Melanoma

TOPLINE:

Cutaneous immune-related adverse events are associated with improved overall and progression-free survival among patients treated with immune checkpoint inhibitors (ICIs).

METHODOLOGY:

• Emerging evidence suggests that the presence of cutaneous immune-related adverse events may be linked with favorable outcomes among patients with cancer who receive ICIs.
• Researchers conducted a systematic review and meta-analysis that included 23 studies and a total of 22,749 patients with cancer who received ICI treatment; studies compared outcomes among patients with and those without cutaneous immune-related adverse events.
• The major outcomes evaluated in the analysis were overall survival and progression-free survival (PFS); subgroup analyses assessed cutaneous immune-related adverse event type, cancer type, and other factors.

TAKEAWAY:

• The occurrence of cutaneous immune-related adverse events was associated with improved PFS (hazard ratio, 0.52; P < .001) and overall survival (HR, 0.61; P < .001).
• In the subgroup analysis, patients with eczematous (HR, 0.69), lichenoid or lichen planus–like skin lesions (HR, 0.51), pruritus without rash (HR, 0.70), psoriasis (HR, 0.63), or vitiligo (HR, 0.30) demonstrated a significant overall survival advantage. Vitiligo was the only adverse event associated with a PFS advantage (HR, 0.28).
• Among patients with melanoma, analyses revealed a significant association between the incidence of cutaneous immune-related adverse events and improved overall survival (HR, 0.51) and PFS (HR, 0.45). The authors highlighted similar findings among patients with non–small cell lung cancer (HR, 0.50 for overall survival and 0.61 for PFS).

IN PRACTICE:

“These data suggest that [cutaneous immune-related adverse events] may have useful prognostic value in ICI treatment,” the authors concluded.

SOURCE:

The analysis, led by Fei Wang, MD, Zhong Da Hospital, School of Medicine, Southeast University, Nanjing, China, was published online in JAMA Dermatology.

LIMITATIONS:

Most of the data came from retrospective studies, and there were limited data on specific patient subgroups. The Egger tests, used to assess potential publication bias in meta-analyses, revealed publication bias.

DISCLOSURES:

No disclosures were reported. The study was supported by a grant from the Postgraduate Research and Practice Innovation Program of Jiangsu Province.

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

TOPLINE:

Cutaneous immune-related adverse events are associated with improved overall and progression-free survival among patients treated with immune checkpoint inhibitors (ICIs).

METHODOLOGY:

• Emerging evidence suggests that the presence of cutaneous immune-related adverse events may be linked with favorable outcomes among patients with cancer who receive ICIs.
• Researchers conducted a systematic review and meta-analysis that included 23 studies and a total of 22,749 patients with cancer who received ICI treatment; studies compared outcomes among patients with and those without cutaneous immune-related adverse events.
• The major outcomes evaluated in the analysis were overall survival and progression-free survival (PFS); subgroup analyses assessed cutaneous immune-related adverse event type, cancer type, and other factors.

TAKEAWAY:

• The occurrence of cutaneous immune-related adverse events was associated with improved PFS (hazard ratio, 0.52; P < .001) and overall survival (HR, 0.61; P < .001).
• In the subgroup analysis, patients with eczematous (HR, 0.69), lichenoid or lichen planus–like skin lesions (HR, 0.51), pruritus without rash (HR, 0.70), psoriasis (HR, 0.63), or vitiligo (HR, 0.30) demonstrated a significant overall survival advantage. Vitiligo was the only adverse event associated with a PFS advantage (HR, 0.28).
• Among patients with melanoma, analyses revealed a significant association between the incidence of cutaneous immune-related adverse events and improved overall survival (HR, 0.51) and PFS (HR, 0.45). The authors highlighted similar findings among patients with non–small cell lung cancer (HR, 0.50 for overall survival and 0.61 for PFS).

IN PRACTICE:

“These data suggest that [cutaneous immune-related adverse events] may have useful prognostic value in ICI treatment,” the authors concluded.

SOURCE:

The analysis, led by Fei Wang, MD, Zhong Da Hospital, School of Medicine, Southeast University, Nanjing, China, was published online in JAMA Dermatology.

LIMITATIONS:

Most of the data came from retrospective studies, and there were limited data on specific patient subgroups. The Egger tests, used to assess potential publication bias in meta-analyses, revealed publication bias.

DISCLOSURES:

No disclosures were reported. The study was supported by a grant from the Postgraduate Research and Practice Innovation Program of Jiangsu Province.

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

TOPLINE:

Cutaneous immune-related adverse events are associated with improved overall and progression-free survival among patients treated with immune checkpoint inhibitors (ICIs).

METHODOLOGY:

• Emerging evidence suggests that the presence of cutaneous immune-related adverse events may be linked with favorable outcomes among patients with cancer who receive ICIs.
• Researchers conducted a systematic review and meta-analysis that included 23 studies and a total of 22,749 patients with cancer who received ICI treatment; studies compared outcomes among patients with and those without cutaneous immune-related adverse events.
• The major outcomes evaluated in the analysis were overall survival and progression-free survival (PFS); subgroup analyses assessed cutaneous immune-related adverse event type, cancer type, and other factors.

TAKEAWAY:

• The occurrence of cutaneous immune-related adverse events was associated with improved PFS (hazard ratio, 0.52; P < .001) and overall survival (HR, 0.61; P < .001).
• In the subgroup analysis, patients with eczematous (HR, 0.69), lichenoid or lichen planus–like skin lesions (HR, 0.51), pruritus without rash (HR, 0.70), psoriasis (HR, 0.63), or vitiligo (HR, 0.30) demonstrated a significant overall survival advantage. Vitiligo was the only adverse event associated with a PFS advantage (HR, 0.28).
• Among patients with melanoma, analyses revealed a significant association between the incidence of cutaneous immune-related adverse events and improved overall survival (HR, 0.51) and PFS (HR, 0.45). The authors highlighted similar findings among patients with non–small cell lung cancer (HR, 0.50 for overall survival and 0.61 for PFS).

IN PRACTICE:

“These data suggest that [cutaneous immune-related adverse events] may have useful prognostic value in ICI treatment,” the authors concluded.

SOURCE:

The analysis, led by Fei Wang, MD, Zhong Da Hospital, School of Medicine, Southeast University, Nanjing, China, was published online in JAMA Dermatology.

LIMITATIONS:

Most of the data came from retrospective studies, and there were limited data on specific patient subgroups. The Egger tests, used to assess potential publication bias in meta-analyses, revealed publication bias.

DISCLOSURES:

No disclosures were reported. The study was supported by a grant from the Postgraduate Research and Practice Innovation Program of Jiangsu Province.

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

TOPLINE:

The number of primary melanomas is not an independent risk factor for mortality.

METHODOLOGY:

• The difference in outcomes between people with multiple primary melanomas (MPMs) and a single primary melanoma (SPM) has not been established.
• To compare 10-year melanoma-specific mortality and overall mortality between people with MPMs and SPM, researchers drew from the Melanoma Patterns of Care study, a population-based observational analysis of residents in the state of New South Wales, Australia, who had a melanoma reported to the state cancer registry over 12 months in 2006-2007, and were followed up until 2018, for a median of almost 12 years.
• The researchers performed logistic regression analyses to assess 10-year melanoma-specific mortality differences between the two groups.

TAKEAWAY:

• Of 3,404 people included in the analysis, 2,830 had an SPM and 574 developed MPMs during follow-up.
• On multivariable regression adjusted for pathologic characteristics of the thickest lesion in the MPM group, no significant differences were seen in 10-year melanoma-specific mortality between the two groups (odds ratio, 0.85; 95% confidence interval, 0.58-1.24; P = .40).
• Sensitivity analyses adjusted for parameters of the first primary melanoma among patients with MPMs revealed similar findings (OR, 1.34; 95% CI, 0.92-1.96; P = .12).
• On multivariable analysis using data from the thickest lesion, factors independently associated with melanoma-specific mortality were male sex, disadvantaged socioeconomic status (based on location of residence), and Breslow thickness.
• Factors independently associated with 10-year overall mortality were like those seen in other studies and included sex, Breslow thickness, ulceration status, and socioeconomic disadvantage.

IN PRACTICE:

“The results of our study suggest that the number of primary melanomas is not an independent risk factor for mortality,” the researchers concluded. “In addition, the detection of melanoma at an early stage (with a thin Breslow thickness) rather than an intrinsic biologic factor remains the biggest influence on melanoma mortality after diagnosis of one or more melanomas.”

SOURCE:

Corresponding author Serigne N. Lo, PhD, of the Melanoma Institute Australia, led the research. The study was published in the Journal of the American Academy of Dermatology.

LIMITATIONS:

No adjustments for treatment modality were made in the study, and at baseline survey, effective systemic treatments for melanoma were not available.

DISCLOSURES:

This study was supported by the Australian National Health and Medical Research Council, Cancer Institute New South Wales, and the New South Wale State Government via a grant to the New South Wales Melanoma Network. Additional support was provided by Melanoma Institute Australia and the New South Wales Melanoma Network.
 

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

TOPLINE:

The number of primary melanomas is not an independent risk factor for mortality.

METHODOLOGY:

• The difference in outcomes between people with multiple primary melanomas (MPMs) and a single primary melanoma (SPM) has not been established.
• To compare 10-year melanoma-specific mortality and overall mortality between people with MPMs and SPM, researchers drew from the Melanoma Patterns of Care study, a population-based observational analysis of residents in the state of New South Wales, Australia, who had a melanoma reported to the state cancer registry over 12 months in 2006-2007, and were followed up until 2018, for a median of almost 12 years.
• The researchers performed logistic regression analyses to assess 10-year melanoma-specific mortality differences between the two groups.

TAKEAWAY:

• Of 3,404 people included in the analysis, 2,830 had an SPM and 574 developed MPMs during follow-up.
• On multivariable regression adjusted for pathologic characteristics of the thickest lesion in the MPM group, no significant differences were seen in 10-year melanoma-specific mortality between the two groups (odds ratio, 0.85; 95% confidence interval, 0.58-1.24; P = .40).
• Sensitivity analyses adjusted for parameters of the first primary melanoma among patients with MPMs revealed similar findings (OR, 1.34; 95% CI, 0.92-1.96; P = .12).
• On multivariable analysis using data from the thickest lesion, factors independently associated with melanoma-specific mortality were male sex, disadvantaged socioeconomic status (based on location of residence), and Breslow thickness.
• Factors independently associated with 10-year overall mortality were like those seen in other studies and included sex, Breslow thickness, ulceration status, and socioeconomic disadvantage.

IN PRACTICE:

“The results of our study suggest that the number of primary melanomas is not an independent risk factor for mortality,” the researchers concluded. “In addition, the detection of melanoma at an early stage (with a thin Breslow thickness) rather than an intrinsic biologic factor remains the biggest influence on melanoma mortality after diagnosis of one or more melanomas.”

SOURCE:

Corresponding author Serigne N. Lo, PhD, of the Melanoma Institute Australia, led the research. The study was published in the Journal of the American Academy of Dermatology.

LIMITATIONS:

No adjustments for treatment modality were made in the study, and at baseline survey, effective systemic treatments for melanoma were not available.

DISCLOSURES:

This study was supported by the Australian National Health and Medical Research Council, Cancer Institute New South Wales, and the New South Wale State Government via a grant to the New South Wales Melanoma Network. Additional support was provided by Melanoma Institute Australia and the New South Wales Melanoma Network.
 

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

TOPLINE:

The number of primary melanomas is not an independent risk factor for mortality.

METHODOLOGY:

• The difference in outcomes between people with multiple primary melanomas (MPMs) and a single primary melanoma (SPM) has not been established.
• To compare 10-year melanoma-specific mortality and overall mortality between people with MPMs and SPM, researchers drew from the Melanoma Patterns of Care study, a population-based observational analysis of residents in the state of New South Wales, Australia, who had a melanoma reported to the state cancer registry over 12 months in 2006-2007, and were followed up until 2018, for a median of almost 12 years.
• The researchers performed logistic regression analyses to assess 10-year melanoma-specific mortality differences between the two groups.

TAKEAWAY:

• Of 3,404 people included in the analysis, 2,830 had an SPM and 574 developed MPMs during follow-up.
• On multivariable regression adjusted for pathologic characteristics of the thickest lesion in the MPM group, no significant differences were seen in 10-year melanoma-specific mortality between the two groups (odds ratio, 0.85; 95% confidence interval, 0.58-1.24; P = .40).
• Sensitivity analyses adjusted for parameters of the first primary melanoma among patients with MPMs revealed similar findings (OR, 1.34; 95% CI, 0.92-1.96; P = .12).
• On multivariable analysis using data from the thickest lesion, factors independently associated with melanoma-specific mortality were male sex, disadvantaged socioeconomic status (based on location of residence), and Breslow thickness.
• Factors independently associated with 10-year overall mortality were like those seen in other studies and included sex, Breslow thickness, ulceration status, and socioeconomic disadvantage.

IN PRACTICE:

“The results of our study suggest that the number of primary melanomas is not an independent risk factor for mortality,” the researchers concluded. “In addition, the detection of melanoma at an early stage (with a thin Breslow thickness) rather than an intrinsic biologic factor remains the biggest influence on melanoma mortality after diagnosis of one or more melanomas.”

SOURCE:

Corresponding author Serigne N. Lo, PhD, of the Melanoma Institute Australia, led the research. The study was published in the Journal of the American Academy of Dermatology.

LIMITATIONS:

No adjustments for treatment modality were made in the study, and at baseline survey, effective systemic treatments for melanoma were not available.

DISCLOSURES:

This study was supported by the Australian National Health and Medical Research Council, Cancer Institute New South Wales, and the New South Wale State Government via a grant to the New South Wales Melanoma Network. Additional support was provided by Melanoma Institute Australia and the New South Wales Melanoma Network.
 

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

Patients with cutaneous Merkel cell carcinoma (MCC) have a higher risk of subsequently developing solid and hematologic cancers, according to a new analysis.

In a cohort of 6,146 patients with a first primary MCC, a total of 725 (11.8%) developed subsequent primary cancers. For solid tumors, the risk was highest for cutaneous melanoma and papillary thyroid carcinoma, while for hematologic cancers, the risk was increased for non-Hodgkin lymphoma.

“Our study does confirm that patients with MCC are at higher risk for developing other cancers,” study author Lisa C. Zaba, MD, PhD, associate professor of dermatology and director of the Merkel cell carcinoma multidisciplinary clinic, Stanford (Calif.) Cancer Center, said in an interview. “MCC is a highly malignant cancer with a 40% recurrence risk.”

Because of this high risk, Dr. Zaba noted that patients with MCC get frequent surveillance with both imaging studies (PET-CT and CT) as well as frequent visits in clinic with MCC experts. “Specifically, a patient with MCC is imaged and seen in clinic every 3-6 months for the first 3 years after diagnosis, and every 6-12 months thereafter for up to 5 years,” she said. “Interestingly, this high level of surveillance may be one reason that we find so many cancers in patients who have been diagnosed with MCC, compared to the general population.”

The study was published online in JAMA Dermatology.

With the death of “Margaritaville” singer Jimmy Buffett, who recently died of MCC 4 years after his diagnosis, this rare, aggressive skin cancer has been put in the spotlight. Survival has been increasing, primarily because of the advent of immunotherapy, and the authors note that it is therefore imperative to better understand the risk of subsequent primary tumors to inform screening and treatment recommendations.

In this cohort study, Dr. Zaba and colleagues identified 6,146 patients from 17 registries of the Surveillance, Epidemiology, and End Results (SEER) Program who had been diagnosed with a first primary cutaneous MCC between 2000 and 2018.

Endpoints were the ratio of observed to expected number of cases of subsequent cancer (Standardized incidence ratio, or SIR) and the excess risk.

Overall, there was an elevated risk of developing a subsequent primary cancer after being diagnosed with MCC (SIR, 1.28; excess risk, 57.25 per 10,000 person-years). This included the risk for all solid tumors including liver (SIR, 1.92; excess risk, 2.77 per 10,000 person-years), pancreas (SIR, 1.65; excess risk, 4.55 per 10,000 person-years), cutaneous melanoma (SIR, 2.36; excess risk, 15.27 per 10,000 person-years), and kidney (SIR, 1.64; excess risk, 3.83 per 10,000 person-years).

There was also a higher risk of developing papillary thyroid carcinoma (PTC) (SIR, 5.26; excess risk, 6.16 per 10,000 person-years).

The risk of developing hematological cancers after MCC was also increased, especially for non-Hodgkin lymphoma (SIR, 2.62; excess risk, 15.48 per 10,000 person-years) and myelodysplastic syndrome (SIR, 2.17; excess risk, 2.73 per 10,000 person-years).

The risk for developing subsequent tumors, including melanoma and non-Hodgkin lymphoma, remained significant for up to 10 years, while the risk for developing PTC and kidney cancers remained for up to 5 years.

“After 3-5 years, when a MCC patient’s risk of MCC recurrence drops below 2%, we do not currently have guidelines in place for additional cancer screening,” Dr. Zaba said. “Regarding patient education, patients with MCC are educated to let us know if they experience any symptoms of cancer between visits, including unintentional weight loss, night sweats, headaches that increasingly worsen, or growing lumps or bumps. These symptoms may occur in a multitude of cancers and not just MCC.”

Weighing in on the study, Jeffrey M. Farma, MD, interim chair, department of surgical oncology at Fox Chase Cancer Center, Philadelphia, noted that MCC is considered to be high risk because of its chances of recurring after surgical resection or spreading to lymph nodes or other areas of the body. “There are approximately 3,000 new cases of melanoma a year in the U.S., and it is 40 times rarer than melanoma,” he said. “Patients are usually diagnosed with Merkel cell carcinoma later in life, and the tumors have been associated with sun exposure and immunosuppression and have also been associated with the polyomavirus.”

That said, however, he emphasized that great strides have been made in treatment. “These tumors are very sensitive to radiation, and we generally treat earlier-stage MCC with a combination of surgery and radiation therapy,” said Dr. Farma. “More recently we have had a lot of success with the use of immunotherapy to treat more advanced MCC.”

Dr. Zaba reported receiving grants from the Kuni Foundation outside the submitted work. No other disclosures were reported. Author Eleni Linos, MD, DrPH, MPH, is supported by grant K24AR075060 from the National Institutes of Health. No other outside funding was reported. Dr. Farma had no disclosures.

Patients with cutaneous Merkel cell carcinoma (MCC) have a higher risk of subsequently developing solid and hematologic cancers, according to a new analysis.

In a cohort of 6,146 patients with a first primary MCC, a total of 725 (11.8%) developed subsequent primary cancers. For solid tumors, the risk was highest for cutaneous melanoma and papillary thyroid carcinoma, while for hematologic cancers, the risk was increased for non-Hodgkin lymphoma.

“Our study does confirm that patients with MCC are at higher risk for developing other cancers,” study author Lisa C. Zaba, MD, PhD, associate professor of dermatology and director of the Merkel cell carcinoma multidisciplinary clinic, Stanford (Calif.) Cancer Center, said in an interview. “MCC is a highly malignant cancer with a 40% recurrence risk.”

Because of this high risk, Dr. Zaba noted that patients with MCC get frequent surveillance with both imaging studies (PET-CT and CT) as well as frequent visits in clinic with MCC experts. “Specifically, a patient with MCC is imaged and seen in clinic every 3-6 months for the first 3 years after diagnosis, and every 6-12 months thereafter for up to 5 years,” she said. “Interestingly, this high level of surveillance may be one reason that we find so many cancers in patients who have been diagnosed with MCC, compared to the general population.”

The study was published online in JAMA Dermatology.

With the death of “Margaritaville” singer Jimmy Buffett, who recently died of MCC 4 years after his diagnosis, this rare, aggressive skin cancer has been put in the spotlight. Survival has been increasing, primarily because of the advent of immunotherapy, and the authors note that it is therefore imperative to better understand the risk of subsequent primary tumors to inform screening and treatment recommendations.

In this cohort study, Dr. Zaba and colleagues identified 6,146 patients from 17 registries of the Surveillance, Epidemiology, and End Results (SEER) Program who had been diagnosed with a first primary cutaneous MCC between 2000 and 2018.

Endpoints were the ratio of observed to expected number of cases of subsequent cancer (Standardized incidence ratio, or SIR) and the excess risk.

Overall, there was an elevated risk of developing a subsequent primary cancer after being diagnosed with MCC (SIR, 1.28; excess risk, 57.25 per 10,000 person-years). This included the risk for all solid tumors including liver (SIR, 1.92; excess risk, 2.77 per 10,000 person-years), pancreas (SIR, 1.65; excess risk, 4.55 per 10,000 person-years), cutaneous melanoma (SIR, 2.36; excess risk, 15.27 per 10,000 person-years), and kidney (SIR, 1.64; excess risk, 3.83 per 10,000 person-years).

There was also a higher risk of developing papillary thyroid carcinoma (PTC) (SIR, 5.26; excess risk, 6.16 per 10,000 person-years).

The risk of developing hematological cancers after MCC was also increased, especially for non-Hodgkin lymphoma (SIR, 2.62; excess risk, 15.48 per 10,000 person-years) and myelodysplastic syndrome (SIR, 2.17; excess risk, 2.73 per 10,000 person-years).

The risk for developing subsequent tumors, including melanoma and non-Hodgkin lymphoma, remained significant for up to 10 years, while the risk for developing PTC and kidney cancers remained for up to 5 years.

“After 3-5 years, when a MCC patient’s risk of MCC recurrence drops below 2%, we do not currently have guidelines in place for additional cancer screening,” Dr. Zaba said. “Regarding patient education, patients with MCC are educated to let us know if they experience any symptoms of cancer between visits, including unintentional weight loss, night sweats, headaches that increasingly worsen, or growing lumps or bumps. These symptoms may occur in a multitude of cancers and not just MCC.”

Weighing in on the study, Jeffrey M. Farma, MD, interim chair, department of surgical oncology at Fox Chase Cancer Center, Philadelphia, noted that MCC is considered to be high risk because of its chances of recurring after surgical resection or spreading to lymph nodes or other areas of the body. “There are approximately 3,000 new cases of melanoma a year in the U.S., and it is 40 times rarer than melanoma,” he said. “Patients are usually diagnosed with Merkel cell carcinoma later in life, and the tumors have been associated with sun exposure and immunosuppression and have also been associated with the polyomavirus.”

That said, however, he emphasized that great strides have been made in treatment. “These tumors are very sensitive to radiation, and we generally treat earlier-stage MCC with a combination of surgery and radiation therapy,” said Dr. Farma. “More recently we have had a lot of success with the use of immunotherapy to treat more advanced MCC.”

Dr. Zaba reported receiving grants from the Kuni Foundation outside the submitted work. No other disclosures were reported. Author Eleni Linos, MD, DrPH, MPH, is supported by grant K24AR075060 from the National Institutes of Health. No other outside funding was reported. Dr. Farma had no disclosures.

Patients with cutaneous Merkel cell carcinoma (MCC) have a higher risk of subsequently developing solid and hematologic cancers, according to a new analysis.

In a cohort of 6,146 patients with a first primary MCC, a total of 725 (11.8%) developed subsequent primary cancers. For solid tumors, the risk was highest for cutaneous melanoma and papillary thyroid carcinoma, while for hematologic cancers, the risk was increased for non-Hodgkin lymphoma.

“Our study does confirm that patients with MCC are at higher risk for developing other cancers,” study author Lisa C. Zaba, MD, PhD, associate professor of dermatology and director of the Merkel cell carcinoma multidisciplinary clinic, Stanford (Calif.) Cancer Center, said in an interview. “MCC is a highly malignant cancer with a 40% recurrence risk.”

Because of this high risk, Dr. Zaba noted that patients with MCC get frequent surveillance with both imaging studies (PET-CT and CT) as well as frequent visits in clinic with MCC experts. “Specifically, a patient with MCC is imaged and seen in clinic every 3-6 months for the first 3 years after diagnosis, and every 6-12 months thereafter for up to 5 years,” she said. “Interestingly, this high level of surveillance may be one reason that we find so many cancers in patients who have been diagnosed with MCC, compared to the general population.”

The study was published online in JAMA Dermatology.

With the death of “Margaritaville” singer Jimmy Buffett, who recently died of MCC 4 years after his diagnosis, this rare, aggressive skin cancer has been put in the spotlight. Survival has been increasing, primarily because of the advent of immunotherapy, and the authors note that it is therefore imperative to better understand the risk of subsequent primary tumors to inform screening and treatment recommendations.

In this cohort study, Dr. Zaba and colleagues identified 6,146 patients from 17 registries of the Surveillance, Epidemiology, and End Results (SEER) Program who had been diagnosed with a first primary cutaneous MCC between 2000 and 2018.

Endpoints were the ratio of observed to expected number of cases of subsequent cancer (Standardized incidence ratio, or SIR) and the excess risk.

Overall, there was an elevated risk of developing a subsequent primary cancer after being diagnosed with MCC (SIR, 1.28; excess risk, 57.25 per 10,000 person-years). This included the risk for all solid tumors including liver (SIR, 1.92; excess risk, 2.77 per 10,000 person-years), pancreas (SIR, 1.65; excess risk, 4.55 per 10,000 person-years), cutaneous melanoma (SIR, 2.36; excess risk, 15.27 per 10,000 person-years), and kidney (SIR, 1.64; excess risk, 3.83 per 10,000 person-years).

There was also a higher risk of developing papillary thyroid carcinoma (PTC) (SIR, 5.26; excess risk, 6.16 per 10,000 person-years).

The risk of developing hematological cancers after MCC was also increased, especially for non-Hodgkin lymphoma (SIR, 2.62; excess risk, 15.48 per 10,000 person-years) and myelodysplastic syndrome (SIR, 2.17; excess risk, 2.73 per 10,000 person-years).

The risk for developing subsequent tumors, including melanoma and non-Hodgkin lymphoma, remained significant for up to 10 years, while the risk for developing PTC and kidney cancers remained for up to 5 years.

“After 3-5 years, when a MCC patient’s risk of MCC recurrence drops below 2%, we do not currently have guidelines in place for additional cancer screening,” Dr. Zaba said. “Regarding patient education, patients with MCC are educated to let us know if they experience any symptoms of cancer between visits, including unintentional weight loss, night sweats, headaches that increasingly worsen, or growing lumps or bumps. These symptoms may occur in a multitude of cancers and not just MCC.”

Weighing in on the study, Jeffrey M. Farma, MD, interim chair, department of surgical oncology at Fox Chase Cancer Center, Philadelphia, noted that MCC is considered to be high risk because of its chances of recurring after surgical resection or spreading to lymph nodes or other areas of the body. “There are approximately 3,000 new cases of melanoma a year in the U.S., and it is 40 times rarer than melanoma,” he said. “Patients are usually diagnosed with Merkel cell carcinoma later in life, and the tumors have been associated with sun exposure and immunosuppression and have also been associated with the polyomavirus.”

That said, however, he emphasized that great strides have been made in treatment. “These tumors are very sensitive to radiation, and we generally treat earlier-stage MCC with a combination of surgery and radiation therapy,” said Dr. Farma. “More recently we have had a lot of success with the use of immunotherapy to treat more advanced MCC.”

Dr. Zaba reported receiving grants from the Kuni Foundation outside the submitted work. No other disclosures were reported. Author Eleni Linos, MD, DrPH, MPH, is supported by grant K24AR075060 from the National Institutes of Health. No other outside funding was reported. Dr. Farma had no disclosures.

PURPOSE

This study addresses a gap in knowledge regarding socioeconomic factors, facility type, and overall survival in stage I vs stage IV Amelanotic Melanoma.

BACKGROUND

Amelanotic Melanoma (AM) is a rare form of melanoma that lacks pigment and accounts for approximately 5% of melanomas. Light skin color and increasing age are important risk factors. Although curable when diagnosed early, it is often missed or mistaken for other benign conditions. A study investigating the impact of facility type on overall survival between stage I vs stage IV AM has yet to be done.

METHODS

This is a retrospective study of patients diagnosed with Amelanotic Melanoma (ICD-8730) between 2004 and 2020 in the National Cancer Database (NCDB) to compare demographic features and overall survival (n = 2147). Exclusion criteria included missing data.

DATA ANALYSIS

Descriptive statistics for all AM patients were collected. Median household income and facility type were compared between patients diagnosed with stage I and stage IV AM using Pearson Chi- Square test. Breslow thickness and overall survival between stage I and stage IV were evaluated using independent t-test and Kaplan-Meier test, respectively. All variables were evaluated for a significance of P < .05.

RESULTS

Most cases analyzed were White (98.1%), male (58.6%), and had Medicare as the primary payor at diagnosis (51.1%). Of 2147 cases, 497 were stage I (23.1%) and 164 were stage IV AM (7.6%) with a mean age at diagnosis of 66.05 and 63.72 years, respectively. There was a significant difference in overall survival between stage I (mean = 118.7 months) and stage 4 (mean = 42.4 months, P < 0.001). The average Breslow thickness was 1.17mm in stage I and 2.59mm in stage IV (P<0.05). More patients diagnosed at stage I used academic facilities than those diagnosed at stage IV (43.9% vs 33.8%, P<0.05). Most patients diagnosed at stage I were high income compared to patients diagnosed at stage IV (55% vs 43.2%, P<0.05).

CONCLUSIONS

With the overall survival of stage IV AM being significantly worse, we hope this study can provide a starting point in the study and prevention of disparities in the early diagnosis of AM.

PURPOSE

This study addresses a gap in knowledge regarding socioeconomic factors, facility type, and overall survival in stage I vs stage IV Amelanotic Melanoma.

BACKGROUND

Amelanotic Melanoma (AM) is a rare form of melanoma that lacks pigment and accounts for approximately 5% of melanomas. Light skin color and increasing age are important risk factors. Although curable when diagnosed early, it is often missed or mistaken for other benign conditions. A study investigating the impact of facility type on overall survival between stage I vs stage IV AM has yet to be done.

METHODS

This is a retrospective study of patients diagnosed with Amelanotic Melanoma (ICD-8730) between 2004 and 2020 in the National Cancer Database (NCDB) to compare demographic features and overall survival (n = 2147). Exclusion criteria included missing data.

DATA ANALYSIS

Descriptive statistics for all AM patients were collected. Median household income and facility type were compared between patients diagnosed with stage I and stage IV AM using Pearson Chi- Square test. Breslow thickness and overall survival between stage I and stage IV were evaluated using independent t-test and Kaplan-Meier test, respectively. All variables were evaluated for a significance of P < .05.

RESULTS

Most cases analyzed were White (98.1%), male (58.6%), and had Medicare as the primary payor at diagnosis (51.1%). Of 2147 cases, 497 were stage I (23.1%) and 164 were stage IV AM (7.6%) with a mean age at diagnosis of 66.05 and 63.72 years, respectively. There was a significant difference in overall survival between stage I (mean = 118.7 months) and stage 4 (mean = 42.4 months, P < 0.001). The average Breslow thickness was 1.17mm in stage I and 2.59mm in stage IV (P<0.05). More patients diagnosed at stage I used academic facilities than those diagnosed at stage IV (43.9% vs 33.8%, P<0.05). Most patients diagnosed at stage I were high income compared to patients diagnosed at stage IV (55% vs 43.2%, P<0.05).

CONCLUSIONS

With the overall survival of stage IV AM being significantly worse, we hope this study can provide a starting point in the study and prevention of disparities in the early diagnosis of AM.

PURPOSE

This study addresses a gap in knowledge regarding socioeconomic factors, facility type, and overall survival in stage I vs stage IV Amelanotic Melanoma.

BACKGROUND

Amelanotic Melanoma (AM) is a rare form of melanoma that lacks pigment and accounts for approximately 5% of melanomas. Light skin color and increasing age are important risk factors. Although curable when diagnosed early, it is often missed or mistaken for other benign conditions. A study investigating the impact of facility type on overall survival between stage I vs stage IV AM has yet to be done.

METHODS

This is a retrospective study of patients diagnosed with Amelanotic Melanoma (ICD-8730) between 2004 and 2020 in the National Cancer Database (NCDB) to compare demographic features and overall survival (n = 2147). Exclusion criteria included missing data.

DATA ANALYSIS

Descriptive statistics for all AM patients were collected. Median household income and facility type were compared between patients diagnosed with stage I and stage IV AM using Pearson Chi- Square test. Breslow thickness and overall survival between stage I and stage IV were evaluated using independent t-test and Kaplan-Meier test, respectively. All variables were evaluated for a significance of P < .05.

RESULTS

Most cases analyzed were White (98.1%), male (58.6%), and had Medicare as the primary payor at diagnosis (51.1%). Of 2147 cases, 497 were stage I (23.1%) and 164 were stage IV AM (7.6%) with a mean age at diagnosis of 66.05 and 63.72 years, respectively. There was a significant difference in overall survival between stage I (mean = 118.7 months) and stage 4 (mean = 42.4 months, P < 0.001). The average Breslow thickness was 1.17mm in stage I and 2.59mm in stage IV (P<0.05). More patients diagnosed at stage I used academic facilities than those diagnosed at stage IV (43.9% vs 33.8%, P<0.05). Most patients diagnosed at stage I were high income compared to patients diagnosed at stage IV (55% vs 43.2%, P<0.05).

CONCLUSIONS

With the overall survival of stage IV AM being significantly worse, we hope this study can provide a starting point in the study and prevention of disparities in the early diagnosis of AM.

PURPOSE

Assess the clinical impact (CI) of UV-related DNA damage signatures (UVsig) in Veterans with cancer of unknown primary (CUP) and cancer of extracutaneous origin (CEO).

BACKGROUND

UVsig have been reported in CUP and CEO (i.e. head and neck cancer and lung cancer). The presence of UVsig suggests a cutaneous origin and potential misclassification of CEO using conventional histopathologic evaluation. Literature on the association of UVsig in pan-cancer genomics is limited.

METHODS

This is a retrospective study of Veterans who underwent comprehensive genomic profiling with FoundationOne CDx during 2/1/2019 to 9/30/2022 through the VA National Precision Oncology Program. The outcome was the CI of UVsig (high, medium, and low) determined by blinded chart reviews: (1) high: UVsig leading to change in diagnoses (CID) and a different first-line therapy (FLT) would have been offered; (2) medium: UVsig leading to CID, but appropriate FLT offered; (3) low: diagnoses modified by clinicians and treated as cutaneous cancers. NCCN Guidelines were referenced for FLT.

DATA ANALYSIS

Descriptive statistics and chi-square tests were utilized to evaluate the UVsig CI.

RESULTS

Among 5,565 cases with 10 or more assessable alterations for UVsig analysis, 650 (11.7%) were positive for UVsig. CUP and CEO cohorts each had 41 cases analyzed. In the CUP cases, 20 (48.8%), 9 (21.9%), and 12 (29.3%) were categorized as having high, medium, and low CI, respectively; and in the CEO cases, it was 22 (53.7%), 15 (36.6%), and 4 (9.8%). There was no difference statistically between the CUP and CEO groups on the percentage distribution of CI (p=0.06). Among the 42 out of 82 cases having high CI, 37 (88.1%) received cytotoxic chemotherapy without any indication, and 5 (11.9%) were not offered immunotherapy (IO) as FLT. More than half of the 82 cases had high CI; more than 90% of the CEO cases had high and medium CI.

IMPLICATIONS

UVsig serves as a useful biomarker for cancers with cutaneous origin. About 1% of the 5,565 cases analyzed had high UVsig CI. Knowledge of UVsig could lead to omission of chemotherapy (hence avoiding toxicities) or addition of IO (for potential benefits).

PURPOSE

Assess the clinical impact (CI) of UV-related DNA damage signatures (UVsig) in Veterans with cancer of unknown primary (CUP) and cancer of extracutaneous origin (CEO).

BACKGROUND

UVsig have been reported in CUP and CEO (i.e. head and neck cancer and lung cancer). The presence of UVsig suggests a cutaneous origin and potential misclassification of CEO using conventional histopathologic evaluation. Literature on the association of UVsig in pan-cancer genomics is limited.

METHODS

This is a retrospective study of Veterans who underwent comprehensive genomic profiling with FoundationOne CDx during 2/1/2019 to 9/30/2022 through the VA National Precision Oncology Program. The outcome was the CI of UVsig (high, medium, and low) determined by blinded chart reviews: (1) high: UVsig leading to change in diagnoses (CID) and a different first-line therapy (FLT) would have been offered; (2) medium: UVsig leading to CID, but appropriate FLT offered; (3) low: diagnoses modified by clinicians and treated as cutaneous cancers. NCCN Guidelines were referenced for FLT.

DATA ANALYSIS

Descriptive statistics and chi-square tests were utilized to evaluate the UVsig CI.

RESULTS

Among 5,565 cases with 10 or more assessable alterations for UVsig analysis, 650 (11.7%) were positive for UVsig. CUP and CEO cohorts each had 41 cases analyzed. In the CUP cases, 20 (48.8%), 9 (21.9%), and 12 (29.3%) were categorized as having high, medium, and low CI, respectively; and in the CEO cases, it was 22 (53.7%), 15 (36.6%), and 4 (9.8%). There was no difference statistically between the CUP and CEO groups on the percentage distribution of CI (p=0.06). Among the 42 out of 82 cases having high CI, 37 (88.1%) received cytotoxic chemotherapy without any indication, and 5 (11.9%) were not offered immunotherapy (IO) as FLT. More than half of the 82 cases had high CI; more than 90% of the CEO cases had high and medium CI.

IMPLICATIONS

UVsig serves as a useful biomarker for cancers with cutaneous origin. About 1% of the 5,565 cases analyzed had high UVsig CI. Knowledge of UVsig could lead to omission of chemotherapy (hence avoiding toxicities) or addition of IO (for potential benefits).

PURPOSE

Assess the clinical impact (CI) of UV-related DNA damage signatures (UVsig) in Veterans with cancer of unknown primary (CUP) and cancer of extracutaneous origin (CEO).

BACKGROUND

UVsig have been reported in CUP and CEO (i.e. head and neck cancer and lung cancer). The presence of UVsig suggests a cutaneous origin and potential misclassification of CEO using conventional histopathologic evaluation. Literature on the association of UVsig in pan-cancer genomics is limited.

METHODS

This is a retrospective study of Veterans who underwent comprehensive genomic profiling with FoundationOne CDx during 2/1/2019 to 9/30/2022 through the VA National Precision Oncology Program. The outcome was the CI of UVsig (high, medium, and low) determined by blinded chart reviews: (1) high: UVsig leading to change in diagnoses (CID) and a different first-line therapy (FLT) would have been offered; (2) medium: UVsig leading to CID, but appropriate FLT offered; (3) low: diagnoses modified by clinicians and treated as cutaneous cancers. NCCN Guidelines were referenced for FLT.

DATA ANALYSIS

Descriptive statistics and chi-square tests were utilized to evaluate the UVsig CI.

RESULTS

Among 5,565 cases with 10 or more assessable alterations for UVsig analysis, 650 (11.7%) were positive for UVsig. CUP and CEO cohorts each had 41 cases analyzed. In the CUP cases, 20 (48.8%), 9 (21.9%), and 12 (29.3%) were categorized as having high, medium, and low CI, respectively; and in the CEO cases, it was 22 (53.7%), 15 (36.6%), and 4 (9.8%). There was no difference statistically between the CUP and CEO groups on the percentage distribution of CI (p=0.06). Among the 42 out of 82 cases having high CI, 37 (88.1%) received cytotoxic chemotherapy without any indication, and 5 (11.9%) were not offered immunotherapy (IO) as FLT. More than half of the 82 cases had high CI; more than 90% of the CEO cases had high and medium CI.

IMPLICATIONS

UVsig serves as a useful biomarker for cancers with cutaneous origin. About 1% of the 5,565 cases analyzed had high UVsig CI. Knowledge of UVsig could lead to omission of chemotherapy (hence avoiding toxicities) or addition of IO (for potential benefits).

Artificial intelligence chatbots can give accurate information to common questions about cancer but not so much when it comes to providing evidence-based cancer treatment recommendations, two new studies suggest.

AI chatbots, such as ChatGPT (OpenAI), are becoming go-to sources for health information. However, no studies have rigorously evaluated the quality of their medical advice, especially for cancer.

Two new studies published in JAMA Oncology did just that.

One, which looked at common cancer-related Google searches, found that AI chatbots generally provide accurate information to consumers, but the information’s usefulness may be limited by its complexity.

The other, which assessed cancer treatment recommendations, found that AI chatbots overall missed the mark on providing recommendations for breast, prostate, and lung cancers in line with national treatment guidelines.

The medical world is becoming “enamored with our newest potential helper, large language models (LLMs) and in particular chatbots, such as ChatGPT,” Atul Butte, MD, PhD, who heads the Bakar Computational Health Sciences Institute, University of California, San Francisco, wrote in an editorial accompanying the studies. “But maybe our core belief in GPT technology as a clinical partner has not sufficiently been earned yet.”

The first study by Alexander Pan of the State University of New York, Brooklyn, and colleagues analyzed the quality of responses to the top five most searched questions on skin, lung, breast, colorectal, and prostate cancer provided by four AI chatbots: ChatGPT-3.5, Perplexity (Perplexity.AI), Chatsonic (Writesonic), and Bing AI (Microsoft).

Questions included what is skin cancer and what are symptoms of prostate, lung, or breast cancer? The team rated the responses for quality, clarity, actionability, misinformation, and readability.

The researchers found that the four chatbots generated “high-quality” responses about the five cancers and did not appear to spread misinformation. Three of the four chatbots cited reputable sources, such as the American Cancer Society, Mayo Clinic, and Centers for Disease Controls and Prevention, which is “reassuring,” the researchers said.

However, the team also found that the usefulness of the information was “limited” because responses were often written at a college reading level. Another limitation: AI chatbots provided concise answers with no visual aids, which may not be sufficient to explain more complex ideas to consumers.

“These limitations suggest that AI chatbots should be used [supplementally] and not as a primary source for medical information,” the authors said, adding that the chatbots “typically acknowledged their limitations in providing individualized advice and encouraged users to seek medical attention.”

A related study in the journal highlighted the ability of AI chatbots to generate appropriate cancer treatment recommendations.

In this analysis, Shan Chen, MS, with the AI in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, and colleagues benchmarked cancer treatment recommendations made by ChatGPT-3.5 against 2021 National Comprehensive Cancer Network guidelines.

The team created 104 prompts designed to elicit basic treatment strategies for various types of cancer, including breast, prostate, and lung cancer. Questions included “What is the treatment for stage I breast cancer?” Several oncologists then assessed the level of concordance between the chatbot responses and NCCN guidelines.

In 62% of the prompts and answers, all the recommended treatments aligned with the oncologists’ views.

The chatbot provided at least one guideline-concordant treatment for 98% of prompts. However, for 34% of prompts, the chatbot also recommended at least one nonconcordant treatment.

And about 13% of recommended treatments were “hallucinated,” that is, not part of any recommended treatment. Hallucinations were primarily recommendations for localized treatment of advanced disease, targeted therapy, or immunotherapy.

Based on the findings, the team recommended that clinicians advise patients that AI chatbots are not a reliable source of cancer treatment information.

“The chatbot did not perform well at providing accurate cancer treatment recommendations,” the authors said. “The chatbot was most likely to mix in incorrect recommendations among correct ones, an error difficult even for experts to detect.”

In his editorial, Dr. Butte highlighted several caveats, including that the teams evaluated “off the shelf” chatbots, which likely had no specific medical training, and the prompts

designed in both studies were very basic, which may have limited their specificity or actionability. Newer LLMs with specific health care training are being released, he explained.

Despite the mixed study findings, Dr. Butte remains optimistic about the future of AI in medicine.

“Today, the reality is that the highest-quality care is concentrated within a few premier medical systems like the NCI Comprehensive Cancer Centers, accessible only to a small fraction of the global population,” Dr. Butte explained. “However, AI has the potential to change this.”

How can we make this happen?

AI algorithms would need to be trained with “data from the best medical systems globally” and “the latest guidelines from NCCN and elsewhere.” Digital health platforms powered by AI could then be designed to provide resources and advice to patients around the globe, Dr. Butte said.

Although “these algorithms will need to be carefully monitored as they are brought into health systems,” Dr. Butte said, it does not change their potential to “improve care for both the haves and have-nots of health care.”

The study by Mr. Pan and colleagues had no specific funding; one author, Stacy Loeb, MD, MSc, PhD, reported a disclosure; no other disclosures were reported. The study by Shan Chen and colleagues was supported by the Woods Foundation; several authors reported disclosures outside the submitted work. Dr. Butte disclosed relationships with several pharmaceutical companies.

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

Artificial intelligence chatbots can give accurate information to common questions about cancer but not so much when it comes to providing evidence-based cancer treatment recommendations, two new studies suggest.

AI chatbots, such as ChatGPT (OpenAI), are becoming go-to sources for health information. However, no studies have rigorously evaluated the quality of their medical advice, especially for cancer.

Two new studies published in JAMA Oncology did just that.

One, which looked at common cancer-related Google searches, found that AI chatbots generally provide accurate information to consumers, but the information’s usefulness may be limited by its complexity.

The other, which assessed cancer treatment recommendations, found that AI chatbots overall missed the mark on providing recommendations for breast, prostate, and lung cancers in line with national treatment guidelines.

The medical world is becoming “enamored with our newest potential helper, large language models (LLMs) and in particular chatbots, such as ChatGPT,” Atul Butte, MD, PhD, who heads the Bakar Computational Health Sciences Institute, University of California, San Francisco, wrote in an editorial accompanying the studies. “But maybe our core belief in GPT technology as a clinical partner has not sufficiently been earned yet.”

The first study by Alexander Pan of the State University of New York, Brooklyn, and colleagues analyzed the quality of responses to the top five most searched questions on skin, lung, breast, colorectal, and prostate cancer provided by four AI chatbots: ChatGPT-3.5, Perplexity (Perplexity.AI), Chatsonic (Writesonic), and Bing AI (Microsoft).

Questions included what is skin cancer and what are symptoms of prostate, lung, or breast cancer? The team rated the responses for quality, clarity, actionability, misinformation, and readability.

The researchers found that the four chatbots generated “high-quality” responses about the five cancers and did not appear to spread misinformation. Three of the four chatbots cited reputable sources, such as the American Cancer Society, Mayo Clinic, and Centers for Disease Controls and Prevention, which is “reassuring,” the researchers said.

However, the team also found that the usefulness of the information was “limited” because responses were often written at a college reading level. Another limitation: AI chatbots provided concise answers with no visual aids, which may not be sufficient to explain more complex ideas to consumers.

“These limitations suggest that AI chatbots should be used [supplementally] and not as a primary source for medical information,” the authors said, adding that the chatbots “typically acknowledged their limitations in providing individualized advice and encouraged users to seek medical attention.”

A related study in the journal highlighted the ability of AI chatbots to generate appropriate cancer treatment recommendations.

In this analysis, Shan Chen, MS, with the AI in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, and colleagues benchmarked cancer treatment recommendations made by ChatGPT-3.5 against 2021 National Comprehensive Cancer Network guidelines.

The team created 104 prompts designed to elicit basic treatment strategies for various types of cancer, including breast, prostate, and lung cancer. Questions included “What is the treatment for stage I breast cancer?” Several oncologists then assessed the level of concordance between the chatbot responses and NCCN guidelines.

In 62% of the prompts and answers, all the recommended treatments aligned with the oncologists’ views.

The chatbot provided at least one guideline-concordant treatment for 98% of prompts. However, for 34% of prompts, the chatbot also recommended at least one nonconcordant treatment.

And about 13% of recommended treatments were “hallucinated,” that is, not part of any recommended treatment. Hallucinations were primarily recommendations for localized treatment of advanced disease, targeted therapy, or immunotherapy.

Based on the findings, the team recommended that clinicians advise patients that AI chatbots are not a reliable source of cancer treatment information.

“The chatbot did not perform well at providing accurate cancer treatment recommendations,” the authors said. “The chatbot was most likely to mix in incorrect recommendations among correct ones, an error difficult even for experts to detect.”

In his editorial, Dr. Butte highlighted several caveats, including that the teams evaluated “off the shelf” chatbots, which likely had no specific medical training, and the prompts

designed in both studies were very basic, which may have limited their specificity or actionability. Newer LLMs with specific health care training are being released, he explained.

Despite the mixed study findings, Dr. Butte remains optimistic about the future of AI in medicine.

“Today, the reality is that the highest-quality care is concentrated within a few premier medical systems like the NCI Comprehensive Cancer Centers, accessible only to a small fraction of the global population,” Dr. Butte explained. “However, AI has the potential to change this.”

How can we make this happen?

AI algorithms would need to be trained with “data from the best medical systems globally” and “the latest guidelines from NCCN and elsewhere.” Digital health platforms powered by AI could then be designed to provide resources and advice to patients around the globe, Dr. Butte said.

Although “these algorithms will need to be carefully monitored as they are brought into health systems,” Dr. Butte said, it does not change their potential to “improve care for both the haves and have-nots of health care.”

The study by Mr. Pan and colleagues had no specific funding; one author, Stacy Loeb, MD, MSc, PhD, reported a disclosure; no other disclosures were reported. The study by Shan Chen and colleagues was supported by the Woods Foundation; several authors reported disclosures outside the submitted work. Dr. Butte disclosed relationships with several pharmaceutical companies.

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

Artificial intelligence chatbots can give accurate information to common questions about cancer but not so much when it comes to providing evidence-based cancer treatment recommendations, two new studies suggest.

AI chatbots, such as ChatGPT (OpenAI), are becoming go-to sources for health information. However, no studies have rigorously evaluated the quality of their medical advice, especially for cancer.

Two new studies published in JAMA Oncology did just that.

One, which looked at common cancer-related Google searches, found that AI chatbots generally provide accurate information to consumers, but the information’s usefulness may be limited by its complexity.

The other, which assessed cancer treatment recommendations, found that AI chatbots overall missed the mark on providing recommendations for breast, prostate, and lung cancers in line with national treatment guidelines.

The medical world is becoming “enamored with our newest potential helper, large language models (LLMs) and in particular chatbots, such as ChatGPT,” Atul Butte, MD, PhD, who heads the Bakar Computational Health Sciences Institute, University of California, San Francisco, wrote in an editorial accompanying the studies. “But maybe our core belief in GPT technology as a clinical partner has not sufficiently been earned yet.”

The first study by Alexander Pan of the State University of New York, Brooklyn, and colleagues analyzed the quality of responses to the top five most searched questions on skin, lung, breast, colorectal, and prostate cancer provided by four AI chatbots: ChatGPT-3.5, Perplexity (Perplexity.AI), Chatsonic (Writesonic), and Bing AI (Microsoft).

Questions included what is skin cancer and what are symptoms of prostate, lung, or breast cancer? The team rated the responses for quality, clarity, actionability, misinformation, and readability.

The researchers found that the four chatbots generated “high-quality” responses about the five cancers and did not appear to spread misinformation. Three of the four chatbots cited reputable sources, such as the American Cancer Society, Mayo Clinic, and Centers for Disease Controls and Prevention, which is “reassuring,” the researchers said.

However, the team also found that the usefulness of the information was “limited” because responses were often written at a college reading level. Another limitation: AI chatbots provided concise answers with no visual aids, which may not be sufficient to explain more complex ideas to consumers.

“These limitations suggest that AI chatbots should be used [supplementally] and not as a primary source for medical information,” the authors said, adding that the chatbots “typically acknowledged their limitations in providing individualized advice and encouraged users to seek medical attention.”

A related study in the journal highlighted the ability of AI chatbots to generate appropriate cancer treatment recommendations.

In this analysis, Shan Chen, MS, with the AI in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, and colleagues benchmarked cancer treatment recommendations made by ChatGPT-3.5 against 2021 National Comprehensive Cancer Network guidelines.

The team created 104 prompts designed to elicit basic treatment strategies for various types of cancer, including breast, prostate, and lung cancer. Questions included “What is the treatment for stage I breast cancer?” Several oncologists then assessed the level of concordance between the chatbot responses and NCCN guidelines.

In 62% of the prompts and answers, all the recommended treatments aligned with the oncologists’ views.

The chatbot provided at least one guideline-concordant treatment for 98% of prompts. However, for 34% of prompts, the chatbot also recommended at least one nonconcordant treatment.

And about 13% of recommended treatments were “hallucinated,” that is, not part of any recommended treatment. Hallucinations were primarily recommendations for localized treatment of advanced disease, targeted therapy, or immunotherapy.

Based on the findings, the team recommended that clinicians advise patients that AI chatbots are not a reliable source of cancer treatment information.

“The chatbot did not perform well at providing accurate cancer treatment recommendations,” the authors said. “The chatbot was most likely to mix in incorrect recommendations among correct ones, an error difficult even for experts to detect.”

In his editorial, Dr. Butte highlighted several caveats, including that the teams evaluated “off the shelf” chatbots, which likely had no specific medical training, and the prompts

designed in both studies were very basic, which may have limited their specificity or actionability. Newer LLMs with specific health care training are being released, he explained.

Despite the mixed study findings, Dr. Butte remains optimistic about the future of AI in medicine.

“Today, the reality is that the highest-quality care is concentrated within a few premier medical systems like the NCI Comprehensive Cancer Centers, accessible only to a small fraction of the global population,” Dr. Butte explained. “However, AI has the potential to change this.”

How can we make this happen?

AI algorithms would need to be trained with “data from the best medical systems globally” and “the latest guidelines from NCCN and elsewhere.” Digital health platforms powered by AI could then be designed to provide resources and advice to patients around the globe, Dr. Butte said.

Although “these algorithms will need to be carefully monitored as they are brought into health systems,” Dr. Butte said, it does not change their potential to “improve care for both the haves and have-nots of health care.”

The study by Mr. Pan and colleagues had no specific funding; one author, Stacy Loeb, MD, MSc, PhD, reported a disclosure; no other disclosures were reported. The study by Shan Chen and colleagues was supported by the Woods Foundation; several authors reported disclosures outside the submitted work. Dr. Butte disclosed relationships with several pharmaceutical companies.

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

Practice Gap

Wound dressings protect the skin and prevent contamination. The hair often makes it difficult to affix a dressing after a minor scalp trauma or local surgery on the head. Traditional approaches for fastening a dressing on the head include bandage winding or adhesive tape, but these methods often affect aesthetics or cause discomfort—bandage winding can make it inconvenient for the patient to move their head, and adhesive tape can cause pain by pulling the hair during removal.

To better position a scalp dressing, tie-over dressings, braid dressings, and paper clips have been used as fixators.^1-3 These methods have benefits and disadvantages.

Tie-over Dressing—The dressing is clasped with long sutures that were reserved during wound closure. This method is sturdy, can slightly compress the wound, and is applicable to any part of the scalp. However, it requires more sutures, and more careful wound care may be required due to the edge of the dressing being close to the wound.

Braid Dressing—Tape, a rubber band, or braided hair is used to bind the gauze pad. This dressing is simple and inexpensive. However, it is limited to patients with long hair; even then, it often is difficult to anchor the dressing by braiding hair. Moreover, removal of the rubber band and tape can cause discomfort or pain.

Paper Clip—This is a simple scalp dressing fixator. However, due to the short and circular structure of the clip, it is not conducive to affixing a gauze dressing for patients with short hair, and it often hooks the gauze and hair, making it inconvenient for the physician and a source of discomfort for the patient when the paper clip is being removed.

The Technique

To address shortcomings of traditional methods, we encourage the use of hairpins to affix a dressing after a scalp wound is sutured. Two steps are required:

• Position the gauze to cover the wound and press the gauze down with your hand.
• Clamp the 4 corners of the dressing and adjacent hair with hairpins (Figure, A).

Practical Implications

Hairpins are common for fixing hairstyles and decorating hair. They are inexpensive, easy to obtain, simple in structure, convenient to use without additional discomfort, and easy to remove (Figure, B). Because most hairpins have a powerful clamping force, they can affix dressings in short hair (Figure, A). All medical staff can use hairpins to anchor the scalp dressing. Even a patient’s family members can carry out simple dressing replacement and wound cleaning using this method. Patients also have many options for hairpin styles, which is especially useful in easing the apprehension of surgery in pediatric patients.

Practice Gap

Wound dressings protect the skin and prevent contamination. The hair often makes it difficult to affix a dressing after a minor scalp trauma or local surgery on the head. Traditional approaches for fastening a dressing on the head include bandage winding or adhesive tape, but these methods often affect aesthetics or cause discomfort—bandage winding can make it inconvenient for the patient to move their head, and adhesive tape can cause pain by pulling the hair during removal.

To better position a scalp dressing, tie-over dressings, braid dressings, and paper clips have been used as fixators.^1-3 These methods have benefits and disadvantages.

Tie-over Dressing—The dressing is clasped with long sutures that were reserved during wound closure. This method is sturdy, can slightly compress the wound, and is applicable to any part of the scalp. However, it requires more sutures, and more careful wound care may be required due to the edge of the dressing being close to the wound.

Braid Dressing—Tape, a rubber band, or braided hair is used to bind the gauze pad. This dressing is simple and inexpensive. However, it is limited to patients with long hair; even then, it often is difficult to anchor the dressing by braiding hair. Moreover, removal of the rubber band and tape can cause discomfort or pain.

Paper Clip—This is a simple scalp dressing fixator. However, due to the short and circular structure of the clip, it is not conducive to affixing a gauze dressing for patients with short hair, and it often hooks the gauze and hair, making it inconvenient for the physician and a source of discomfort for the patient when the paper clip is being removed.

The Technique

To address shortcomings of traditional methods, we encourage the use of hairpins to affix a dressing after a scalp wound is sutured. Two steps are required:

• Position the gauze to cover the wound and press the gauze down with your hand.
• Clamp the 4 corners of the dressing and adjacent hair with hairpins (Figure, A).

Practical Implications

Hairpins are common for fixing hairstyles and decorating hair. They are inexpensive, easy to obtain, simple in structure, convenient to use without additional discomfort, and easy to remove (Figure, B). Because most hairpins have a powerful clamping force, they can affix dressings in short hair (Figure, A). All medical staff can use hairpins to anchor the scalp dressing. Even a patient’s family members can carry out simple dressing replacement and wound cleaning using this method. Patients also have many options for hairpin styles, which is especially useful in easing the apprehension of surgery in pediatric patients.

Practice Gap

Wound dressings protect the skin and prevent contamination. The hair often makes it difficult to affix a dressing after a minor scalp trauma or local surgery on the head. Traditional approaches for fastening a dressing on the head include bandage winding or adhesive tape, but these methods often affect aesthetics or cause discomfort—bandage winding can make it inconvenient for the patient to move their head, and adhesive tape can cause pain by pulling the hair during removal.

To better position a scalp dressing, tie-over dressings, braid dressings, and paper clips have been used as fixators.^1-3 These methods have benefits and disadvantages.

Tie-over Dressing—The dressing is clasped with long sutures that were reserved during wound closure. This method is sturdy, can slightly compress the wound, and is applicable to any part of the scalp. However, it requires more sutures, and more careful wound care may be required due to the edge of the dressing being close to the wound.

Braid Dressing—Tape, a rubber band, or braided hair is used to bind the gauze pad. This dressing is simple and inexpensive. However, it is limited to patients with long hair; even then, it often is difficult to anchor the dressing by braiding hair. Moreover, removal of the rubber band and tape can cause discomfort or pain.

Paper Clip—This is a simple scalp dressing fixator. However, due to the short and circular structure of the clip, it is not conducive to affixing a gauze dressing for patients with short hair, and it often hooks the gauze and hair, making it inconvenient for the physician and a source of discomfort for the patient when the paper clip is being removed.

The Technique

To address shortcomings of traditional methods, we encourage the use of hairpins to affix a dressing after a scalp wound is sutured. Two steps are required:

• Position the gauze to cover the wound and press the gauze down with your hand.
• Clamp the 4 corners of the dressing and adjacent hair with hairpins (Figure, A).

Practical Implications

Hairpins are common for fixing hairstyles and decorating hair. They are inexpensive, easy to obtain, simple in structure, convenient to use without additional discomfort, and easy to remove (Figure, B). Because most hairpins have a powerful clamping force, they can affix dressings in short hair (Figure, A). All medical staff can use hairpins to anchor the scalp dressing. Even a patient’s family members can carry out simple dressing replacement and wound cleaning using this method. Patients also have many options for hairpin styles, which is especially useful in easing the apprehension of surgery in pediatric patients.

An influential Nature paper predicted in 2017 that advances in artificial intelligence (AI) could unleash remarkable changes in dermatology, such as using phones to help detect skin cancer earlier.

Given that about 6.3 billion smartphones would soon be in use, this AI approach could provide a gateway for “low-cost universal access to vital diagnostic care,” wrote Justin M. Ko, MD, MBA, a dermatologist, and colleagues from Stanford (Calif.) University that included other dermatologists and engineers.

Dr. Ko and his coauthors described how they trained a computer system to identify both benign and cancerous skin lesions. They used an approach known as a convolutional neural network, often deployed for projects seeking to train computers to “see” through image analysis. They said that their test of this system found it to be on par with the performance of 21 board-certified dermatologists.

“This fast, scalable method is deployable on mobile devices and holds the potential for substantial clinical impact, including broadening the scope of primary care practice and augmenting clinical decision-making for dermatology specialists,” they wrote in their paper.

More than 6 years later, there are signs that companies are making progress toward moving skin checks using this technology into U.S. primary care settings – but only with devices that employ special tools.

It may prove tougher for companies to eventually secure the sign-off of the U.S. Food and Drug Administration for mobile apps intended to let consumers handle this task with smartphones.

Such tools would need to be proven highly accurate before release, because too many false positives mean that people would be needlessly exposed to biopsies, said Sancy A. Leachman, MD, PhD, director of the melanoma research program and chair of the department of dermatology at Oregon Health & Science University, Portland.

And false-negative readings would allow melanoma to advance and even be fatal, Dr. Leachman told this news organization.

Roxana Daneshjou, MD, PhD, a dermatologist at Stanford who has studied the promise and the pitfalls of AI in medicine, said that developers of a consumer skin-check app would need to know how people would react to their readings. That includes a good sense of how often they would appropriately seek medical care for a concerning reading. (She was not an author of the previously cited Nature paper but has published widely on AI.)

Christopher Smith

“The direct-to-consumer diagnostic space makes me nervous,” Dr. Daneshjou said in an interview. “In order to do it, you really need to have good studies in consumer populations prior to release. You need to show how effective it is with follow up.”
 

FDA shows interest – and reservations

As of July, the FDA had not yet given its okay for marketing of any consumer apps intended to help people detect signs of skin cancer, an agency spokesperson told this news organization.

To date, the agency has only cleared two AI-based products for this task, both meant to be used by dermatologists. And only one of these two products, Scibase’s Nevisense, remains in use in the United States. The other, MelaFind, has been discontinued. In 2017, Strata Skin Sciences said that the product did not win “a significant enough level of acceptance by dermatologists to justify the continued investment” in it. And the company said it notified the 90 owners of MelaFind devices in the United States that it would no longer support the device.

But another company, DermaSensor, said in a 2021 press release that it expects its AI-powered tool, also named DermaSensor, to be the “first ever FDA cleared or approved skin cancer detection device for primary care providers.”

The Miami-based firm said that the FDA had granted its product a “breakthrough” device designation. A breakthrough designation means that agency staff will offer extra help and guidance to companies in developing a product, because of its expected benefit for patients.

In a 2020 press release, 3Derm Systems, now owned by Digital Diagnostics, made a similar announcement about winning FDA breakthrough designation for an AI-powered tool intended to allow skin checks in primary care settings.

(The FDA generally does not comment on its reviews of experimental drugs and devices, but companies can do so. Several other companies have announced FDA breakthrough designations for AI-driven products intended to check for skin lesions, but these might be used in settings other than primary care.)

Both DermaSensor and Digital Diagnostics have chairs with notable track records for winning FDA approvals of other devices. DermaSensor’s Maurice Ferre, MD, also is the chairman of Insightec, which in 2016 won the first FDA approval for a device with a breakthrough designation device that uses ultrasound to treat tremors.

In 2018, the FDA allowed Digital Diagnostics, then called IDx, to introduce in the United States the first medical device using AI in primary care offices to check for signs of diabetic retinopathy. This product also had an FDA breakthrough designation. The executive chairman and founder of Digital Diagnostics is Michael Abramoff, MD, PhD, professor of engineering and ophthalmology at the University of Iowa, Iowa City. Dr. Abramoff and the team behind the AI tool for retinopathy, now called the LumineticsCore system, also scored a notable win with Medicare, which agreed to cover use of the product through a dedicated CPT code.
 

FDA draft guidance

The FDA has acknowledged the interest in broadening access to skin checks via AI.

This was a topic of discussion at a 2-day advisory committee meeting the FDA held last year. In April 2023, the FDA outlined some of its expectations for future regulation of skin-analyzing tools as part of a wide-ranging draft guidance document intended to aid companies in their efforts to develop products using a form of AI known as machine learning.

In the document, the FDA described how it might approach applications for “hypothetical” devices using this kind of AI, such as a special tool to help primary care clinicians identify lesions in need of further investigation. Such a product would use a specific camera for gathering data for its initial clearance, in the FDA’s hypothetical scenario.

The FDA staff offered technical suggestions about what the developer of this hypothetical device would have to do to extend its use to smartphones and tablets while keeping clinicians as the intended users.

Some of these expanded uses could fall within the bounds of the FDA’s initial clearance and thus not trigger a need for a new marketing submission, the agency said. But seeking to shift this hypothetical product to “patient-facing” use would require a new marketing submission to the FDA, the agency said.

In this scenario, a company would expect people to follow up with a dermatologist after receiving a report suggesting cancer. Thus, this kind of a change could expose patients to “many new, unconsidered risks,” the FDA said.
 

Reality check?

The state of current efforts to develop consumer apps for checking for skin cancer seems to be summarized well on the website for the MoleMapper. The app was developed by researchers at OHSU to help people track how their moles change over time.

“Mole Mapper is NOT designed to provide medical advice, professional diagnosis, opinion, or treatment. Currently, there is not enough data to develop an app that can diagnose melanoma, but if enough data is collected through Mole Mapper and shared with researchers, it may be possible in the future,” the app’s website says.

OHSU released MoleMapper as an iPhone app in 2015. The aim of this project was to help people track the moles on their skin while also fostering an experiment in “citizen science,” OHSU’s Dr. Leachman told this news organization.

OHSU researchers hoped that the digital images taken by members of the public on cell phones could one day be used to develop diagnostic algorithms for melanoma.

But around 2017, the MoleMapper team realized that they would not be able to create a diagnostic app at this time, Dr. Leachman explained. They could not collect enough data of adequate quality.

And by 2021, it was clear that they could not even develop a successful app to triage patients to assess who needs to be seen quickly. The amount of data required was, at this point, beyond what the team could collect, Dr. Leachman said in an interview.

That was a disappointment because the team had successfully completed the difficult task of creating a confidential pathway for collecting these images via both iPhones and smartphones run on Android.

“We thought if we built it, people would come, but that’s not what happened,” Dr. Leachman said. Many patients didn’t want their images used for research or would fail to follow up with details of biopsy reports. Sometimes images were not captured well enough to be of use.

“You need at least hundreds of thousands, if not millions, of data points that have been verified with pathologies, and nobody was giving us back that data. That was the reality,” Dr. Leachman said.

There were valuable lessons in that setback. The OHSU team now has a better grasp of the challenges of trying to build a data-collection system that could prove helpful in assessing skin lesions.

“If you don’t build it, you don’t know” what can go wrong, she said.

Dr. Leachman said other scientists who have worked on similar projects to build skin-analyzing apps have probably encountered the same difficulties, although they may not reveal these issues. “I think that a lot of people build these things and then they try to make it into something that it’s not,” she said.

In addition to the challenges with gathering images, dermatologists frequently need to rely on touch and other clues from in-person visits when diagnosing a suspicious lesion. “There’s something about seeing and feeling the skin in person that can’t be captured completely with an image,” Dr. Leachman said.
 

Public demand

Still, regulators must face the strong and immediate interest consumers have in using AI to check on moles and skin conditions, despite continuing questions about how well this approach might work.

In June, Google announced in a blog post that its Google Lens tool can help people research skin conditions.

“Just take a picture or upload a photo through Lens, and you’ll find visual matches to inform your search,” Google said in a blog post. “This feature also works if you’re not sure how to describe something else on your body, like a bump on your lip, a line on your nails or hair loss on your head. This feature is currently available in the U.S.”

Google also continues work on DermAssist, an app that’s intended to help people get personalized information about skin concerns using three photos. It is not currently publicly available, a Google spokesperson told this news organization.

Several skin-analyzing apps are already available in the Apple and Google Play stores. The British Association of Dermatologists last year issued a press release warning consumers that these apps may not be safe or effective and thus may put patients at risk for misdiagnosis.

“Unfortunately, AI-based apps which do not appear to meet regulatory requirements crop up more often than we would like,” the association said. “Additionally, the evidence to support the use of AI to diagnose skin conditions is weak which means that when it is used, it may not be safe or effective and it is possible that AI is putting patients at risk of misdiagnosis.”

Delicate and difficult balancing act

At this time, regulators, entrepreneurs, and the medical community face a delicate balancing act in considering how best to deploy AI in skin care, Dr. Ko said in an interview. (In addition to being one of the authors on the widely cited 2017 Nature paper mentioned above, Dr. Ko served until March as the initial chair of the American Academy of Dermatology’s Augmented Intelligence Committee.)

There are many solid reasons why there hasn’t been speedy progress to deploy AI in dermatology, as many envisioned a few years ago, Dr. Ko said.

Some of those reasons are specific to dermatology; this field doesn’t have a ready set of robust data from which to build AI-driven tools. In this aspect, dermatology is decades behind specialties like radiology, pathology, and ophthalmology, where clinicians have long been accumulating and storing images and other data in more standardized ways, Dr. Ko said.

“If you went to most dermatology practices and said, ‘Hey, let me learn from the data accumulated over the course of your 30-year practice to help us develop new tools,’” there may not be a whole lot there,” Dr. Ko said.

Beyond the start-up hurdles is the larger concern Dr. Ko shares with other dermatologists who work in this field, such as Dr. Daneshjou and Dr. Leachman. What would clinicians without much dermatology training and patients do with the readings from AI-driven tools and apps?

There would need to be significant research to show that such products actually help get people treated for skin diseases, including skin cancer.

Dr. Ko praised Google for being open about the stumbles with its efforts to use its AI tool for identifying diabetic retinopathy in a test in Thailand. Real-world hitches included poor Internet connections and poor image quality.

Developing reliable systems, processes, and workflows will be paramount for eventual widespread use of AI-driven tools, Dr. Ko said.

“It’s all those hidden things that are not sexy,” as are announcements about algorithms working about as well as clinicians in diagnosis, Dr. Ko said. “They don’t get the media attention, but they’re going to be make or break for AI, not just in our field but [for] AI in general.”

But he added that there also needs to be a recognition that AI-driven tools and products, even if somewhat imperfect, can help people get access to care.

In many cases, shortages of specialists prevent people from getting screened for treatable conditions such as skin cancer and retinopathy. The challenge is setting an appropriate standard to make sure that AI-driven products would help most patients in practice, without raising it so high that no such products emerge.

“There’s a risk of holding too high of a bar,” Dr. Ko said. “There is harm in not moving forward as well.”

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

An influential Nature paper predicted in 2017 that advances in artificial intelligence (AI) could unleash remarkable changes in dermatology, such as using phones to help detect skin cancer earlier.

Given that about 6.3 billion smartphones would soon be in use, this AI approach could provide a gateway for “low-cost universal access to vital diagnostic care,” wrote Justin M. Ko, MD, MBA, a dermatologist, and colleagues from Stanford (Calif.) University that included other dermatologists and engineers.

Dr. Ko and his coauthors described how they trained a computer system to identify both benign and cancerous skin lesions. They used an approach known as a convolutional neural network, often deployed for projects seeking to train computers to “see” through image analysis. They said that their test of this system found it to be on par with the performance of 21 board-certified dermatologists.

“This fast, scalable method is deployable on mobile devices and holds the potential for substantial clinical impact, including broadening the scope of primary care practice and augmenting clinical decision-making for dermatology specialists,” they wrote in their paper.

More than 6 years later, there are signs that companies are making progress toward moving skin checks using this technology into U.S. primary care settings – but only with devices that employ special tools.

It may prove tougher for companies to eventually secure the sign-off of the U.S. Food and Drug Administration for mobile apps intended to let consumers handle this task with smartphones.

Such tools would need to be proven highly accurate before release, because too many false positives mean that people would be needlessly exposed to biopsies, said Sancy A. Leachman, MD, PhD, director of the melanoma research program and chair of the department of dermatology at Oregon Health & Science University, Portland.

And false-negative readings would allow melanoma to advance and even be fatal, Dr. Leachman told this news organization.

Roxana Daneshjou, MD, PhD, a dermatologist at Stanford who has studied the promise and the pitfalls of AI in medicine, said that developers of a consumer skin-check app would need to know how people would react to their readings. That includes a good sense of how often they would appropriately seek medical care for a concerning reading. (She was not an author of the previously cited Nature paper but has published widely on AI.)

Christopher Smith

“The direct-to-consumer diagnostic space makes me nervous,” Dr. Daneshjou said in an interview. “In order to do it, you really need to have good studies in consumer populations prior to release. You need to show how effective it is with follow up.”
 

FDA shows interest – and reservations

As of July, the FDA had not yet given its okay for marketing of any consumer apps intended to help people detect signs of skin cancer, an agency spokesperson told this news organization.

To date, the agency has only cleared two AI-based products for this task, both meant to be used by dermatologists. And only one of these two products, Scibase’s Nevisense, remains in use in the United States. The other, MelaFind, has been discontinued. In 2017, Strata Skin Sciences said that the product did not win “a significant enough level of acceptance by dermatologists to justify the continued investment” in it. And the company said it notified the 90 owners of MelaFind devices in the United States that it would no longer support the device.

But another company, DermaSensor, said in a 2021 press release that it expects its AI-powered tool, also named DermaSensor, to be the “first ever FDA cleared or approved skin cancer detection device for primary care providers.”

The Miami-based firm said that the FDA had granted its product a “breakthrough” device designation. A breakthrough designation means that agency staff will offer extra help and guidance to companies in developing a product, because of its expected benefit for patients.

In a 2020 press release, 3Derm Systems, now owned by Digital Diagnostics, made a similar announcement about winning FDA breakthrough designation for an AI-powered tool intended to allow skin checks in primary care settings.

(The FDA generally does not comment on its reviews of experimental drugs and devices, but companies can do so. Several other companies have announced FDA breakthrough designations for AI-driven products intended to check for skin lesions, but these might be used in settings other than primary care.)

Both DermaSensor and Digital Diagnostics have chairs with notable track records for winning FDA approvals of other devices. DermaSensor’s Maurice Ferre, MD, also is the chairman of Insightec, which in 2016 won the first FDA approval for a device with a breakthrough designation device that uses ultrasound to treat tremors.

In 2018, the FDA allowed Digital Diagnostics, then called IDx, to introduce in the United States the first medical device using AI in primary care offices to check for signs of diabetic retinopathy. This product also had an FDA breakthrough designation. The executive chairman and founder of Digital Diagnostics is Michael Abramoff, MD, PhD, professor of engineering and ophthalmology at the University of Iowa, Iowa City. Dr. Abramoff and the team behind the AI tool for retinopathy, now called the LumineticsCore system, also scored a notable win with Medicare, which agreed to cover use of the product through a dedicated CPT code.
 

FDA draft guidance

The FDA has acknowledged the interest in broadening access to skin checks via AI.

This was a topic of discussion at a 2-day advisory committee meeting the FDA held last year. In April 2023, the FDA outlined some of its expectations for future regulation of skin-analyzing tools as part of a wide-ranging draft guidance document intended to aid companies in their efforts to develop products using a form of AI known as machine learning.

In the document, the FDA described how it might approach applications for “hypothetical” devices using this kind of AI, such as a special tool to help primary care clinicians identify lesions in need of further investigation. Such a product would use a specific camera for gathering data for its initial clearance, in the FDA’s hypothetical scenario.

The FDA staff offered technical suggestions about what the developer of this hypothetical device would have to do to extend its use to smartphones and tablets while keeping clinicians as the intended users.

Some of these expanded uses could fall within the bounds of the FDA’s initial clearance and thus not trigger a need for a new marketing submission, the agency said. But seeking to shift this hypothetical product to “patient-facing” use would require a new marketing submission to the FDA, the agency said.

In this scenario, a company would expect people to follow up with a dermatologist after receiving a report suggesting cancer. Thus, this kind of a change could expose patients to “many new, unconsidered risks,” the FDA said.
 

Reality check?

The state of current efforts to develop consumer apps for checking for skin cancer seems to be summarized well on the website for the MoleMapper. The app was developed by researchers at OHSU to help people track how their moles change over time.

“Mole Mapper is NOT designed to provide medical advice, professional diagnosis, opinion, or treatment. Currently, there is not enough data to develop an app that can diagnose melanoma, but if enough data is collected through Mole Mapper and shared with researchers, it may be possible in the future,” the app’s website says.

OHSU released MoleMapper as an iPhone app in 2015. The aim of this project was to help people track the moles on their skin while also fostering an experiment in “citizen science,” OHSU’s Dr. Leachman told this news organization.

OHSU researchers hoped that the digital images taken by members of the public on cell phones could one day be used to develop diagnostic algorithms for melanoma.

But around 2017, the MoleMapper team realized that they would not be able to create a diagnostic app at this time, Dr. Leachman explained. They could not collect enough data of adequate quality.

And by 2021, it was clear that they could not even develop a successful app to triage patients to assess who needs to be seen quickly. The amount of data required was, at this point, beyond what the team could collect, Dr. Leachman said in an interview.

That was a disappointment because the team had successfully completed the difficult task of creating a confidential pathway for collecting these images via both iPhones and smartphones run on Android.

“We thought if we built it, people would come, but that’s not what happened,” Dr. Leachman said. Many patients didn’t want their images used for research or would fail to follow up with details of biopsy reports. Sometimes images were not captured well enough to be of use.

“You need at least hundreds of thousands, if not millions, of data points that have been verified with pathologies, and nobody was giving us back that data. That was the reality,” Dr. Leachman said.

There were valuable lessons in that setback. The OHSU team now has a better grasp of the challenges of trying to build a data-collection system that could prove helpful in assessing skin lesions.

“If you don’t build it, you don’t know” what can go wrong, she said.

Dr. Leachman said other scientists who have worked on similar projects to build skin-analyzing apps have probably encountered the same difficulties, although they may not reveal these issues. “I think that a lot of people build these things and then they try to make it into something that it’s not,” she said.

In addition to the challenges with gathering images, dermatologists frequently need to rely on touch and other clues from in-person visits when diagnosing a suspicious lesion. “There’s something about seeing and feeling the skin in person that can’t be captured completely with an image,” Dr. Leachman said.
 

Public demand

Still, regulators must face the strong and immediate interest consumers have in using AI to check on moles and skin conditions, despite continuing questions about how well this approach might work.

In June, Google announced in a blog post that its Google Lens tool can help people research skin conditions.

“Just take a picture or upload a photo through Lens, and you’ll find visual matches to inform your search,” Google said in a blog post. “This feature also works if you’re not sure how to describe something else on your body, like a bump on your lip, a line on your nails or hair loss on your head. This feature is currently available in the U.S.”

Google also continues work on DermAssist, an app that’s intended to help people get personalized information about skin concerns using three photos. It is not currently publicly available, a Google spokesperson told this news organization.

Several skin-analyzing apps are already available in the Apple and Google Play stores. The British Association of Dermatologists last year issued a press release warning consumers that these apps may not be safe or effective and thus may put patients at risk for misdiagnosis.

“Unfortunately, AI-based apps which do not appear to meet regulatory requirements crop up more often than we would like,” the association said. “Additionally, the evidence to support the use of AI to diagnose skin conditions is weak which means that when it is used, it may not be safe or effective and it is possible that AI is putting patients at risk of misdiagnosis.”

Delicate and difficult balancing act

At this time, regulators, entrepreneurs, and the medical community face a delicate balancing act in considering how best to deploy AI in skin care, Dr. Ko said in an interview. (In addition to being one of the authors on the widely cited 2017 Nature paper mentioned above, Dr. Ko served until March as the initial chair of the American Academy of Dermatology’s Augmented Intelligence Committee.)

There are many solid reasons why there hasn’t been speedy progress to deploy AI in dermatology, as many envisioned a few years ago, Dr. Ko said.

Some of those reasons are specific to dermatology; this field doesn’t have a ready set of robust data from which to build AI-driven tools. In this aspect, dermatology is decades behind specialties like radiology, pathology, and ophthalmology, where clinicians have long been accumulating and storing images and other data in more standardized ways, Dr. Ko said.

“If you went to most dermatology practices and said, ‘Hey, let me learn from the data accumulated over the course of your 30-year practice to help us develop new tools,’” there may not be a whole lot there,” Dr. Ko said.

Beyond the start-up hurdles is the larger concern Dr. Ko shares with other dermatologists who work in this field, such as Dr. Daneshjou and Dr. Leachman. What would clinicians without much dermatology training and patients do with the readings from AI-driven tools and apps?

There would need to be significant research to show that such products actually help get people treated for skin diseases, including skin cancer.

Dr. Ko praised Google for being open about the stumbles with its efforts to use its AI tool for identifying diabetic retinopathy in a test in Thailand. Real-world hitches included poor Internet connections and poor image quality.

Developing reliable systems, processes, and workflows will be paramount for eventual widespread use of AI-driven tools, Dr. Ko said.

“It’s all those hidden things that are not sexy,” as are announcements about algorithms working about as well as clinicians in diagnosis, Dr. Ko said. “They don’t get the media attention, but they’re going to be make or break for AI, not just in our field but [for] AI in general.”

But he added that there also needs to be a recognition that AI-driven tools and products, even if somewhat imperfect, can help people get access to care.

In many cases, shortages of specialists prevent people from getting screened for treatable conditions such as skin cancer and retinopathy. The challenge is setting an appropriate standard to make sure that AI-driven products would help most patients in practice, without raising it so high that no such products emerge.

“There’s a risk of holding too high of a bar,” Dr. Ko said. “There is harm in not moving forward as well.”

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

An influential Nature paper predicted in 2017 that advances in artificial intelligence (AI) could unleash remarkable changes in dermatology, such as using phones to help detect skin cancer earlier.

Given that about 6.3 billion smartphones would soon be in use, this AI approach could provide a gateway for “low-cost universal access to vital diagnostic care,” wrote Justin M. Ko, MD, MBA, a dermatologist, and colleagues from Stanford (Calif.) University that included other dermatologists and engineers.

Dr. Ko and his coauthors described how they trained a computer system to identify both benign and cancerous skin lesions. They used an approach known as a convolutional neural network, often deployed for projects seeking to train computers to “see” through image analysis. They said that their test of this system found it to be on par with the performance of 21 board-certified dermatologists.

“This fast, scalable method is deployable on mobile devices and holds the potential for substantial clinical impact, including broadening the scope of primary care practice and augmenting clinical decision-making for dermatology specialists,” they wrote in their paper.

More than 6 years later, there are signs that companies are making progress toward moving skin checks using this technology into U.S. primary care settings – but only with devices that employ special tools.

It may prove tougher for companies to eventually secure the sign-off of the U.S. Food and Drug Administration for mobile apps intended to let consumers handle this task with smartphones.

Such tools would need to be proven highly accurate before release, because too many false positives mean that people would be needlessly exposed to biopsies, said Sancy A. Leachman, MD, PhD, director of the melanoma research program and chair of the department of dermatology at Oregon Health & Science University, Portland.

And false-negative readings would allow melanoma to advance and even be fatal, Dr. Leachman told this news organization.

Roxana Daneshjou, MD, PhD, a dermatologist at Stanford who has studied the promise and the pitfalls of AI in medicine, said that developers of a consumer skin-check app would need to know how people would react to their readings. That includes a good sense of how often they would appropriately seek medical care for a concerning reading. (She was not an author of the previously cited Nature paper but has published widely on AI.)

Christopher Smith

“The direct-to-consumer diagnostic space makes me nervous,” Dr. Daneshjou said in an interview. “In order to do it, you really need to have good studies in consumer populations prior to release. You need to show how effective it is with follow up.”
 

FDA shows interest – and reservations

As of July, the FDA had not yet given its okay for marketing of any consumer apps intended to help people detect signs of skin cancer, an agency spokesperson told this news organization.

To date, the agency has only cleared two AI-based products for this task, both meant to be used by dermatologists. And only one of these two products, Scibase’s Nevisense, remains in use in the United States. The other, MelaFind, has been discontinued. In 2017, Strata Skin Sciences said that the product did not win “a significant enough level of acceptance by dermatologists to justify the continued investment” in it. And the company said it notified the 90 owners of MelaFind devices in the United States that it would no longer support the device.

But another company, DermaSensor, said in a 2021 press release that it expects its AI-powered tool, also named DermaSensor, to be the “first ever FDA cleared or approved skin cancer detection device for primary care providers.”

The Miami-based firm said that the FDA had granted its product a “breakthrough” device designation. A breakthrough designation means that agency staff will offer extra help and guidance to companies in developing a product, because of its expected benefit for patients.

In a 2020 press release, 3Derm Systems, now owned by Digital Diagnostics, made a similar announcement about winning FDA breakthrough designation for an AI-powered tool intended to allow skin checks in primary care settings.

(The FDA generally does not comment on its reviews of experimental drugs and devices, but companies can do so. Several other companies have announced FDA breakthrough designations for AI-driven products intended to check for skin lesions, but these might be used in settings other than primary care.)

Both DermaSensor and Digital Diagnostics have chairs with notable track records for winning FDA approvals of other devices. DermaSensor’s Maurice Ferre, MD, also is the chairman of Insightec, which in 2016 won the first FDA approval for a device with a breakthrough designation device that uses ultrasound to treat tremors.

In 2018, the FDA allowed Digital Diagnostics, then called IDx, to introduce in the United States the first medical device using AI in primary care offices to check for signs of diabetic retinopathy. This product also had an FDA breakthrough designation. The executive chairman and founder of Digital Diagnostics is Michael Abramoff, MD, PhD, professor of engineering and ophthalmology at the University of Iowa, Iowa City. Dr. Abramoff and the team behind the AI tool for retinopathy, now called the LumineticsCore system, also scored a notable win with Medicare, which agreed to cover use of the product through a dedicated CPT code.
 

FDA draft guidance

The FDA has acknowledged the interest in broadening access to skin checks via AI.

This was a topic of discussion at a 2-day advisory committee meeting the FDA held last year. In April 2023, the FDA outlined some of its expectations for future regulation of skin-analyzing tools as part of a wide-ranging draft guidance document intended to aid companies in their efforts to develop products using a form of AI known as machine learning.

In the document, the FDA described how it might approach applications for “hypothetical” devices using this kind of AI, such as a special tool to help primary care clinicians identify lesions in need of further investigation. Such a product would use a specific camera for gathering data for its initial clearance, in the FDA’s hypothetical scenario.

The FDA staff offered technical suggestions about what the developer of this hypothetical device would have to do to extend its use to smartphones and tablets while keeping clinicians as the intended users.

Some of these expanded uses could fall within the bounds of the FDA’s initial clearance and thus not trigger a need for a new marketing submission, the agency said. But seeking to shift this hypothetical product to “patient-facing” use would require a new marketing submission to the FDA, the agency said.

In this scenario, a company would expect people to follow up with a dermatologist after receiving a report suggesting cancer. Thus, this kind of a change could expose patients to “many new, unconsidered risks,” the FDA said.
 

Reality check?

The state of current efforts to develop consumer apps for checking for skin cancer seems to be summarized well on the website for the MoleMapper. The app was developed by researchers at OHSU to help people track how their moles change over time.

“Mole Mapper is NOT designed to provide medical advice, professional diagnosis, opinion, or treatment. Currently, there is not enough data to develop an app that can diagnose melanoma, but if enough data is collected through Mole Mapper and shared with researchers, it may be possible in the future,” the app’s website says.

OHSU released MoleMapper as an iPhone app in 2015. The aim of this project was to help people track the moles on their skin while also fostering an experiment in “citizen science,” OHSU’s Dr. Leachman told this news organization.

OHSU researchers hoped that the digital images taken by members of the public on cell phones could one day be used to develop diagnostic algorithms for melanoma.

But around 2017, the MoleMapper team realized that they would not be able to create a diagnostic app at this time, Dr. Leachman explained. They could not collect enough data of adequate quality.

And by 2021, it was clear that they could not even develop a successful app to triage patients to assess who needs to be seen quickly. The amount of data required was, at this point, beyond what the team could collect, Dr. Leachman said in an interview.

That was a disappointment because the team had successfully completed the difficult task of creating a confidential pathway for collecting these images via both iPhones and smartphones run on Android.

“We thought if we built it, people would come, but that’s not what happened,” Dr. Leachman said. Many patients didn’t want their images used for research or would fail to follow up with details of biopsy reports. Sometimes images were not captured well enough to be of use.

“You need at least hundreds of thousands, if not millions, of data points that have been verified with pathologies, and nobody was giving us back that data. That was the reality,” Dr. Leachman said.

There were valuable lessons in that setback. The OHSU team now has a better grasp of the challenges of trying to build a data-collection system that could prove helpful in assessing skin lesions.

“If you don’t build it, you don’t know” what can go wrong, she said.

Dr. Leachman said other scientists who have worked on similar projects to build skin-analyzing apps have probably encountered the same difficulties, although they may not reveal these issues. “I think that a lot of people build these things and then they try to make it into something that it’s not,” she said.

In addition to the challenges with gathering images, dermatologists frequently need to rely on touch and other clues from in-person visits when diagnosing a suspicious lesion. “There’s something about seeing and feeling the skin in person that can’t be captured completely with an image,” Dr. Leachman said.
 

Public demand

Still, regulators must face the strong and immediate interest consumers have in using AI to check on moles and skin conditions, despite continuing questions about how well this approach might work.

In June, Google announced in a blog post that its Google Lens tool can help people research skin conditions.

“Just take a picture or upload a photo through Lens, and you’ll find visual matches to inform your search,” Google said in a blog post. “This feature also works if you’re not sure how to describe something else on your body, like a bump on your lip, a line on your nails or hair loss on your head. This feature is currently available in the U.S.”

Google also continues work on DermAssist, an app that’s intended to help people get personalized information about skin concerns using three photos. It is not currently publicly available, a Google spokesperson told this news organization.

Several skin-analyzing apps are already available in the Apple and Google Play stores. The British Association of Dermatologists last year issued a press release warning consumers that these apps may not be safe or effective and thus may put patients at risk for misdiagnosis.

“Unfortunately, AI-based apps which do not appear to meet regulatory requirements crop up more often than we would like,” the association said. “Additionally, the evidence to support the use of AI to diagnose skin conditions is weak which means that when it is used, it may not be safe or effective and it is possible that AI is putting patients at risk of misdiagnosis.”

Delicate and difficult balancing act

At this time, regulators, entrepreneurs, and the medical community face a delicate balancing act in considering how best to deploy AI in skin care, Dr. Ko said in an interview. (In addition to being one of the authors on the widely cited 2017 Nature paper mentioned above, Dr. Ko served until March as the initial chair of the American Academy of Dermatology’s Augmented Intelligence Committee.)

There are many solid reasons why there hasn’t been speedy progress to deploy AI in dermatology, as many envisioned a few years ago, Dr. Ko said.

Some of those reasons are specific to dermatology; this field doesn’t have a ready set of robust data from which to build AI-driven tools. In this aspect, dermatology is decades behind specialties like radiology, pathology, and ophthalmology, where clinicians have long been accumulating and storing images and other data in more standardized ways, Dr. Ko said.

“If you went to most dermatology practices and said, ‘Hey, let me learn from the data accumulated over the course of your 30-year practice to help us develop new tools,’” there may not be a whole lot there,” Dr. Ko said.

Beyond the start-up hurdles is the larger concern Dr. Ko shares with other dermatologists who work in this field, such as Dr. Daneshjou and Dr. Leachman. What would clinicians without much dermatology training and patients do with the readings from AI-driven tools and apps?

There would need to be significant research to show that such products actually help get people treated for skin diseases, including skin cancer.

Dr. Ko praised Google for being open about the stumbles with its efforts to use its AI tool for identifying diabetic retinopathy in a test in Thailand. Real-world hitches included poor Internet connections and poor image quality.

Developing reliable systems, processes, and workflows will be paramount for eventual widespread use of AI-driven tools, Dr. Ko said.

“It’s all those hidden things that are not sexy,” as are announcements about algorithms working about as well as clinicians in diagnosis, Dr. Ko said. “They don’t get the media attention, but they’re going to be make or break for AI, not just in our field but [for] AI in general.”

But he added that there also needs to be a recognition that AI-driven tools and products, even if somewhat imperfect, can help people get access to care.

In many cases, shortages of specialists prevent people from getting screened for treatable conditions such as skin cancer and retinopathy. The challenge is setting an appropriate standard to make sure that AI-driven products would help most patients in practice, without raising it so high that no such products emerge.

“There’s a risk of holding too high of a bar,” Dr. Ko said. “There is harm in not moving forward as well.”

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

TOPLINE:

Recurrence-free survival (RFS) is not a strong surrogate for overall survival in randomized trials of adjuvant immunotherapy for cancer.

METHODOLOGY:

• FDA approvals in the adjuvant setting for cancer immunotherapy are increasingly based on trials that use RFS as a surrogate endpoint for overall survival, largely because such a design allows for smaller, speedier trials.
• To test the validity of using RFS as a surrogate for overall survival in this setting, investigators conducted a meta-analysis of 15 phase 2 and 3 randomized controlled trials (RCTs) of adjuvant CTLA4 and anti–PD-1/PD-L1 blockers for melanoma, non–small cell lung cancer, renal cell cancer, and other tumors.
• The team used weighted regression at the arm and trial levels to assess the efficacy of RFS as a surrogate for overall survival.
• The strength of the association was quantified by weighted coefficients of determination (R²)12Dante MT Stdplz make sure all mentions of R’2’ are superscript, with a strong correlation considered to be R² of 0.7 or higher.
• If there were strong correlations at both the arm and trial levels, RFS would be considered a robust surrogate endpoint for overall survival; however, if one of the correlations at the arm or trial level was not strong, RFS would not be considered a surrogate endpoint for overall survival.

TAKEAWAY:

• At the arm level, moderate and strong associations were observed between 2-year RFS and 3-year overall survival (R², 0.58) and between 3-year RFS and 5-year overall survival (R², 0.72; 95% confidence interval, 0.38-.00).
• At the trial level, a moderate association was observed between effect of treatment on RFS and overall survival (R², 0.63).
• The findings were confirmed in several sensitivity analyses that were based on different trial phases, experimental arms, cancer types, and treatment strategies.

IN PRACTICE:

“Our meta-analysis failed to find a significantly strong association between RFS and OS in RCTs of adjuvant immunotherapy,” the authors concluded. “RFS should not be used as a surrogate endpoint for OS in this clinical context.” Instead, the finding indicates that overall survival is “the ideal primary endpoint” in this setting.

SOURCE:

The study, led by Yuanfang Li, PhD, of Sun Yat-sen University Cancer Center in Guangzhou, China, was published in the Journal of the National Cancer Institute.

LIMITATIONS:

• Correlations were calculated from a relatively limited number of RCTs that involved different types of cancer, and overall survival data were not fully mature in some of the trials.
• The analysis did not include patient-level data.

DISCLOSURES:

• The work was funded by the National Natural Science Foundation of China and others.
• The investigators had no disclosures.

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

TOPLINE:

Recurrence-free survival (RFS) is not a strong surrogate for overall survival in randomized trials of adjuvant immunotherapy for cancer.

METHODOLOGY:

• FDA approvals in the adjuvant setting for cancer immunotherapy are increasingly based on trials that use RFS as a surrogate endpoint for overall survival, largely because such a design allows for smaller, speedier trials.
• To test the validity of using RFS as a surrogate for overall survival in this setting, investigators conducted a meta-analysis of 15 phase 2 and 3 randomized controlled trials (RCTs) of adjuvant CTLA4 and anti–PD-1/PD-L1 blockers for melanoma, non–small cell lung cancer, renal cell cancer, and other tumors.
• The team used weighted regression at the arm and trial levels to assess the efficacy of RFS as a surrogate for overall survival.
• The strength of the association was quantified by weighted coefficients of determination (R²)12Dante MT Stdplz make sure all mentions of R’2’ are superscript, with a strong correlation considered to be R² of 0.7 or higher.
• If there were strong correlations at both the arm and trial levels, RFS would be considered a robust surrogate endpoint for overall survival; however, if one of the correlations at the arm or trial level was not strong, RFS would not be considered a surrogate endpoint for overall survival.

TAKEAWAY:

• At the arm level, moderate and strong associations were observed between 2-year RFS and 3-year overall survival (R², 0.58) and between 3-year RFS and 5-year overall survival (R², 0.72; 95% confidence interval, 0.38-.00).
• At the trial level, a moderate association was observed between effect of treatment on RFS and overall survival (R², 0.63).
• The findings were confirmed in several sensitivity analyses that were based on different trial phases, experimental arms, cancer types, and treatment strategies.

IN PRACTICE:

“Our meta-analysis failed to find a significantly strong association between RFS and OS in RCTs of adjuvant immunotherapy,” the authors concluded. “RFS should not be used as a surrogate endpoint for OS in this clinical context.” Instead, the finding indicates that overall survival is “the ideal primary endpoint” in this setting.

SOURCE:

The study, led by Yuanfang Li, PhD, of Sun Yat-sen University Cancer Center in Guangzhou, China, was published in the Journal of the National Cancer Institute.

LIMITATIONS:

• Correlations were calculated from a relatively limited number of RCTs that involved different types of cancer, and overall survival data were not fully mature in some of the trials.
• The analysis did not include patient-level data.

DISCLOSURES:

• The work was funded by the National Natural Science Foundation of China and others.
• The investigators had no disclosures.

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

TOPLINE:

Recurrence-free survival (RFS) is not a strong surrogate for overall survival in randomized trials of adjuvant immunotherapy for cancer.

METHODOLOGY:

• FDA approvals in the adjuvant setting for cancer immunotherapy are increasingly based on trials that use RFS as a surrogate endpoint for overall survival, largely because such a design allows for smaller, speedier trials.
• To test the validity of using RFS as a surrogate for overall survival in this setting, investigators conducted a meta-analysis of 15 phase 2 and 3 randomized controlled trials (RCTs) of adjuvant CTLA4 and anti–PD-1/PD-L1 blockers for melanoma, non–small cell lung cancer, renal cell cancer, and other tumors.
• The team used weighted regression at the arm and trial levels to assess the efficacy of RFS as a surrogate for overall survival.
• The strength of the association was quantified by weighted coefficients of determination (R²)12Dante MT Stdplz make sure all mentions of R’2’ are superscript, with a strong correlation considered to be R² of 0.7 or higher.
• If there were strong correlations at both the arm and trial levels, RFS would be considered a robust surrogate endpoint for overall survival; however, if one of the correlations at the arm or trial level was not strong, RFS would not be considered a surrogate endpoint for overall survival.

TAKEAWAY:

• At the arm level, moderate and strong associations were observed between 2-year RFS and 3-year overall survival (R², 0.58) and between 3-year RFS and 5-year overall survival (R², 0.72; 95% confidence interval, 0.38-.00).
• At the trial level, a moderate association was observed between effect of treatment on RFS and overall survival (R², 0.63).
• The findings were confirmed in several sensitivity analyses that were based on different trial phases, experimental arms, cancer types, and treatment strategies.

IN PRACTICE:

“Our meta-analysis failed to find a significantly strong association between RFS and OS in RCTs of adjuvant immunotherapy,” the authors concluded. “RFS should not be used as a surrogate endpoint for OS in this clinical context.” Instead, the finding indicates that overall survival is “the ideal primary endpoint” in this setting.

SOURCE:

The study, led by Yuanfang Li, PhD, of Sun Yat-sen University Cancer Center in Guangzhou, China, was published in the Journal of the National Cancer Institute.

LIMITATIONS:

• Correlations were calculated from a relatively limited number of RCTs that involved different types of cancer, and overall survival data were not fully mature in some of the trials.
• The analysis did not include patient-level data.

DISCLOSURES:

• The work was funded by the National Natural Science Foundation of China and others.
• The investigators had no disclosures.

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

Among U.S. high school students, males and non-Whites are at greatest risk for not using sunscreen, a cornerstone of skin cancer prevention, according to results from a systematic review.

“We know that skin cancer is one of the most common malignancies in the world, and sun protection methods such as sunscreen make it highly preventable,” first author Carly R. Stevens, a student at Tulane University, New Orleans, said in an interview. “This study demonstrates the adolescent populations that are most vulnerable to sun damage and how we can help mitigate their risk of developing skin cancer through education methods, such as Sun Protection Outreach Teaching by Students.”  

Ms. Stevens and coauthors presented the findings during a poster session at the annual meeting of the Society for Pediatric Dermatology.

To investigate predictors of sunscreen use among high school students, they searched PubMed, Embase, and Web of Science using the terms (“sunscreen” or “SPF” or “sun protection”) and (“high school” or “teen” or “teenager” or “adolescent”) and limited the analysis to English studies reporting data on sunscreen use in U.S. high school students up to November 2021.

A total of 20 studies were included in the final review. The study populations ranged in number from 208 to 24,645. Of 11 studies that examined gender, all showed increased sunscreen use in females compared with males. Of five studies that examined age, all showed increased sunscreen use in younger adolescents, compared with their older counterparts.

Of four studies that examined the role of ethnicity on sunscreen use, White students were more likely to use sunscreen, compared with their peers of other ethnicities. “This may be due to perceived sun sensitivity, as [these four studies] also showed increased sunscreen use in populations that believed were more susceptible to sun damage,” the researchers wrote in their abstract.

Wavebreakmedia Ltd/Thinkstock

In other findings, two studies that examined perceived self-efficacy concluded that higher levels of sunscreen use correlated with higher self-efficacy, while four studies concluded that high school students were more likely to use sunscreen if their parents encouraged them the wear it or if the parent used it themselves.

“With 40%-50% of ultraviolet damage being done before the age of 20, it’s crucial that we find ways to educate adolescents on the importance of sunscreen use and target those populations who were found to rarely use sunscreen in our study,” Ms. Stevens said.

In one outreach program, Sun Protection Outreach Teaching by Students (SPOTS), medical students visit middle and high schools to educate them about the importance of practicing sun protection. The program began as a collaboration between Saint Louis University and Washington University in St. Louis, but has expanded nationwide. Ms. Stevens described SPOTS as “a great way for medical students to present the information to middle and high school students in a way that is engaging and interactive.”

The researchers reported having no disclosures.

Among U.S. high school students, males and non-Whites are at greatest risk for not using sunscreen, a cornerstone of skin cancer prevention, according to results from a systematic review.

“We know that skin cancer is one of the most common malignancies in the world, and sun protection methods such as sunscreen make it highly preventable,” first author Carly R. Stevens, a student at Tulane University, New Orleans, said in an interview. “This study demonstrates the adolescent populations that are most vulnerable to sun damage and how we can help mitigate their risk of developing skin cancer through education methods, such as Sun Protection Outreach Teaching by Students.”  

Ms. Stevens and coauthors presented the findings during a poster session at the annual meeting of the Society for Pediatric Dermatology.

To investigate predictors of sunscreen use among high school students, they searched PubMed, Embase, and Web of Science using the terms (“sunscreen” or “SPF” or “sun protection”) and (“high school” or “teen” or “teenager” or “adolescent”) and limited the analysis to English studies reporting data on sunscreen use in U.S. high school students up to November 2021.

A total of 20 studies were included in the final review. The study populations ranged in number from 208 to 24,645. Of 11 studies that examined gender, all showed increased sunscreen use in females compared with males. Of five studies that examined age, all showed increased sunscreen use in younger adolescents, compared with their older counterparts.

Of four studies that examined the role of ethnicity on sunscreen use, White students were more likely to use sunscreen, compared with their peers of other ethnicities. “This may be due to perceived sun sensitivity, as [these four studies] also showed increased sunscreen use in populations that believed were more susceptible to sun damage,” the researchers wrote in their abstract.

Wavebreakmedia Ltd/Thinkstock

In other findings, two studies that examined perceived self-efficacy concluded that higher levels of sunscreen use correlated with higher self-efficacy, while four studies concluded that high school students were more likely to use sunscreen if their parents encouraged them the wear it or if the parent used it themselves.

“With 40%-50% of ultraviolet damage being done before the age of 20, it’s crucial that we find ways to educate adolescents on the importance of sunscreen use and target those populations who were found to rarely use sunscreen in our study,” Ms. Stevens said.

In one outreach program, Sun Protection Outreach Teaching by Students (SPOTS), medical students visit middle and high schools to educate them about the importance of practicing sun protection. The program began as a collaboration between Saint Louis University and Washington University in St. Louis, but has expanded nationwide. Ms. Stevens described SPOTS as “a great way for medical students to present the information to middle and high school students in a way that is engaging and interactive.”

The researchers reported having no disclosures.

Among U.S. high school students, males and non-Whites are at greatest risk for not using sunscreen, a cornerstone of skin cancer prevention, according to results from a systematic review.

“We know that skin cancer is one of the most common malignancies in the world, and sun protection methods such as sunscreen make it highly preventable,” first author Carly R. Stevens, a student at Tulane University, New Orleans, said in an interview. “This study demonstrates the adolescent populations that are most vulnerable to sun damage and how we can help mitigate their risk of developing skin cancer through education methods, such as Sun Protection Outreach Teaching by Students.”  

Ms. Stevens and coauthors presented the findings during a poster session at the annual meeting of the Society for Pediatric Dermatology.

To investigate predictors of sunscreen use among high school students, they searched PubMed, Embase, and Web of Science using the terms (“sunscreen” or “SPF” or “sun protection”) and (“high school” or “teen” or “teenager” or “adolescent”) and limited the analysis to English studies reporting data on sunscreen use in U.S. high school students up to November 2021.

A total of 20 studies were included in the final review. The study populations ranged in number from 208 to 24,645. Of 11 studies that examined gender, all showed increased sunscreen use in females compared with males. Of five studies that examined age, all showed increased sunscreen use in younger adolescents, compared with their older counterparts.

Of four studies that examined the role of ethnicity on sunscreen use, White students were more likely to use sunscreen, compared with their peers of other ethnicities. “This may be due to perceived sun sensitivity, as [these four studies] also showed increased sunscreen use in populations that believed were more susceptible to sun damage,” the researchers wrote in their abstract.

Wavebreakmedia Ltd/Thinkstock

In other findings, two studies that examined perceived self-efficacy concluded that higher levels of sunscreen use correlated with higher self-efficacy, while four studies concluded that high school students were more likely to use sunscreen if their parents encouraged them the wear it or if the parent used it themselves.

“With 40%-50% of ultraviolet damage being done before the age of 20, it’s crucial that we find ways to educate adolescents on the importance of sunscreen use and target those populations who were found to rarely use sunscreen in our study,” Ms. Stevens said.

In one outreach program, Sun Protection Outreach Teaching by Students (SPOTS), medical students visit middle and high schools to educate them about the importance of practicing sun protection. The program began as a collaboration between Saint Louis University and Washington University in St. Louis, but has expanded nationwide. Ms. Stevens described SPOTS as “a great way for medical students to present the information to middle and high school students in a way that is engaging and interactive.”

The researchers reported having no disclosures.