; P = .035) and sexual health score (OR, 0.366; P = .03).
• Between 6 and 24 months after radiotherapy, 26.4% of patients (19 of 72) in the MRI group vs 42.3% (30 of 71) in the CT group reported clinically relevant deterioration in bowel function.

IN PRACTICE:

“Our secondary analysis of a randomized trial revealed that aggressive planning for margin reduction with MRI guidance vs CT guidance for prostate SBRT led to lower physician-scored genitourinary and gastrointestinal toxicity and better bowel and sexual quality-of-life metrics over 2 years of follow-up,” the authors wrote.

SOURCE:

This study, led by Amar U. Kishan, University of California Los Angeles, was published online in European Urology.

LIMITATIONS:

The absence of blinding in this study may have influenced both physician-scored toxicity assessments and patient-reported quality-of-life outcomes. The MIRAGE trial was not specifically designed with sufficient statistical power to evaluate the secondary analyses presented in this study.

DISCLOSURES:

This study was supported by grants from the US Department of Defense. Several authors reported receiving grants or personal fees among other ties with various sources.

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:

Age-standardized mortality rates for hepatocellular carcinoma (HCC) in the United States are expected to rise from 5.03 per 100,000 persons in 2022 to 6.39 per 100,000 persons by 2040. Alcohol-associated liver disease (ALD) will likely become the leading cause of HCC-related mortality by 2026, and metabolic dysfunction–associated steatotic liver disease (MASLD) is projected to become the second leading cause by 2032, a new analysis found. 

METHODOLOGY:

• HCC accounts for 75%-85% of primary liver cancers and most liver cancer deaths. Researchers have observed an upward trend in the incidence of and mortality from HCC in the past 2 decades.
• This cross-sectional study analyzed 188,280 HCC-related deaths among adults aged 25 and older to determine trends in mortality rates and project age-standardized mortality rates through 2040. Data came from the National Vital Statistics System database from 2006 to 2022.
• Researchers stratified mortality data by etiology of liver disease (ALD, hepatitis B virus, hepatitis C virus, and MASLD), age groups (25-64 or 65 and older years), sex, and race/ethnicity.
• Demographic data showed that 77.4% of deaths occurred in men, 55.6% in individuals aged 65 years or older, and 62.3% in White individuals.

TAKEAWAY:

• Overall, the age-standardized mortality rate for HCC-related deaths increased from 3.65 per 100,000 persons in 2006 to 5.03 in 2022 and was projected to increase to 6.39 per 100,000 persons by 2040.
• Sex- and age-related disparities were substantial. Men had much higher rates of HCC-related mortality than women (8.15 vs 2.33 per 100,000 persons), with a projected rate among men of 9.78 per 100,000 persons by 2040. HCC-related mortality rates for people aged 65 years or older were 10 times higher than for those aged 25-64 years (18.37 vs 1.79 per 100,000 persons) in 2022 and was projected to reach 32.81 per 100,000 persons by 2040 in the older group.
• Although hepatitis C virus–related deaths were projected to decline from 0.69 to 0.03 per 100,000 persons by 2034, ALD- and MASLD-related deaths showed increasing trends, with both projected to become the two leading causes of HCC-related mortality in the next few years.
• Racial disparities were also evident. By 2040, the American Indian/Alaska Native population showed the highest increase in projected HCC-related mortality rates, which went from 5.46 per 100,000 persons in 2006 to a project increase to 14.71 per 100,000 persons.

IN PRACTICE:

“HCC mortality was projected to continue increasing in the US, primarily due to rising rates of deaths attributable to ALD and MASLD,” the authors wrote. 

This “study highlights the importance of addressing these conditions to decrease the burden of liver disease and liver disease mortality in the future,” Emad Qayed, MD, MPH, Emory University School of Medicine, Atlanta, wrote in an accompanying editorial.

SOURCE:

The study was led by Sikai Qiu, MM, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, China, and was published online in JAMA Network Open.
 

LIMITATIONS:

The National Vital Statistics System database used in this study captured only mortality data without access to detailed clinical records or individual medical histories. Researchers could not analyze socioeconomic factors or individual-level risk factors owing to data anonymization requirements. Additionally, the inclusion of the COVID-19 pandemic period could have influenced observed trends and reliability of future projections.
 

DISCLOSURES:

This study was supported by grants from the National Natural Science Foundation of China. Several authors reported receiving consulting fees, speaking fees, or research support from various sources.

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 appeared on Medscape.com.

TOPLINE:

Age-standardized mortality rates for hepatocellular carcinoma (HCC) in the United States are expected to rise from 5.03 per 100,000 persons in 2022 to 6.39 per 100,000 persons by 2040. Alcohol-associated liver disease (ALD) will likely become the leading cause of HCC-related mortality by 2026, and metabolic dysfunction–associated steatotic liver disease (MASLD) is projected to become the second leading cause by 2032, a new analysis found. 

METHODOLOGY:

• HCC accounts for 75%-85% of primary liver cancers and most liver cancer deaths. Researchers have observed an upward trend in the incidence of and mortality from HCC in the past 2 decades.
• This cross-sectional study analyzed 188,280 HCC-related deaths among adults aged 25 and older to determine trends in mortality rates and project age-standardized mortality rates through 2040. Data came from the National Vital Statistics System database from 2006 to 2022.
• Researchers stratified mortality data by etiology of liver disease (ALD, hepatitis B virus, hepatitis C virus, and MASLD), age groups (25-64 or 65 and older years), sex, and race/ethnicity.
• Demographic data showed that 77.4% of deaths occurred in men, 55.6% in individuals aged 65 years or older, and 62.3% in White individuals.

TAKEAWAY:

• Overall, the age-standardized mortality rate for HCC-related deaths increased from 3.65 per 100,000 persons in 2006 to 5.03 in 2022 and was projected to increase to 6.39 per 100,000 persons by 2040.
• Sex- and age-related disparities were substantial. Men had much higher rates of HCC-related mortality than women (8.15 vs 2.33 per 100,000 persons), with a projected rate among men of 9.78 per 100,000 persons by 2040. HCC-related mortality rates for people aged 65 years or older were 10 times higher than for those aged 25-64 years (18.37 vs 1.79 per 100,000 persons) in 2022 and was projected to reach 32.81 per 100,000 persons by 2040 in the older group.
• Although hepatitis C virus–related deaths were projected to decline from 0.69 to 0.03 per 100,000 persons by 2034, ALD- and MASLD-related deaths showed increasing trends, with both projected to become the two leading causes of HCC-related mortality in the next few years.
• Racial disparities were also evident. By 2040, the American Indian/Alaska Native population showed the highest increase in projected HCC-related mortality rates, which went from 5.46 per 100,000 persons in 2006 to a project increase to 14.71 per 100,000 persons.

IN PRACTICE:

“HCC mortality was projected to continue increasing in the US, primarily due to rising rates of deaths attributable to ALD and MASLD,” the authors wrote. 

This “study highlights the importance of addressing these conditions to decrease the burden of liver disease and liver disease mortality in the future,” Emad Qayed, MD, MPH, Emory University School of Medicine, Atlanta, wrote in an accompanying editorial.

SOURCE:

The study was led by Sikai Qiu, MM, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, China, and was published online in JAMA Network Open.
 

LIMITATIONS:

The National Vital Statistics System database used in this study captured only mortality data without access to detailed clinical records or individual medical histories. Researchers could not analyze socioeconomic factors or individual-level risk factors owing to data anonymization requirements. Additionally, the inclusion of the COVID-19 pandemic period could have influenced observed trends and reliability of future projections.
 

DISCLOSURES:

This study was supported by grants from the National Natural Science Foundation of China. Several authors reported receiving consulting fees, speaking fees, or research support from various sources.

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 appeared on Medscape.com.

TOPLINE:

Age-standardized mortality rates for hepatocellular carcinoma (HCC) in the United States are expected to rise from 5.03 per 100,000 persons in 2022 to 6.39 per 100,000 persons by 2040. Alcohol-associated liver disease (ALD) will likely become the leading cause of HCC-related mortality by 2026, and metabolic dysfunction–associated steatotic liver disease (MASLD) is projected to become the second leading cause by 2032, a new analysis found. 

METHODOLOGY:

• HCC accounts for 75%-85% of primary liver cancers and most liver cancer deaths. Researchers have observed an upward trend in the incidence of and mortality from HCC in the past 2 decades.
• This cross-sectional study analyzed 188,280 HCC-related deaths among adults aged 25 and older to determine trends in mortality rates and project age-standardized mortality rates through 2040. Data came from the National Vital Statistics System database from 2006 to 2022.
• Researchers stratified mortality data by etiology of liver disease (ALD, hepatitis B virus, hepatitis C virus, and MASLD), age groups (25-64 or 65 and older years), sex, and race/ethnicity.
• Demographic data showed that 77.4% of deaths occurred in men, 55.6% in individuals aged 65 years or older, and 62.3% in White individuals.

TAKEAWAY:

• Overall, the age-standardized mortality rate for HCC-related deaths increased from 3.65 per 100,000 persons in 2006 to 5.03 in 2022 and was projected to increase to 6.39 per 100,000 persons by 2040.
• Sex- and age-related disparities were substantial. Men had much higher rates of HCC-related mortality than women (8.15 vs 2.33 per 100,000 persons), with a projected rate among men of 9.78 per 100,000 persons by 2040. HCC-related mortality rates for people aged 65 years or older were 10 times higher than for those aged 25-64 years (18.37 vs 1.79 per 100,000 persons) in 2022 and was projected to reach 32.81 per 100,000 persons by 2040 in the older group.
• Although hepatitis C virus–related deaths were projected to decline from 0.69 to 0.03 per 100,000 persons by 2034, ALD- and MASLD-related deaths showed increasing trends, with both projected to become the two leading causes of HCC-related mortality in the next few years.
• Racial disparities were also evident. By 2040, the American Indian/Alaska Native population showed the highest increase in projected HCC-related mortality rates, which went from 5.46 per 100,000 persons in 2006 to a project increase to 14.71 per 100,000 persons.

IN PRACTICE:

“HCC mortality was projected to continue increasing in the US, primarily due to rising rates of deaths attributable to ALD and MASLD,” the authors wrote. 

This “study highlights the importance of addressing these conditions to decrease the burden of liver disease and liver disease mortality in the future,” Emad Qayed, MD, MPH, Emory University School of Medicine, Atlanta, wrote in an accompanying editorial.

SOURCE:

The study was led by Sikai Qiu, MM, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, China, and was published online in JAMA Network Open.
 

LIMITATIONS:

The National Vital Statistics System database used in this study captured only mortality data without access to detailed clinical records or individual medical histories. Researchers could not analyze socioeconomic factors or individual-level risk factors owing to data anonymization requirements. Additionally, the inclusion of the COVID-19 pandemic period could have influenced observed trends and reliability of future projections.
 

DISCLOSURES:

This study was supported by grants from the National Natural Science Foundation of China. Several authors reported receiving consulting fees, speaking fees, or research support from various sources.

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 appeared on Medscape.com.

Cutaneous melanoma is a type of skin cancer typically associated with significant ultraviolet radiation exposure. Melanoma arises from melanocytes, cells found within the lower portion of the epidermis that make the pigment melanin.

While much less common than squamous cell carcinoma or basal cell carcinoma, melanoma is responsible for most deaths from skin cancer. In 2024, there will be more than 100,000 new cases of melanoma and over 8,000 melanoma-related deaths.¹ If localized at the time of diagnosis, survival rates are excellent. Cutaneous melanomas are more common in those with fair complexions or who have had long periods of exposure to natural or artificial sunlight.

Melanoma can also occur in mucous membranes. Mucosal melanoma is much less common than cutaneous melanoma and accounts for only a very small percentage of all new melanoma diagnoses. Unlike their cutaneous counterparts, risk factors for mucosal melanomas have yet to be identified. Although there is some disagreement on whether vulvar melanomas represent cutaneous or mucous melanomas, vulvovaginal melanomas have historically been considered to be mucosal melanomas.

Vulvovaginal melanomas are characterized by a high mortality rate, diagnostic challenges, and lack of awareness, making early detection and intervention crucial to improving patient outcomes. The 5-year overall survival rate for vulvar melanoma is 36% and for vaginal melanoma ranges between 5% and 25%.² Survival rates for vulvovaginal melanomas are lower than for other types of vulvar cancers (72%) or for cutaneous melanomas (72%-81%).²

Racial disparities in survival rates for mucosal and cutaneous melanomas were highlighted in a retrospective study using the Surveillance Epidemiology and End Results (SEER) database. Although the number of Black patients included was small, the median overall survival in that population was less than that in non-Black patients with vulvovaginal melanoma (16 vs. 39 months). Similar findings were noted in Black patients with cutaneous melanoma, compared with non-Black patients (median overall survival, 124 vs 319 months).³

One of the most significant obstacles in the diagnosis of vulvar and vaginal melanoma is its rarity. Both patients and clinicians alike may fail to recognize early warning signs. In a world where skin cancer is heavily publicized, melanoma in the genital area is not as frequently discussed or understood. Postmenopausal patients may have less regular gynecologic care, and unless they present with specific symptoms prompting an exam, melanomas can grow undetected, progressing to more advanced stages before they are discovered.

The median age of patients diagnosed with vulvar and vaginal melanomas is 67-68.^4,5 Symptoms can be subtle and nonspecific. Women with vulvar melanoma may experience symptoms that are similar to other vulvar cancers including pruritus, irritation, pain, bleeding, or a new or growing mass. While vaginal melanoma can be asymptomatic, patients frequently present with vaginal bleeding, discharge, and/or pain (including dyspareunia).

Vulvovaginal melanomas may present differently than cutaneous melanomas. Vulvar melanomas are often pigmented and frequently present as ulcerated lesions. In some cases, though, they appear amelanotic (lacking pigment), making them even harder to identify. The ABCDEs of skin cancer (asymmetry, border, color, diameter, evolving) should be applied to these lesions. Change in the size, shape, or pigment of preexisting melanosis (areas of hyperpigmentation caused by increased melanin), should raise concern for possible malignant transformation. 

Most vaginal melanomas occur within the distal third of the vagina, frequently along the anterior vaginal wall.⁶ They can be polypoid or nodular in appearance and may be ulcerated. While biopsy of any suspicious, enlarging/changing, or symptomatic lesion should be performed, it may be prudent to pause prior to biopsy of a vaginal lesion depending on its appearance. Although rare, gestational trophoblastic neoplasia (GTN) can present with vaginal metastases, and these lesions are frequently very vascular and pose a high bleeding risk if biopsied. They may look dark blue or black. If there is any concern for metastatic GTN on vaginal exam, a beta-hCG level should be obtained prior to biopsy.

Treatment of vulvovaginal melanoma may include surgical excision, systemic therapy, radiation therapy, or a combination of treatments. There is growing use of immunotherapy that mirrors cutaneous melanoma therapy.

Vulvar and vaginal melanoma represent a rare yet serious health issue for women and their impact on public health should not be underestimated. Vulvovaginal melanoma often goes unrecognized until it has reached an advanced stage. Increased awareness about these rare forms of melanoma among both patients and healthcare professionals is vital to improve early detection and treatment outcomes. With greater attention to this disease, we can strive for better diagnostic methods, more effective treatments, and ultimately, a reduction in mortality rates associated with vulvar and vaginal melanoma.

Dr. Tucker is assistant professor of gynecologic oncology at the University of North Carolina at Chapel Hill. She has no conflicts of interest.

References

1. National Cancer Institute. Cancer Stat Facts: Melanoma of the skin. 2024 Dec 2. Available from: https://seer.cancer.gov/statfacts/html/melan.html.

2. Piura B. Lancet Oncol. 2008 Oct;9(10):973-81. .

3. Mert I et al. Int J Gynecol Cancer. 2013;23(6):1118-25.

4. Wang D et al. Am J Cancer Res. 2020 Dec 1;10(12):4017-37.

5. Albert A et al. J Gynecol Oncol. 2020 Sep;31(5):e66.

Cutaneous melanoma is a type of skin cancer typically associated with significant ultraviolet radiation exposure. Melanoma arises from melanocytes, cells found within the lower portion of the epidermis that make the pigment melanin.

While much less common than squamous cell carcinoma or basal cell carcinoma, melanoma is responsible for most deaths from skin cancer. In 2024, there will be more than 100,000 new cases of melanoma and over 8,000 melanoma-related deaths.¹ If localized at the time of diagnosis, survival rates are excellent. Cutaneous melanomas are more common in those with fair complexions or who have had long periods of exposure to natural or artificial sunlight.

Melanoma can also occur in mucous membranes. Mucosal melanoma is much less common than cutaneous melanoma and accounts for only a very small percentage of all new melanoma diagnoses. Unlike their cutaneous counterparts, risk factors for mucosal melanomas have yet to be identified. Although there is some disagreement on whether vulvar melanomas represent cutaneous or mucous melanomas, vulvovaginal melanomas have historically been considered to be mucosal melanomas.

Vulvovaginal melanomas are characterized by a high mortality rate, diagnostic challenges, and lack of awareness, making early detection and intervention crucial to improving patient outcomes. The 5-year overall survival rate for vulvar melanoma is 36% and for vaginal melanoma ranges between 5% and 25%.² Survival rates for vulvovaginal melanomas are lower than for other types of vulvar cancers (72%) or for cutaneous melanomas (72%-81%).²

Racial disparities in survival rates for mucosal and cutaneous melanomas were highlighted in a retrospective study using the Surveillance Epidemiology and End Results (SEER) database. Although the number of Black patients included was small, the median overall survival in that population was less than that in non-Black patients with vulvovaginal melanoma (16 vs. 39 months). Similar findings were noted in Black patients with cutaneous melanoma, compared with non-Black patients (median overall survival, 124 vs 319 months).³

One of the most significant obstacles in the diagnosis of vulvar and vaginal melanoma is its rarity. Both patients and clinicians alike may fail to recognize early warning signs. In a world where skin cancer is heavily publicized, melanoma in the genital area is not as frequently discussed or understood. Postmenopausal patients may have less regular gynecologic care, and unless they present with specific symptoms prompting an exam, melanomas can grow undetected, progressing to more advanced stages before they are discovered.

The median age of patients diagnosed with vulvar and vaginal melanomas is 67-68.^4,5 Symptoms can be subtle and nonspecific. Women with vulvar melanoma may experience symptoms that are similar to other vulvar cancers including pruritus, irritation, pain, bleeding, or a new or growing mass. While vaginal melanoma can be asymptomatic, patients frequently present with vaginal bleeding, discharge, and/or pain (including dyspareunia).

Vulvovaginal melanomas may present differently than cutaneous melanomas. Vulvar melanomas are often pigmented and frequently present as ulcerated lesions. In some cases, though, they appear amelanotic (lacking pigment), making them even harder to identify. The ABCDEs of skin cancer (asymmetry, border, color, diameter, evolving) should be applied to these lesions. Change in the size, shape, or pigment of preexisting melanosis (areas of hyperpigmentation caused by increased melanin), should raise concern for possible malignant transformation. 

Most vaginal melanomas occur within the distal third of the vagina, frequently along the anterior vaginal wall.⁶ They can be polypoid or nodular in appearance and may be ulcerated. While biopsy of any suspicious, enlarging/changing, or symptomatic lesion should be performed, it may be prudent to pause prior to biopsy of a vaginal lesion depending on its appearance. Although rare, gestational trophoblastic neoplasia (GTN) can present with vaginal metastases, and these lesions are frequently very vascular and pose a high bleeding risk if biopsied. They may look dark blue or black. If there is any concern for metastatic GTN on vaginal exam, a beta-hCG level should be obtained prior to biopsy.

Treatment of vulvovaginal melanoma may include surgical excision, systemic therapy, radiation therapy, or a combination of treatments. There is growing use of immunotherapy that mirrors cutaneous melanoma therapy.

Vulvar and vaginal melanoma represent a rare yet serious health issue for women and their impact on public health should not be underestimated. Vulvovaginal melanoma often goes unrecognized until it has reached an advanced stage. Increased awareness about these rare forms of melanoma among both patients and healthcare professionals is vital to improve early detection and treatment outcomes. With greater attention to this disease, we can strive for better diagnostic methods, more effective treatments, and ultimately, a reduction in mortality rates associated with vulvar and vaginal melanoma.

Dr. Tucker is assistant professor of gynecologic oncology at the University of North Carolina at Chapel Hill. She has no conflicts of interest.

References

1. National Cancer Institute. Cancer Stat Facts: Melanoma of the skin. 2024 Dec 2. Available from: https://seer.cancer.gov/statfacts/html/melan.html.

2. Piura B. Lancet Oncol. 2008 Oct;9(10):973-81. .

3. Mert I et al. Int J Gynecol Cancer. 2013;23(6):1118-25.

4. Wang D et al. Am J Cancer Res. 2020 Dec 1;10(12):4017-37.

5. Albert A et al. J Gynecol Oncol. 2020 Sep;31(5):e66.

Cutaneous melanoma is a type of skin cancer typically associated with significant ultraviolet radiation exposure. Melanoma arises from melanocytes, cells found within the lower portion of the epidermis that make the pigment melanin.

While much less common than squamous cell carcinoma or basal cell carcinoma, melanoma is responsible for most deaths from skin cancer. In 2024, there will be more than 100,000 new cases of melanoma and over 8,000 melanoma-related deaths.¹ If localized at the time of diagnosis, survival rates are excellent. Cutaneous melanomas are more common in those with fair complexions or who have had long periods of exposure to natural or artificial sunlight.

Melanoma can also occur in mucous membranes. Mucosal melanoma is much less common than cutaneous melanoma and accounts for only a very small percentage of all new melanoma diagnoses. Unlike their cutaneous counterparts, risk factors for mucosal melanomas have yet to be identified. Although there is some disagreement on whether vulvar melanomas represent cutaneous or mucous melanomas, vulvovaginal melanomas have historically been considered to be mucosal melanomas.

Vulvovaginal melanomas are characterized by a high mortality rate, diagnostic challenges, and lack of awareness, making early detection and intervention crucial to improving patient outcomes. The 5-year overall survival rate for vulvar melanoma is 36% and for vaginal melanoma ranges between 5% and 25%.² Survival rates for vulvovaginal melanomas are lower than for other types of vulvar cancers (72%) or for cutaneous melanomas (72%-81%).²

Racial disparities in survival rates for mucosal and cutaneous melanomas were highlighted in a retrospective study using the Surveillance Epidemiology and End Results (SEER) database. Although the number of Black patients included was small, the median overall survival in that population was less than that in non-Black patients with vulvovaginal melanoma (16 vs. 39 months). Similar findings were noted in Black patients with cutaneous melanoma, compared with non-Black patients (median overall survival, 124 vs 319 months).³

One of the most significant obstacles in the diagnosis of vulvar and vaginal melanoma is its rarity. Both patients and clinicians alike may fail to recognize early warning signs. In a world where skin cancer is heavily publicized, melanoma in the genital area is not as frequently discussed or understood. Postmenopausal patients may have less regular gynecologic care, and unless they present with specific symptoms prompting an exam, melanomas can grow undetected, progressing to more advanced stages before they are discovered.

The median age of patients diagnosed with vulvar and vaginal melanomas is 67-68.^4,5 Symptoms can be subtle and nonspecific. Women with vulvar melanoma may experience symptoms that are similar to other vulvar cancers including pruritus, irritation, pain, bleeding, or a new or growing mass. While vaginal melanoma can be asymptomatic, patients frequently present with vaginal bleeding, discharge, and/or pain (including dyspareunia).

Vulvovaginal melanomas may present differently than cutaneous melanomas. Vulvar melanomas are often pigmented and frequently present as ulcerated lesions. In some cases, though, they appear amelanotic (lacking pigment), making them even harder to identify. The ABCDEs of skin cancer (asymmetry, border, color, diameter, evolving) should be applied to these lesions. Change in the size, shape, or pigment of preexisting melanosis (areas of hyperpigmentation caused by increased melanin), should raise concern for possible malignant transformation. 

Most vaginal melanomas occur within the distal third of the vagina, frequently along the anterior vaginal wall.⁶ They can be polypoid or nodular in appearance and may be ulcerated. While biopsy of any suspicious, enlarging/changing, or symptomatic lesion should be performed, it may be prudent to pause prior to biopsy of a vaginal lesion depending on its appearance. Although rare, gestational trophoblastic neoplasia (GTN) can present with vaginal metastases, and these lesions are frequently very vascular and pose a high bleeding risk if biopsied. They may look dark blue or black. If there is any concern for metastatic GTN on vaginal exam, a beta-hCG level should be obtained prior to biopsy.

Treatment of vulvovaginal melanoma may include surgical excision, systemic therapy, radiation therapy, or a combination of treatments. There is growing use of immunotherapy that mirrors cutaneous melanoma therapy.

Vulvar and vaginal melanoma represent a rare yet serious health issue for women and their impact on public health should not be underestimated. Vulvovaginal melanoma often goes unrecognized until it has reached an advanced stage. Increased awareness about these rare forms of melanoma among both patients and healthcare professionals is vital to improve early detection and treatment outcomes. With greater attention to this disease, we can strive for better diagnostic methods, more effective treatments, and ultimately, a reduction in mortality rates associated with vulvar and vaginal melanoma.

Dr. Tucker is assistant professor of gynecologic oncology at the University of North Carolina at Chapel Hill. She has no conflicts of interest.

References

1. National Cancer Institute. Cancer Stat Facts: Melanoma of the skin. 2024 Dec 2. Available from: https://seer.cancer.gov/statfacts/html/melan.html.

2. Piura B. Lancet Oncol. 2008 Oct;9(10):973-81. .

3. Mert I et al. Int J Gynecol Cancer. 2013;23(6):1118-25.

4. Wang D et al. Am J Cancer Res. 2020 Dec 1;10(12):4017-37.

5. Albert A et al. J Gynecol Oncol. 2020 Sep;31(5):e66.

TOPLINE:

Survivors of blood or marrow transplant (BMT) face a significant risk of developing cutaneous malignant neoplasms, including basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanoma, with a cumulative incidence of 27.4% over 30 years, according to the results of a cohort study.

METHODOLOGY:

• The retrospective cohort study included 3880 BMT survivors (median age, 44 years; 55.8% men; 4.9% Black, 12.1 Hispanic, and 74.7% non-Hispanic White individuals) who underwent transplant between 1974 to 2014.
• Participants completed the BMT Survivor Study survey and were followed up for a median of 9.5 years.
• The primary outcomes were the development of subsequent cutaneous malignant neoplasms (BCC, SCC, or melanoma).

TAKEAWAY:

• The 30-year cumulative incidence of any cutaneous malignant neoplasm was 27.4% — 18% for BCC, 9.8% for SCC, and 3.7% for melanoma.
• A higher risk for skin cancer was reported for patients aged 50 years or more (subdistribution hazard ratio [SHR], 2.23; 95% CI, 1.83-2.71), and men (SHR, 1.40; 95% CI, 1.18-1.65).
• Allogeneic BMT with chronic graft-vs-host disease (cGVHD) increased the risk for skin cancer (SHR, 1.84; 95% CI, 1.37-2.47), compared with autologous BMT, while post-BMT immunosuppression increased risk for all types (overall SHR, 1.53; 95% CI, 1.26-1.86).
• The risk for any skin cancer was significantly lower in Black individuals (SHR, 0.14; 95% CI, 0.05-0.37), Hispanic individuals (SHR, 0.29; 95%CI, 0.20-0.62), and patients of other races or who were multiracial (SHR, 0.22; 95% CI, 0.13-0.37) than in non-Hispanic White patients.

IN PRACTICE:

In the study, “risk factors for post-BMT cutaneous malignant neoplasms included pretransplant treatment with a monoclonal antibody, cGVHD, and posttransplant immunosuppression,” the authors wrote, adding that the findings “could inform targeted surveillance of BMT survivors.” Most BMT survivors, “do not undergo routine dermatologic surveillance, highlighting the need to understand risk factors and incorporate risk-informed dermatologic surveillance into survivorship care plans.”

SOURCE:

The study was led by Kristy K. Broman, MD, MPH, University of Alabama at Birmingham, and was published online on December 18 in JAMA Dermatology.

LIMITATIONS:

Limitations included self-reported data and possible underreporting of melanoma cases in the SEER database. Additionally, the study did not capture other risk factors for cutaneous malignant neoplasms such as skin phototype, ultraviolet light exposure, or family history. The duration of posttransplant immunosuppression was not collected, and surveys were administered at variable intervals, though all were completed more than 2 years post BMT.

DISCLOSURES:

The study was supported by the National Cancer Institute (NCI) and the Leukemia and Lymphoma Society. Broman received grants from NCI, the National Center for Advancing Translational Sciences, the American Society of Clinical Oncology, and the American College of Surgeons. Another author reported receiving grants outside this work.

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

TOPLINE:

Survivors of blood or marrow transplant (BMT) face a significant risk of developing cutaneous malignant neoplasms, including basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanoma, with a cumulative incidence of 27.4% over 30 years, according to the results of a cohort study.

METHODOLOGY:

• The retrospective cohort study included 3880 BMT survivors (median age, 44 years; 55.8% men; 4.9% Black, 12.1 Hispanic, and 74.7% non-Hispanic White individuals) who underwent transplant between 1974 to 2014.
• Participants completed the BMT Survivor Study survey and were followed up for a median of 9.5 years.
• The primary outcomes were the development of subsequent cutaneous malignant neoplasms (BCC, SCC, or melanoma).

TAKEAWAY:

• The 30-year cumulative incidence of any cutaneous malignant neoplasm was 27.4% — 18% for BCC, 9.8% for SCC, and 3.7% for melanoma.
• A higher risk for skin cancer was reported for patients aged 50 years or more (subdistribution hazard ratio [SHR], 2.23; 95% CI, 1.83-2.71), and men (SHR, 1.40; 95% CI, 1.18-1.65).
• Allogeneic BMT with chronic graft-vs-host disease (cGVHD) increased the risk for skin cancer (SHR, 1.84; 95% CI, 1.37-2.47), compared with autologous BMT, while post-BMT immunosuppression increased risk for all types (overall SHR, 1.53; 95% CI, 1.26-1.86).
• The risk for any skin cancer was significantly lower in Black individuals (SHR, 0.14; 95% CI, 0.05-0.37), Hispanic individuals (SHR, 0.29; 95%CI, 0.20-0.62), and patients of other races or who were multiracial (SHR, 0.22; 95% CI, 0.13-0.37) than in non-Hispanic White patients.

IN PRACTICE:

In the study, “risk factors for post-BMT cutaneous malignant neoplasms included pretransplant treatment with a monoclonal antibody, cGVHD, and posttransplant immunosuppression,” the authors wrote, adding that the findings “could inform targeted surveillance of BMT survivors.” Most BMT survivors, “do not undergo routine dermatologic surveillance, highlighting the need to understand risk factors and incorporate risk-informed dermatologic surveillance into survivorship care plans.”

SOURCE:

The study was led by Kristy K. Broman, MD, MPH, University of Alabama at Birmingham, and was published online on December 18 in JAMA Dermatology.

LIMITATIONS:

Limitations included self-reported data and possible underreporting of melanoma cases in the SEER database. Additionally, the study did not capture other risk factors for cutaneous malignant neoplasms such as skin phototype, ultraviolet light exposure, or family history. The duration of posttransplant immunosuppression was not collected, and surveys were administered at variable intervals, though all were completed more than 2 years post BMT.

DISCLOSURES:

The study was supported by the National Cancer Institute (NCI) and the Leukemia and Lymphoma Society. Broman received grants from NCI, the National Center for Advancing Translational Sciences, the American Society of Clinical Oncology, and the American College of Surgeons. Another author reported receiving grants outside this work.

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

TOPLINE:

Survivors of blood or marrow transplant (BMT) face a significant risk of developing cutaneous malignant neoplasms, including basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanoma, with a cumulative incidence of 27.4% over 30 years, according to the results of a cohort study.

METHODOLOGY:

• The retrospective cohort study included 3880 BMT survivors (median age, 44 years; 55.8% men; 4.9% Black, 12.1 Hispanic, and 74.7% non-Hispanic White individuals) who underwent transplant between 1974 to 2014.
• Participants completed the BMT Survivor Study survey and were followed up for a median of 9.5 years.
• The primary outcomes were the development of subsequent cutaneous malignant neoplasms (BCC, SCC, or melanoma).

TAKEAWAY:

• The 30-year cumulative incidence of any cutaneous malignant neoplasm was 27.4% — 18% for BCC, 9.8% for SCC, and 3.7% for melanoma.
• A higher risk for skin cancer was reported for patients aged 50 years or more (subdistribution hazard ratio [SHR], 2.23; 95% CI, 1.83-2.71), and men (SHR, 1.40; 95% CI, 1.18-1.65).
• Allogeneic BMT with chronic graft-vs-host disease (cGVHD) increased the risk for skin cancer (SHR, 1.84; 95% CI, 1.37-2.47), compared with autologous BMT, while post-BMT immunosuppression increased risk for all types (overall SHR, 1.53; 95% CI, 1.26-1.86).
• The risk for any skin cancer was significantly lower in Black individuals (SHR, 0.14; 95% CI, 0.05-0.37), Hispanic individuals (SHR, 0.29; 95%CI, 0.20-0.62), and patients of other races or who were multiracial (SHR, 0.22; 95% CI, 0.13-0.37) than in non-Hispanic White patients.

IN PRACTICE:

In the study, “risk factors for post-BMT cutaneous malignant neoplasms included pretransplant treatment with a monoclonal antibody, cGVHD, and posttransplant immunosuppression,” the authors wrote, adding that the findings “could inform targeted surveillance of BMT survivors.” Most BMT survivors, “do not undergo routine dermatologic surveillance, highlighting the need to understand risk factors and incorporate risk-informed dermatologic surveillance into survivorship care plans.”

SOURCE:

The study was led by Kristy K. Broman, MD, MPH, University of Alabama at Birmingham, and was published online on December 18 in JAMA Dermatology.

LIMITATIONS:

Limitations included self-reported data and possible underreporting of melanoma cases in the SEER database. Additionally, the study did not capture other risk factors for cutaneous malignant neoplasms such as skin phototype, ultraviolet light exposure, or family history. The duration of posttransplant immunosuppression was not collected, and surveys were administered at variable intervals, though all were completed more than 2 years post BMT.

DISCLOSURES:

The study was supported by the National Cancer Institute (NCI) and the Leukemia and Lymphoma Society. Broman received grants from NCI, the National Center for Advancing Translational Sciences, the American Society of Clinical Oncology, and the American College of Surgeons. Another author reported receiving grants outside this work.

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

The question has been lingering for years in medical science circles. Since 2020, when the artificial intelligence (AI) model AlphaFold made it possible to predict protein structures, would the technology open the drug discovery floodgates?

Short answer: No. At least not yet.

The longer answer goes something like this:

A drug target (such as a mutation) is like a lock. The right drug (a protein designed to bind to the mutation, stopping its activity) is the key. But proteins are fidgety and flexible.

“They’re basically molecular springs,” said Gabriel Monteiro da Silva, PhD, a computational chemistry research scientist at Genesis Therapeutics. “Your key can bend and alter the shape of the lock, and if you don’t account for that, your key might fail.”

This is the protein problem in drug development. Another issue making this challenge so vexing is that proteins don’t act in isolation. Their interactions with other proteins, ribonucleic acid, and DNA can affect how they bind to molecules and the shapes they adopt.

Newer versions of AlphaFold, such as AlphaFold Multimer and AlphaFold 3 (the code for which was recently revealed for academic use), can predict many interactions among proteins and between proteins and other molecules. But these tools still have weak points scientists are trying to overcome or work around.

“Those kinds of dynamics and multiple conformations are still quite challenging for the AI models to predict,” said James Zou, PhD, associate professor of biomedical data science at Stanford University in California.

“We’re finding more and more that the only way we can make these structures useful for drug discovery is if we incorporate dynamics, if we incorporate more physics into the model,” said Monteiro da Silva.

Monteiro da Silva spent 3 years during his PhD at Brown University, Providence, Rhode Island, running physics-based simulations in the lab, trying to understand why proteins carrying certain mutations are drug resistant. His results showed how “the changing landscape of shapes that a protein can take” prevented the drug from binding.

It took him 3 years to model just four mutations.

AI can do better — and the struggle is fascinating. By developing models that build on the predictive power of AlphaFold, scientists are uncovering new details about protein activity — insights that can lead to new therapeutics and reveal why existing ones stop working — much faster than they could with traditional methods or AlphaFold alone.

 

New Windows into Protein Dynamics

By predicting protein structural details, AlphaFold models also made it possible to predict pockets where drugs could bind.

A notable step, “but that’s just the starting point,” said Pedro Beltrao, PhD, an associate professor at Institute of Molecular Systems Biology, ETH Zurich in Switzerland. “It’s still very difficult, given a pocket, to actually design the drug or figure out what the pocket binds.”

Going back to the lock-and-key analogy: While he was at Brown, with a team of researchers in the Rubenstein Group, Monteiro da Silva helped create a model to better understand how mutations affect “the shape and dynamics of the lock.” They manipulated the amino acid sequences of proteins, guiding their evolution. This enabled them to use AlphaFold to predict “protein ensembles” and how frequently those ensembles appear. Each ensemble represents the many different shapes a protein can take under given conditions.

“Essentially, it tries to find the most common shapes that a protein will take over an arbitrary amount of time,” Monteiro da Silva said. “If we can predict these ensembles at scale and fast, then we can screen many mutations that cause resistance and develop drugs that will not be affected by that resistance.”

To evaluate their method, the researchers focused on ABL1, a well-studied kinase that causes leukemia. ABL1 can be drugged – unless it carries or develops a mutation that causes drug resistance. Currently there are no drugs that work against proteins carrying those mutations, according to Monteiro da Silva. The researchers used their hybrid AI-meets-physics method to investigate how drugs bind to different ABL1 mutations, screening 100 mutations in just 1 month.

“It’s not going to be perfect for every one of them. But if we have 100 and we get 20 with good accuracy, that’s better than doing four over 3 years,” Monteiro da Silva said.

A forthcoming paper will make their model publicly available in “an easy-to-use graphical interface” that they hope clinicians and medicinal chemists will try out. It can also complement other AI-based tools that dig into protein dynamics, according to Monteiro da Silva.

 

Complementary Tools to Speed Up Discovery 

Another aspect of the protein problem is scale. One protein can interact with hundreds of other proteins, which in turn may interact with hundreds more, all of which comprise the human interactome.

Feixiong Cheng, PhD, helped build PIONEER, a deep learning model that predicts the three-dimensional (3D) structure of interactions between proteins across the interactome.

Most disease mutations disrupt specific interactions between proteins, making their affinity stronger or weaker, explained Cheng. To treat a disease without causing major side effects, scientists need a precise understanding of those interactions.

“From the drug discovery perspective, we cannot just focus on single proteins. We have to understand the protein environment, in particular how the protein interacts with other proteins,” said Cheng, director of Cleveland Clinic Genome Center, Cleveland.

PIONEER helps by blending AlphaFold’s protein structure predictions with next-generation sequencing, a type of genomic research that identifies mutations in the human genome. The model predicts the 3D structure of the places where proteins interact — the binding sites, or interfaces — across the interactome.

“We tell you not only that a binds b, but where on a and where on b the two proteins interact,” said Haiyuan Yu, PhD, director of the Center for Innovative Proteomics, Cornell University, and co-creator of PIONEER.

This can help scientists understand “why a mutation, protein, or even network is a good target for therapeutic discovery,” Cheng said.

The researchers validated PIONEER’s predictions in the lab, testing the impacts of roughly 3000 mutations on 7000 pairs of interacting proteins. Based on their findings, they plan to develop and test treatments for lung and endometrial cancer.

PIONEER can also help scientists home in on how a mutation causes a disease, such as by showing recurrent mutations.

“If you find cancer mutations hitting an interface again and again and again, it means that this is likely to be driving cancer progression,” said Beltrao.

Beltrao’s lab and others have looked for recurrent mutations by using AlphaFold Multimer and AlphaFold 3 to directly model protein interactions. It’s a much slower approach (Pioneer is more than 5000 faster than AlphaFold Multimer, according to Cheng). But it could allow scientists to model interfaces that are not shown by PIONEER.

“You will need many different things to try to come up with a structural modeling of the interactome, and all these will have limitations,” said Beltrao. “Their method is a very good step forward, and there’ll be other approaches that are complementary, to continue to add details.”

 

And It Wouldn’t be an AI Mission Without ChatGPT

Large language models, such as ChatGPT, are another way that scientists are adding details to protein structure predictions. Zou used GPT-4 to “fine tune” a protein language model, called evolutionary scale modeling (ESM-2), which predicts protein structures directly from a protein sequence.

First, they trained ChatGPT on thousands of papers and studies containing information about the functions, biophysical properties, and disease relevance of different mutations. Next, they used the trained model to “teach” ESM-2, boosting its ability “to predict which mutations are likely to have larger effects or smaller effects,” Zou said. The same could be done for a model like AlphaFold, according to Zou.

“They are quite complementary in that the large language model contains a lot more information about the functions and the biophysics of different mutations and proteins as captured in text,” he said, whereas “you can’t give AlphaFold a piece of paper.”

Exactly how AlphaFold makes its predictions is another mystery. “It will somehow learn protein dynamics phenomenologically,” said Monteiro da Silva. He and others are trying to understand how that happens, in hopes of creating even more accurate predictive models. But for the time being, AI-based methods still need assistance from physics.

“The dream is that we achieve a state where we rely on just the fast methods, and they’re accurate enough,” he said. “But we’re so far from that.”

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

The question has been lingering for years in medical science circles. Since 2020, when the artificial intelligence (AI) model AlphaFold made it possible to predict protein structures, would the technology open the drug discovery floodgates?

Short answer: No. At least not yet.

The longer answer goes something like this:

A drug target (such as a mutation) is like a lock. The right drug (a protein designed to bind to the mutation, stopping its activity) is the key. But proteins are fidgety and flexible.

“They’re basically molecular springs,” said Gabriel Monteiro da Silva, PhD, a computational chemistry research scientist at Genesis Therapeutics. “Your key can bend and alter the shape of the lock, and if you don’t account for that, your key might fail.”

This is the protein problem in drug development. Another issue making this challenge so vexing is that proteins don’t act in isolation. Their interactions with other proteins, ribonucleic acid, and DNA can affect how they bind to molecules and the shapes they adopt.

Newer versions of AlphaFold, such as AlphaFold Multimer and AlphaFold 3 (the code for which was recently revealed for academic use), can predict many interactions among proteins and between proteins and other molecules. But these tools still have weak points scientists are trying to overcome or work around.

“Those kinds of dynamics and multiple conformations are still quite challenging for the AI models to predict,” said James Zou, PhD, associate professor of biomedical data science at Stanford University in California.

“We’re finding more and more that the only way we can make these structures useful for drug discovery is if we incorporate dynamics, if we incorporate more physics into the model,” said Monteiro da Silva.

Monteiro da Silva spent 3 years during his PhD at Brown University, Providence, Rhode Island, running physics-based simulations in the lab, trying to understand why proteins carrying certain mutations are drug resistant. His results showed how “the changing landscape of shapes that a protein can take” prevented the drug from binding.

It took him 3 years to model just four mutations.

AI can do better — and the struggle is fascinating. By developing models that build on the predictive power of AlphaFold, scientists are uncovering new details about protein activity — insights that can lead to new therapeutics and reveal why existing ones stop working — much faster than they could with traditional methods or AlphaFold alone.

 

New Windows into Protein Dynamics

By predicting protein structural details, AlphaFold models also made it possible to predict pockets where drugs could bind.

A notable step, “but that’s just the starting point,” said Pedro Beltrao, PhD, an associate professor at Institute of Molecular Systems Biology, ETH Zurich in Switzerland. “It’s still very difficult, given a pocket, to actually design the drug or figure out what the pocket binds.”

Going back to the lock-and-key analogy: While he was at Brown, with a team of researchers in the Rubenstein Group, Monteiro da Silva helped create a model to better understand how mutations affect “the shape and dynamics of the lock.” They manipulated the amino acid sequences of proteins, guiding their evolution. This enabled them to use AlphaFold to predict “protein ensembles” and how frequently those ensembles appear. Each ensemble represents the many different shapes a protein can take under given conditions.

“Essentially, it tries to find the most common shapes that a protein will take over an arbitrary amount of time,” Monteiro da Silva said. “If we can predict these ensembles at scale and fast, then we can screen many mutations that cause resistance and develop drugs that will not be affected by that resistance.”

To evaluate their method, the researchers focused on ABL1, a well-studied kinase that causes leukemia. ABL1 can be drugged – unless it carries or develops a mutation that causes drug resistance. Currently there are no drugs that work against proteins carrying those mutations, according to Monteiro da Silva. The researchers used their hybrid AI-meets-physics method to investigate how drugs bind to different ABL1 mutations, screening 100 mutations in just 1 month.

“It’s not going to be perfect for every one of them. But if we have 100 and we get 20 with good accuracy, that’s better than doing four over 3 years,” Monteiro da Silva said.

A forthcoming paper will make their model publicly available in “an easy-to-use graphical interface” that they hope clinicians and medicinal chemists will try out. It can also complement other AI-based tools that dig into protein dynamics, according to Monteiro da Silva.

 

Complementary Tools to Speed Up Discovery 

Another aspect of the protein problem is scale. One protein can interact with hundreds of other proteins, which in turn may interact with hundreds more, all of which comprise the human interactome.

Feixiong Cheng, PhD, helped build PIONEER, a deep learning model that predicts the three-dimensional (3D) structure of interactions between proteins across the interactome.

Most disease mutations disrupt specific interactions between proteins, making their affinity stronger or weaker, explained Cheng. To treat a disease without causing major side effects, scientists need a precise understanding of those interactions.

“From the drug discovery perspective, we cannot just focus on single proteins. We have to understand the protein environment, in particular how the protein interacts with other proteins,” said Cheng, director of Cleveland Clinic Genome Center, Cleveland.

PIONEER helps by blending AlphaFold’s protein structure predictions with next-generation sequencing, a type of genomic research that identifies mutations in the human genome. The model predicts the 3D structure of the places where proteins interact — the binding sites, or interfaces — across the interactome.

“We tell you not only that a binds b, but where on a and where on b the two proteins interact,” said Haiyuan Yu, PhD, director of the Center for Innovative Proteomics, Cornell University, and co-creator of PIONEER.

This can help scientists understand “why a mutation, protein, or even network is a good target for therapeutic discovery,” Cheng said.

The researchers validated PIONEER’s predictions in the lab, testing the impacts of roughly 3000 mutations on 7000 pairs of interacting proteins. Based on their findings, they plan to develop and test treatments for lung and endometrial cancer.

PIONEER can also help scientists home in on how a mutation causes a disease, such as by showing recurrent mutations.

“If you find cancer mutations hitting an interface again and again and again, it means that this is likely to be driving cancer progression,” said Beltrao.

Beltrao’s lab and others have looked for recurrent mutations by using AlphaFold Multimer and AlphaFold 3 to directly model protein interactions. It’s a much slower approach (Pioneer is more than 5000 faster than AlphaFold Multimer, according to Cheng). But it could allow scientists to model interfaces that are not shown by PIONEER.

“You will need many different things to try to come up with a structural modeling of the interactome, and all these will have limitations,” said Beltrao. “Their method is a very good step forward, and there’ll be other approaches that are complementary, to continue to add details.”

 

And It Wouldn’t be an AI Mission Without ChatGPT

Large language models, such as ChatGPT, are another way that scientists are adding details to protein structure predictions. Zou used GPT-4 to “fine tune” a protein language model, called evolutionary scale modeling (ESM-2), which predicts protein structures directly from a protein sequence.

First, they trained ChatGPT on thousands of papers and studies containing information about the functions, biophysical properties, and disease relevance of different mutations. Next, they used the trained model to “teach” ESM-2, boosting its ability “to predict which mutations are likely to have larger effects or smaller effects,” Zou said. The same could be done for a model like AlphaFold, according to Zou.

“They are quite complementary in that the large language model contains a lot more information about the functions and the biophysics of different mutations and proteins as captured in text,” he said, whereas “you can’t give AlphaFold a piece of paper.”

Exactly how AlphaFold makes its predictions is another mystery. “It will somehow learn protein dynamics phenomenologically,” said Monteiro da Silva. He and others are trying to understand how that happens, in hopes of creating even more accurate predictive models. But for the time being, AI-based methods still need assistance from physics.

“The dream is that we achieve a state where we rely on just the fast methods, and they’re accurate enough,” he said. “But we’re so far from that.”

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

The question has been lingering for years in medical science circles. Since 2020, when the artificial intelligence (AI) model AlphaFold made it possible to predict protein structures, would the technology open the drug discovery floodgates?

Short answer: No. At least not yet.

The longer answer goes something like this:

A drug target (such as a mutation) is like a lock. The right drug (a protein designed to bind to the mutation, stopping its activity) is the key. But proteins are fidgety and flexible.

“They’re basically molecular springs,” said Gabriel Monteiro da Silva, PhD, a computational chemistry research scientist at Genesis Therapeutics. “Your key can bend and alter the shape of the lock, and if you don’t account for that, your key might fail.”

This is the protein problem in drug development. Another issue making this challenge so vexing is that proteins don’t act in isolation. Their interactions with other proteins, ribonucleic acid, and DNA can affect how they bind to molecules and the shapes they adopt.

Newer versions of AlphaFold, such as AlphaFold Multimer and AlphaFold 3 (the code for which was recently revealed for academic use), can predict many interactions among proteins and between proteins and other molecules. But these tools still have weak points scientists are trying to overcome or work around.

“Those kinds of dynamics and multiple conformations are still quite challenging for the AI models to predict,” said James Zou, PhD, associate professor of biomedical data science at Stanford University in California.

“We’re finding more and more that the only way we can make these structures useful for drug discovery is if we incorporate dynamics, if we incorporate more physics into the model,” said Monteiro da Silva.

Monteiro da Silva spent 3 years during his PhD at Brown University, Providence, Rhode Island, running physics-based simulations in the lab, trying to understand why proteins carrying certain mutations are drug resistant. His results showed how “the changing landscape of shapes that a protein can take” prevented the drug from binding.

It took him 3 years to model just four mutations.

AI can do better — and the struggle is fascinating. By developing models that build on the predictive power of AlphaFold, scientists are uncovering new details about protein activity — insights that can lead to new therapeutics and reveal why existing ones stop working — much faster than they could with traditional methods or AlphaFold alone.

 

New Windows into Protein Dynamics

By predicting protein structural details, AlphaFold models also made it possible to predict pockets where drugs could bind.

A notable step, “but that’s just the starting point,” said Pedro Beltrao, PhD, an associate professor at Institute of Molecular Systems Biology, ETH Zurich in Switzerland. “It’s still very difficult, given a pocket, to actually design the drug or figure out what the pocket binds.”

Going back to the lock-and-key analogy: While he was at Brown, with a team of researchers in the Rubenstein Group, Monteiro da Silva helped create a model to better understand how mutations affect “the shape and dynamics of the lock.” They manipulated the amino acid sequences of proteins, guiding their evolution. This enabled them to use AlphaFold to predict “protein ensembles” and how frequently those ensembles appear. Each ensemble represents the many different shapes a protein can take under given conditions.

“Essentially, it tries to find the most common shapes that a protein will take over an arbitrary amount of time,” Monteiro da Silva said. “If we can predict these ensembles at scale and fast, then we can screen many mutations that cause resistance and develop drugs that will not be affected by that resistance.”

To evaluate their method, the researchers focused on ABL1, a well-studied kinase that causes leukemia. ABL1 can be drugged – unless it carries or develops a mutation that causes drug resistance. Currently there are no drugs that work against proteins carrying those mutations, according to Monteiro da Silva. The researchers used their hybrid AI-meets-physics method to investigate how drugs bind to different ABL1 mutations, screening 100 mutations in just 1 month.

“It’s not going to be perfect for every one of them. But if we have 100 and we get 20 with good accuracy, that’s better than doing four over 3 years,” Monteiro da Silva said.

A forthcoming paper will make their model publicly available in “an easy-to-use graphical interface” that they hope clinicians and medicinal chemists will try out. It can also complement other AI-based tools that dig into protein dynamics, according to Monteiro da Silva.

 

Complementary Tools to Speed Up Discovery 

Another aspect of the protein problem is scale. One protein can interact with hundreds of other proteins, which in turn may interact with hundreds more, all of which comprise the human interactome.

Feixiong Cheng, PhD, helped build PIONEER, a deep learning model that predicts the three-dimensional (3D) structure of interactions between proteins across the interactome.

Most disease mutations disrupt specific interactions between proteins, making their affinity stronger or weaker, explained Cheng. To treat a disease without causing major side effects, scientists need a precise understanding of those interactions.

“From the drug discovery perspective, we cannot just focus on single proteins. We have to understand the protein environment, in particular how the protein interacts with other proteins,” said Cheng, director of Cleveland Clinic Genome Center, Cleveland.

PIONEER helps by blending AlphaFold’s protein structure predictions with next-generation sequencing, a type of genomic research that identifies mutations in the human genome. The model predicts the 3D structure of the places where proteins interact — the binding sites, or interfaces — across the interactome.

“We tell you not only that a binds b, but where on a and where on b the two proteins interact,” said Haiyuan Yu, PhD, director of the Center for Innovative Proteomics, Cornell University, and co-creator of PIONEER.

This can help scientists understand “why a mutation, protein, or even network is a good target for therapeutic discovery,” Cheng said.

The researchers validated PIONEER’s predictions in the lab, testing the impacts of roughly 3000 mutations on 7000 pairs of interacting proteins. Based on their findings, they plan to develop and test treatments for lung and endometrial cancer.

PIONEER can also help scientists home in on how a mutation causes a disease, such as by showing recurrent mutations.

“If you find cancer mutations hitting an interface again and again and again, it means that this is likely to be driving cancer progression,” said Beltrao.

Beltrao’s lab and others have looked for recurrent mutations by using AlphaFold Multimer and AlphaFold 3 to directly model protein interactions. It’s a much slower approach (Pioneer is more than 5000 faster than AlphaFold Multimer, according to Cheng). But it could allow scientists to model interfaces that are not shown by PIONEER.

“You will need many different things to try to come up with a structural modeling of the interactome, and all these will have limitations,” said Beltrao. “Their method is a very good step forward, and there’ll be other approaches that are complementary, to continue to add details.”

 

And It Wouldn’t be an AI Mission Without ChatGPT

Large language models, such as ChatGPT, are another way that scientists are adding details to protein structure predictions. Zou used GPT-4 to “fine tune” a protein language model, called evolutionary scale modeling (ESM-2), which predicts protein structures directly from a protein sequence.

First, they trained ChatGPT on thousands of papers and studies containing information about the functions, biophysical properties, and disease relevance of different mutations. Next, they used the trained model to “teach” ESM-2, boosting its ability “to predict which mutations are likely to have larger effects or smaller effects,” Zou said. The same could be done for a model like AlphaFold, according to Zou.

“They are quite complementary in that the large language model contains a lot more information about the functions and the biophysics of different mutations and proteins as captured in text,” he said, whereas “you can’t give AlphaFold a piece of paper.”

Exactly how AlphaFold makes its predictions is another mystery. “It will somehow learn protein dynamics phenomenologically,” said Monteiro da Silva. He and others are trying to understand how that happens, in hopes of creating even more accurate predictive models. But for the time being, AI-based methods still need assistance from physics.

“The dream is that we achieve a state where we rely on just the fast methods, and they’re accurate enough,” he said. “But we’re so far from that.”

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

This transcript has been edited for clarity. 

I would like to briefly talk about a very interesting paper and one that probably has about as much to inform the doctor-patient relationship as any paper you can think of. 

The title itself gives you a little bit of that answer before I even discuss the outcome. The paper is “The Benefits of Quitting Smoking at Different Ages,” recently published in The American Journal of Preventive Medicine.

I’m not going to even begin to attempt to explore the statistics of the analysis, but I think the conclusions are both fascinating and important. I will read the first sentence of the results and then just comment on some of the others because there’s just so much data here and I really want to focus on the punchline. 

The results section said that, compared with people who never smoked, those who smoke currently, aged 35, 45, 55, 65, or 75, (those were all the groups they looked at), and who have smoked throughout adulthood until that age will lose an average of 9.1, 8.3, 7.3, 5.9, and 4.4 years of life, respectively — obviously, it’s a lot — if they continue to smoke for the rest of their lives. 

If somebody is smoking at age 35 and they continue to smoke, they could lose 9 years of life on average. We know that. It’s terrible. That’s why people should never smoke. Period. End of story. There’s no social value. There’s no health value of smoking. It’s a deadly recreational activity for multiple illnesses, and obviously, cancer is prominent among them.

Here’s the conclusion of the paper that I think is interesting. That doctor, whether it’s a primary care doctor, an oncologist, an ob/gyn, or a family doctor, is seeing Mr Smith or Mrs Jones in the office today, whether they know that patient well or not very well, and they’re still smoking. However, if the person we’re describing here quits smoking at these ages, how much life do they add back, compared with if they continued?

They may say: “Oh, I’ve been smoking all my life. What difference does it make? The die is cast.” Wrong! If you’ve been smoking your whole adult life — so let’s just say that you started at age 18, age 20, age 15, or even age 12 — but you quit smoking at the age of 35, you’re going to add 8 years of life on average. If you quit smoking when you’re 65, having smoked your whole adult life, you will add 1.7 years of life. That’s 1.7 years to be with your family, to be with your grandchildren, and enjoy life. If you ask, “Oh, what difference does it make?” It makes a big difference. 

I’ll share another statistic and I’ll be done. I think this is really an interesting one. The chances of gaining at least a year of life among those who quit smoking at the age of 65 was 23.4%. There is a 1 out of 4 chance that you’re going to live an additional year if you stop at age 65. Even if you stop smoking at age 75, you have a 14% chance of living at least an additional year longer than you would have if you didn’t stop smoking. 

There is much to think about here, much to consider, and much to discuss potentially with patients.

Dr. Markman is Professor of Medical Oncology and Therapeutics Research, City of Hope Comprehensive Cancer Center; President, Medicine & Science, City of Hope Atlanta, Chicago, Phoenix. He reported conflicts of interest with GlaxoSmithKline and AstraZeneca.

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

This transcript has been edited for clarity. 

I would like to briefly talk about a very interesting paper and one that probably has about as much to inform the doctor-patient relationship as any paper you can think of. 

The title itself gives you a little bit of that answer before I even discuss the outcome. The paper is “The Benefits of Quitting Smoking at Different Ages,” recently published in The American Journal of Preventive Medicine.

I’m not going to even begin to attempt to explore the statistics of the analysis, but I think the conclusions are both fascinating and important. I will read the first sentence of the results and then just comment on some of the others because there’s just so much data here and I really want to focus on the punchline. 

The results section said that, compared with people who never smoked, those who smoke currently, aged 35, 45, 55, 65, or 75, (those were all the groups they looked at), and who have smoked throughout adulthood until that age will lose an average of 9.1, 8.3, 7.3, 5.9, and 4.4 years of life, respectively — obviously, it’s a lot — if they continue to smoke for the rest of their lives. 

If somebody is smoking at age 35 and they continue to smoke, they could lose 9 years of life on average. We know that. It’s terrible. That’s why people should never smoke. Period. End of story. There’s no social value. There’s no health value of smoking. It’s a deadly recreational activity for multiple illnesses, and obviously, cancer is prominent among them.

Here’s the conclusion of the paper that I think is interesting. That doctor, whether it’s a primary care doctor, an oncologist, an ob/gyn, or a family doctor, is seeing Mr Smith or Mrs Jones in the office today, whether they know that patient well or not very well, and they’re still smoking. However, if the person we’re describing here quits smoking at these ages, how much life do they add back, compared with if they continued?

They may say: “Oh, I’ve been smoking all my life. What difference does it make? The die is cast.” Wrong! If you’ve been smoking your whole adult life — so let’s just say that you started at age 18, age 20, age 15, or even age 12 — but you quit smoking at the age of 35, you’re going to add 8 years of life on average. If you quit smoking when you’re 65, having smoked your whole adult life, you will add 1.7 years of life. That’s 1.7 years to be with your family, to be with your grandchildren, and enjoy life. If you ask, “Oh, what difference does it make?” It makes a big difference. 

I’ll share another statistic and I’ll be done. I think this is really an interesting one. The chances of gaining at least a year of life among those who quit smoking at the age of 65 was 23.4%. There is a 1 out of 4 chance that you’re going to live an additional year if you stop at age 65. Even if you stop smoking at age 75, you have a 14% chance of living at least an additional year longer than you would have if you didn’t stop smoking. 

There is much to think about here, much to consider, and much to discuss potentially with patients.

Dr. Markman is Professor of Medical Oncology and Therapeutics Research, City of Hope Comprehensive Cancer Center; President, Medicine & Science, City of Hope Atlanta, Chicago, Phoenix. He reported conflicts of interest with GlaxoSmithKline and AstraZeneca.

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

This transcript has been edited for clarity. 

I would like to briefly talk about a very interesting paper and one that probably has about as much to inform the doctor-patient relationship as any paper you can think of. 

The title itself gives you a little bit of that answer before I even discuss the outcome. The paper is “The Benefits of Quitting Smoking at Different Ages,” recently published in The American Journal of Preventive Medicine.

I’m not going to even begin to attempt to explore the statistics of the analysis, but I think the conclusions are both fascinating and important. I will read the first sentence of the results and then just comment on some of the others because there’s just so much data here and I really want to focus on the punchline. 

The results section said that, compared with people who never smoked, those who smoke currently, aged 35, 45, 55, 65, or 75, (those were all the groups they looked at), and who have smoked throughout adulthood until that age will lose an average of 9.1, 8.3, 7.3, 5.9, and 4.4 years of life, respectively — obviously, it’s a lot — if they continue to smoke for the rest of their lives. 

If somebody is smoking at age 35 and they continue to smoke, they could lose 9 years of life on average. We know that. It’s terrible. That’s why people should never smoke. Period. End of story. There’s no social value. There’s no health value of smoking. It’s a deadly recreational activity for multiple illnesses, and obviously, cancer is prominent among them.

Here’s the conclusion of the paper that I think is interesting. That doctor, whether it’s a primary care doctor, an oncologist, an ob/gyn, or a family doctor, is seeing Mr Smith or Mrs Jones in the office today, whether they know that patient well or not very well, and they’re still smoking. However, if the person we’re describing here quits smoking at these ages, how much life do they add back, compared with if they continued?

They may say: “Oh, I’ve been smoking all my life. What difference does it make? The die is cast.” Wrong! If you’ve been smoking your whole adult life — so let’s just say that you started at age 18, age 20, age 15, or even age 12 — but you quit smoking at the age of 35, you’re going to add 8 years of life on average. If you quit smoking when you’re 65, having smoked your whole adult life, you will add 1.7 years of life. That’s 1.7 years to be with your family, to be with your grandchildren, and enjoy life. If you ask, “Oh, what difference does it make?” It makes a big difference. 

I’ll share another statistic and I’ll be done. I think this is really an interesting one. The chances of gaining at least a year of life among those who quit smoking at the age of 65 was 23.4%. There is a 1 out of 4 chance that you’re going to live an additional year if you stop at age 65. Even if you stop smoking at age 75, you have a 14% chance of living at least an additional year longer than you would have if you didn’t stop smoking. 

There is much to think about here, much to consider, and much to discuss potentially with patients.

Dr. Markman is Professor of Medical Oncology and Therapeutics Research, City of Hope Comprehensive Cancer Center; President, Medicine & Science, City of Hope Atlanta, Chicago, Phoenix. He reported conflicts of interest with GlaxoSmithKline and AstraZeneca.

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

TOPLINE:

In patients with stage II or III colorectal cancer (CRC), frequent follow-up testing with CT scans and serum carcinoembryonic antigen (CEA) screening provides no significant overall or cancer-specific survival benefits at 10 years, according to findings from a secondary analysis.

METHODOLOGY:

• After curative surgery for CRC, intensive patient follow-up is common in clinical practice. However, there’s limited evidence to suggest that more frequent testing provides a long-term survival benefit.
• In the COLOFOL trial, patients with stage II or III CRC who had undergone curative resection were randomly assigned to either high-frequency follow-up (CT scans and CEA screening at 6, 12, 18, 24, and 36 months) or low-frequency follow-up (testing at 12 and 36 months) after surgery.
• This secondary analysis of the COLOFOL trial included 2456 patients (median age, 65 years), 1227 of whom received high-frequency follow-up and 1229 of whom received low-frequency follow-up.
• The main outcome of the secondary analysis was 10-year overall mortality and CRC–specific mortality rates.
• The analysis included both intention-to-treat and per-protocol approaches, with outcomes measured through December 2020.

TAKEAWAY:

• In the intention-to-treat analysis, the 10-year overall mortality rates were similar between the high- and low-frequency follow-up groups — 27.1% and 28.4%, respectively (risk difference, 1.3%; P = .46).
• A per-protocol analysis confirmed these findings: The 10-year overall mortality risk was 26.4% in the high-frequency group and 27.8% in the low-frequency group.
• The 10-year CRC–specific mortality rate was also similar between the high-frequency and low-frequency groups — 15.6% and 16.0%, respectively — (risk difference, 0.4%; P = .72). The same pattern was seen in the per-protocol analysis, which found a 10-year CRC–specific mortality risk of 15.6% in the high-frequency group and 15.9% in the low-frequency group.
• Subgroup analyses by cancer stage and location (rectal and colon) also revealed no significant differences in mortality outcomes between the two follow-up groups.

IN PRACTICE:

“This secondary analysis of the COLOFOL randomized clinical trial found that, among patients with stage II or III colorectal cancer, more frequent follow-up testing with CT scan and CEA screening, compared with less frequent follow-up, did not result in a significant rate reduction in 10-year overall mortality or colorectal cancer-specific mortality,” the authors concluded. “The results of this trial should be considered as the evidence base for updating clinical guidelines.”

SOURCE:

The study, led by Henrik Toft Sørensen, MD, PhD, DMSc, DSc, Aarhus University Hospital and Aarhus University, Aarhus, Denmark, was published online in JAMA Network Open.

LIMITATIONS:

The staff turnover at recruitment centers potentially affected protocol adherence. The inability to blind patients and physicians to the follow-up frequency was another limitation. The low-frequency follow-up protocol was less intensive than that recommended in the current guidelines by the National Comprehensive Cancer Network and the American Society of Clinical Oncology, potentially limiting comparisons to current standard practices.

DISCLOSURES:

The initial trial received unrestricted grants from multiple organizations including the Nordic Cancer Union, A.P. Møller Foundation, Beckett Foundation, Danish Cancer Society, and Swedish Cancer Foundation project. The authors reported no relevant 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:

In patients with stage II or III colorectal cancer (CRC), frequent follow-up testing with CT scans and serum carcinoembryonic antigen (CEA) screening provides no significant overall or cancer-specific survival benefits at 10 years, according to findings from a secondary analysis.

METHODOLOGY:

• After curative surgery for CRC, intensive patient follow-up is common in clinical practice. However, there’s limited evidence to suggest that more frequent testing provides a long-term survival benefit.
• In the COLOFOL trial, patients with stage II or III CRC who had undergone curative resection were randomly assigned to either high-frequency follow-up (CT scans and CEA screening at 6, 12, 18, 24, and 36 months) or low-frequency follow-up (testing at 12 and 36 months) after surgery.
• This secondary analysis of the COLOFOL trial included 2456 patients (median age, 65 years), 1227 of whom received high-frequency follow-up and 1229 of whom received low-frequency follow-up.
• The main outcome of the secondary analysis was 10-year overall mortality and CRC–specific mortality rates.
• The analysis included both intention-to-treat and per-protocol approaches, with outcomes measured through December 2020.

TAKEAWAY:

• In the intention-to-treat analysis, the 10-year overall mortality rates were similar between the high- and low-frequency follow-up groups — 27.1% and 28.4%, respectively (risk difference, 1.3%; P = .46).
• A per-protocol analysis confirmed these findings: The 10-year overall mortality risk was 26.4% in the high-frequency group and 27.8% in the low-frequency group.
• The 10-year CRC–specific mortality rate was also similar between the high-frequency and low-frequency groups — 15.6% and 16.0%, respectively — (risk difference, 0.4%; P = .72). The same pattern was seen in the per-protocol analysis, which found a 10-year CRC–specific mortality risk of 15.6% in the high-frequency group and 15.9% in the low-frequency group.
• Subgroup analyses by cancer stage and location (rectal and colon) also revealed no significant differences in mortality outcomes between the two follow-up groups.

IN PRACTICE:

“This secondary analysis of the COLOFOL randomized clinical trial found that, among patients with stage II or III colorectal cancer, more frequent follow-up testing with CT scan and CEA screening, compared with less frequent follow-up, did not result in a significant rate reduction in 10-year overall mortality or colorectal cancer-specific mortality,” the authors concluded. “The results of this trial should be considered as the evidence base for updating clinical guidelines.”

SOURCE:

The study, led by Henrik Toft Sørensen, MD, PhD, DMSc, DSc, Aarhus University Hospital and Aarhus University, Aarhus, Denmark, was published online in JAMA Network Open.

LIMITATIONS:

The staff turnover at recruitment centers potentially affected protocol adherence. The inability to blind patients and physicians to the follow-up frequency was another limitation. The low-frequency follow-up protocol was less intensive than that recommended in the current guidelines by the National Comprehensive Cancer Network and the American Society of Clinical Oncology, potentially limiting comparisons to current standard practices.

DISCLOSURES:

The initial trial received unrestricted grants from multiple organizations including the Nordic Cancer Union, A.P. Møller Foundation, Beckett Foundation, Danish Cancer Society, and Swedish Cancer Foundation project. The authors reported no relevant 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:

In patients with stage II or III colorectal cancer (CRC), frequent follow-up testing with CT scans and serum carcinoembryonic antigen (CEA) screening provides no significant overall or cancer-specific survival benefits at 10 years, according to findings from a secondary analysis.

METHODOLOGY:

• After curative surgery for CRC, intensive patient follow-up is common in clinical practice. However, there’s limited evidence to suggest that more frequent testing provides a long-term survival benefit.
• In the COLOFOL trial, patients with stage II or III CRC who had undergone curative resection were randomly assigned to either high-frequency follow-up (CT scans and CEA screening at 6, 12, 18, 24, and 36 months) or low-frequency follow-up (testing at 12 and 36 months) after surgery.
• This secondary analysis of the COLOFOL trial included 2456 patients (median age, 65 years), 1227 of whom received high-frequency follow-up and 1229 of whom received low-frequency follow-up.
• The main outcome of the secondary analysis was 10-year overall mortality and CRC–specific mortality rates.
• The analysis included both intention-to-treat and per-protocol approaches, with outcomes measured through December 2020.

TAKEAWAY:

• In the intention-to-treat analysis, the 10-year overall mortality rates were similar between the high- and low-frequency follow-up groups — 27.1% and 28.4%, respectively (risk difference, 1.3%; P = .46).
• A per-protocol analysis confirmed these findings: The 10-year overall mortality risk was 26.4% in the high-frequency group and 27.8% in the low-frequency group.
• The 10-year CRC–specific mortality rate was also similar between the high-frequency and low-frequency groups — 15.6% and 16.0%, respectively — (risk difference, 0.4%; P = .72). The same pattern was seen in the per-protocol analysis, which found a 10-year CRC–specific mortality risk of 15.6% in the high-frequency group and 15.9% in the low-frequency group.
• Subgroup analyses by cancer stage and location (rectal and colon) also revealed no significant differences in mortality outcomes between the two follow-up groups.

IN PRACTICE:

“This secondary analysis of the COLOFOL randomized clinical trial found that, among patients with stage II or III colorectal cancer, more frequent follow-up testing with CT scan and CEA screening, compared with less frequent follow-up, did not result in a significant rate reduction in 10-year overall mortality or colorectal cancer-specific mortality,” the authors concluded. “The results of this trial should be considered as the evidence base for updating clinical guidelines.”

SOURCE:

The study, led by Henrik Toft Sørensen, MD, PhD, DMSc, DSc, Aarhus University Hospital and Aarhus University, Aarhus, Denmark, was published online in JAMA Network Open.

LIMITATIONS:

The staff turnover at recruitment centers potentially affected protocol adherence. The inability to blind patients and physicians to the follow-up frequency was another limitation. The low-frequency follow-up protocol was less intensive than that recommended in the current guidelines by the National Comprehensive Cancer Network and the American Society of Clinical Oncology, potentially limiting comparisons to current standard practices.

DISCLOSURES:

The initial trial received unrestricted grants from multiple organizations including the Nordic Cancer Union, A.P. Møller Foundation, Beckett Foundation, Danish Cancer Society, and Swedish Cancer Foundation project. The authors reported no relevant 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.

NEW YORK CITY — The total body skin examination with or without dermatoscopy might eventually be marginalized by noninvasive technologies that greatly reduce the need for biopsy while increasing sensitivity and specificity, according to an expert describing four such technologies now in routine use at his own institution.

For skin cancer screening, existing and coming technologies represent “the future of dermatology,” but “we can and should be [already] trying to incorporate these into routine practice,” said Jonathan Ungar, MD, assistant professor of dermatology at the Icahn School of Medicine at Mount Sinai, New York City.

 

Technologies such as electrical impedance spectroscopy (EIS), optical coherence tomography (OCT), and reflectance confocal microscopy (RCM) have immediate utility for improving skin cancer detection with fewer biopsies, but this is just the beginning, according to Ungar, who is also medical director of the Kimberly and Eric J. Waldman Melanoma and Skin Cancer Center at Mount Sinai, New York City.

“There is going to be a day when we are not cutting to make a diagnosis,” he said during a presentation at the 27th Annual Winter Symposium — Advances in Medical and Surgical Dermatology (MSWS) 2024.

 

Four Noninvasive Tools Are in Routine Use

Each of these technologies, along with total body photography (TBP), is currently in use at Mount Sinai as well as other tertiary centers to improve diagnostic accuracy at the same time they reduce invasive tests. The initial excitement about these technologies was based on their potential to avoid biopsy in cosmetically sensitive areas, but Ungar suggested that wider application is being driven by better rates of detection, less morbidity, and improved patient satisfaction.

Patients are happy to avoid invasive procedures whenever they can, Ungar noted. In addition to concern about pain or discomfort and a small but measurable risk for infection, patients face a wound that requires healing and the potential for an enduring scar whether the histology is positive for a malignancy.

While none of the four technologies Ungar outlined typically provide a yes or no answer regarding the presence of a malignancy, they do improve diagnostic accuracy with a lower rate of biopsy.

 

Each Noninvasive Tool Reduces Biopsy Rates

In the case of EIS, for example, the impedance of a painless and harmless electrical current directed into the skin with a handheld probe differentiates normal from abnormal skin through an EIS algorithm. Ungar said it does not require training. A result negative for an abnormality has about a 90% predictive value, and it means that a biopsy can be avoided if there are no other reasons for suspicion.

With a price estimated in the thousands of dollars, the device and software are “not so expensive,” particularly when the tool results in fewer biopsies, Ungar noted.

OCT has a similar profile. Again, used as an adjunct to other types of evaluations, including a history and visual inspection, this helps in modulating suspicion of malignancy. In published studies, OCT has proven superior to dermatoscopy for cancer detection. Citing a 14-study meta-analysis, Ungar said that the sensitivity of OCT for melanoma exceeds, and the specificity approaches, 90%. For basal cell cancers, it is even better.

RCM involves directing a laser into the skin to detect abnormal cells that reflect light. It enables visualization of the skin by layers to the papillary dermis in a detail that is comparable with histology, according to Ungar. Imaging performed with the device used at Mount Sinai (VivaScope 1500, Caliber Imaging & Diagnostics) is reimbursed by Medicare.

Once comfortable with the technology, scanning and interpretation take slightly more time than that required of EIS or OCT, but, like the others, it is painless and helpful for determining whether further evaluation is needed, according to Ungar.

“It is extremely useful in reducing the number of biopsies,” whether melanoma or basal cell malignancies, he said.

 

Total Body Photograph Helps With Serial Screens

While not specifically a diagnostic tool, TBP can also play a role in reducing biopsies through its highly efficient ability to document the evolution of lesions over time.

As its name implies, essentially the entire body surface is captured by multiple cameras mounted in a circle around the patient. Unlike sequential photos that require far more time to take and store and are challenging to organize and retrieve, the device used at Mount Sinai (Vectra Wb180 1360, Canfield Scientific) can complete the photos in about 2 minutes.

Software for organizing and storing the photos, to which dermatoscope images of individual lesions can be attached if helpful, results in efficient retrieval of photos at sequential visits for evaluating change in any specific lesion.

“It is very easy to use,” according to Ungar, who noted that although the underlying idea is not, the technology of taking, storing, and retrieving photographs has been “perhaps perfected” with this approach.

 

Noninvasive Screening Training Is Appropriate

Year after year, dermatology residents undergo intensive instruction to master the traditional methods of skin examination with the naked eye and the help of a dermatoscope, but Ungar considers the noninvasive tools to be another step forward. They lower miss rates while reducing the need for histopathology.

Adding these new technologies to routine patient care resonates for many experts, even if the protocols of when to use with the tool are not well established.

Angela J. Lamb, MD, an associate professor of dermatology at Mount Sinai, who has been following the work of Ungar with interest, sees merit in his argument. Not surprisingly, she thinks that any approach shown to boost skin cancer detection is something that deserves attention, but she thinks the effort to safely eliminate biopsies with a low likelihood of a positive finding cannot be ignored.

“Patients want to avoid biopsies when they can,” Lamb told this news organization, and she does not think this is limited to biopsies on the face or other cosmetically sensitive areas.

As a result, she said that she does see the rationale for incorporating the newer technologies into routine care and called this an “important” effort to improve the patient experience as well as reduce missed lesions.

Ungar reported financial relationships with AbbVie, Bristol-Myers Squibb, Castle Biosciences, Dermavant, Janssen Pharmaceuticals, Menlo Therapeutics, Mitsubishi Tanabe Pharma America, and UCB. Lamb reported no potential conflicts of interest.

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

NEW YORK CITY — The total body skin examination with or without dermatoscopy might eventually be marginalized by noninvasive technologies that greatly reduce the need for biopsy while increasing sensitivity and specificity, according to an expert describing four such technologies now in routine use at his own institution.

For skin cancer screening, existing and coming technologies represent “the future of dermatology,” but “we can and should be [already] trying to incorporate these into routine practice,” said Jonathan Ungar, MD, assistant professor of dermatology at the Icahn School of Medicine at Mount Sinai, New York City.

 

Technologies such as electrical impedance spectroscopy (EIS), optical coherence tomography (OCT), and reflectance confocal microscopy (RCM) have immediate utility for improving skin cancer detection with fewer biopsies, but this is just the beginning, according to Ungar, who is also medical director of the Kimberly and Eric J. Waldman Melanoma and Skin Cancer Center at Mount Sinai, New York City.

“There is going to be a day when we are not cutting to make a diagnosis,” he said during a presentation at the 27th Annual Winter Symposium — Advances in Medical and Surgical Dermatology (MSWS) 2024.

 

Four Noninvasive Tools Are in Routine Use

Each of these technologies, along with total body photography (TBP), is currently in use at Mount Sinai as well as other tertiary centers to improve diagnostic accuracy at the same time they reduce invasive tests. The initial excitement about these technologies was based on their potential to avoid biopsy in cosmetically sensitive areas, but Ungar suggested that wider application is being driven by better rates of detection, less morbidity, and improved patient satisfaction.

Patients are happy to avoid invasive procedures whenever they can, Ungar noted. In addition to concern about pain or discomfort and a small but measurable risk for infection, patients face a wound that requires healing and the potential for an enduring scar whether the histology is positive for a malignancy.

While none of the four technologies Ungar outlined typically provide a yes or no answer regarding the presence of a malignancy, they do improve diagnostic accuracy with a lower rate of biopsy.

 

Each Noninvasive Tool Reduces Biopsy Rates

In the case of EIS, for example, the impedance of a painless and harmless electrical current directed into the skin with a handheld probe differentiates normal from abnormal skin through an EIS algorithm. Ungar said it does not require training. A result negative for an abnormality has about a 90% predictive value, and it means that a biopsy can be avoided if there are no other reasons for suspicion.

With a price estimated in the thousands of dollars, the device and software are “not so expensive,” particularly when the tool results in fewer biopsies, Ungar noted.

OCT has a similar profile. Again, used as an adjunct to other types of evaluations, including a history and visual inspection, this helps in modulating suspicion of malignancy. In published studies, OCT has proven superior to dermatoscopy for cancer detection. Citing a 14-study meta-analysis, Ungar said that the sensitivity of OCT for melanoma exceeds, and the specificity approaches, 90%. For basal cell cancers, it is even better.

RCM involves directing a laser into the skin to detect abnormal cells that reflect light. It enables visualization of the skin by layers to the papillary dermis in a detail that is comparable with histology, according to Ungar. Imaging performed with the device used at Mount Sinai (VivaScope 1500, Caliber Imaging & Diagnostics) is reimbursed by Medicare.

Once comfortable with the technology, scanning and interpretation take slightly more time than that required of EIS or OCT, but, like the others, it is painless and helpful for determining whether further evaluation is needed, according to Ungar.

“It is extremely useful in reducing the number of biopsies,” whether melanoma or basal cell malignancies, he said.

 

Total Body Photograph Helps With Serial Screens

While not specifically a diagnostic tool, TBP can also play a role in reducing biopsies through its highly efficient ability to document the evolution of lesions over time.

As its name implies, essentially the entire body surface is captured by multiple cameras mounted in a circle around the patient. Unlike sequential photos that require far more time to take and store and are challenging to organize and retrieve, the device used at Mount Sinai (Vectra Wb180 1360, Canfield Scientific) can complete the photos in about 2 minutes.

Software for organizing and storing the photos, to which dermatoscope images of individual lesions can be attached if helpful, results in efficient retrieval of photos at sequential visits for evaluating change in any specific lesion.

“It is very easy to use,” according to Ungar, who noted that although the underlying idea is not, the technology of taking, storing, and retrieving photographs has been “perhaps perfected” with this approach.

 

Noninvasive Screening Training Is Appropriate

Year after year, dermatology residents undergo intensive instruction to master the traditional methods of skin examination with the naked eye and the help of a dermatoscope, but Ungar considers the noninvasive tools to be another step forward. They lower miss rates while reducing the need for histopathology.

Adding these new technologies to routine patient care resonates for many experts, even if the protocols of when to use with the tool are not well established.

Angela J. Lamb, MD, an associate professor of dermatology at Mount Sinai, who has been following the work of Ungar with interest, sees merit in his argument. Not surprisingly, she thinks that any approach shown to boost skin cancer detection is something that deserves attention, but she thinks the effort to safely eliminate biopsies with a low likelihood of a positive finding cannot be ignored.

“Patients want to avoid biopsies when they can,” Lamb told this news organization, and she does not think this is limited to biopsies on the face or other cosmetically sensitive areas.

As a result, she said that she does see the rationale for incorporating the newer technologies into routine care and called this an “important” effort to improve the patient experience as well as reduce missed lesions.

Ungar reported financial relationships with AbbVie, Bristol-Myers Squibb, Castle Biosciences, Dermavant, Janssen Pharmaceuticals, Menlo Therapeutics, Mitsubishi Tanabe Pharma America, and UCB. Lamb reported no potential conflicts of interest.

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

NEW YORK CITY — The total body skin examination with or without dermatoscopy might eventually be marginalized by noninvasive technologies that greatly reduce the need for biopsy while increasing sensitivity and specificity, according to an expert describing four such technologies now in routine use at his own institution.

For skin cancer screening, existing and coming technologies represent “the future of dermatology,” but “we can and should be [already] trying to incorporate these into routine practice,” said Jonathan Ungar, MD, assistant professor of dermatology at the Icahn School of Medicine at Mount Sinai, New York City.

 

Technologies such as electrical impedance spectroscopy (EIS), optical coherence tomography (OCT), and reflectance confocal microscopy (RCM) have immediate utility for improving skin cancer detection with fewer biopsies, but this is just the beginning, according to Ungar, who is also medical director of the Kimberly and Eric J. Waldman Melanoma and Skin Cancer Center at Mount Sinai, New York City.

“There is going to be a day when we are not cutting to make a diagnosis,” he said during a presentation at the 27th Annual Winter Symposium — Advances in Medical and Surgical Dermatology (MSWS) 2024.

 

Four Noninvasive Tools Are in Routine Use

Each of these technologies, along with total body photography (TBP), is currently in use at Mount Sinai as well as other tertiary centers to improve diagnostic accuracy at the same time they reduce invasive tests. The initial excitement about these technologies was based on their potential to avoid biopsy in cosmetically sensitive areas, but Ungar suggested that wider application is being driven by better rates of detection, less morbidity, and improved patient satisfaction.

Patients are happy to avoid invasive procedures whenever they can, Ungar noted. In addition to concern about pain or discomfort and a small but measurable risk for infection, patients face a wound that requires healing and the potential for an enduring scar whether the histology is positive for a malignancy.

While none of the four technologies Ungar outlined typically provide a yes or no answer regarding the presence of a malignancy, they do improve diagnostic accuracy with a lower rate of biopsy.

 

Each Noninvasive Tool Reduces Biopsy Rates

In the case of EIS, for example, the impedance of a painless and harmless electrical current directed into the skin with a handheld probe differentiates normal from abnormal skin through an EIS algorithm. Ungar said it does not require training. A result negative for an abnormality has about a 90% predictive value, and it means that a biopsy can be avoided if there are no other reasons for suspicion.

With a price estimated in the thousands of dollars, the device and software are “not so expensive,” particularly when the tool results in fewer biopsies, Ungar noted.

OCT has a similar profile. Again, used as an adjunct to other types of evaluations, including a history and visual inspection, this helps in modulating suspicion of malignancy. In published studies, OCT has proven superior to dermatoscopy for cancer detection. Citing a 14-study meta-analysis, Ungar said that the sensitivity of OCT for melanoma exceeds, and the specificity approaches, 90%. For basal cell cancers, it is even better.

RCM involves directing a laser into the skin to detect abnormal cells that reflect light. It enables visualization of the skin by layers to the papillary dermis in a detail that is comparable with histology, according to Ungar. Imaging performed with the device used at Mount Sinai (VivaScope 1500, Caliber Imaging & Diagnostics) is reimbursed by Medicare.

Once comfortable with the technology, scanning and interpretation take slightly more time than that required of EIS or OCT, but, like the others, it is painless and helpful for determining whether further evaluation is needed, according to Ungar.

“It is extremely useful in reducing the number of biopsies,” whether melanoma or basal cell malignancies, he said.

 

Total Body Photograph Helps With Serial Screens

While not specifically a diagnostic tool, TBP can also play a role in reducing biopsies through its highly efficient ability to document the evolution of lesions over time.

As its name implies, essentially the entire body surface is captured by multiple cameras mounted in a circle around the patient. Unlike sequential photos that require far more time to take and store and are challenging to organize and retrieve, the device used at Mount Sinai (Vectra Wb180 1360, Canfield Scientific) can complete the photos in about 2 minutes.

Software for organizing and storing the photos, to which dermatoscope images of individual lesions can be attached if helpful, results in efficient retrieval of photos at sequential visits for evaluating change in any specific lesion.

“It is very easy to use,” according to Ungar, who noted that although the underlying idea is not, the technology of taking, storing, and retrieving photographs has been “perhaps perfected” with this approach.

 

Noninvasive Screening Training Is Appropriate

Year after year, dermatology residents undergo intensive instruction to master the traditional methods of skin examination with the naked eye and the help of a dermatoscope, but Ungar considers the noninvasive tools to be another step forward. They lower miss rates while reducing the need for histopathology.

Adding these new technologies to routine patient care resonates for many experts, even if the protocols of when to use with the tool are not well established.

Angela J. Lamb, MD, an associate professor of dermatology at Mount Sinai, who has been following the work of Ungar with interest, sees merit in his argument. Not surprisingly, she thinks that any approach shown to boost skin cancer detection is something that deserves attention, but she thinks the effort to safely eliminate biopsies with a low likelihood of a positive finding cannot be ignored.

“Patients want to avoid biopsies when they can,” Lamb told this news organization, and she does not think this is limited to biopsies on the face or other cosmetically sensitive areas.

As a result, she said that she does see the rationale for incorporating the newer technologies into routine care and called this an “important” effort to improve the patient experience as well as reduce missed lesions.

Ungar reported financial relationships with AbbVie, Bristol-Myers Squibb, Castle Biosciences, Dermavant, Janssen Pharmaceuticals, Menlo Therapeutics, Mitsubishi Tanabe Pharma America, and UCB. Lamb reported no potential conflicts of interest.

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