Melanoma Coverage from Every Angle

Can Second Opinions From Pathologists Improve Melanoma Diagnoses?

By: Cordi Craig
Posted: Friday, November 8, 2019

Although diagnosing melanoma can be challenging, a new diagnostic study suggests that receiving a second opinion from certified dermatopathologists can help improve the overall accuracy and reliability of diagnosing melanocytic lesions. However, discordance among pathologists remained high, and second opinions did not eliminate or reduce misclassification of these lesions. The report of these findings was published in JAMA Network Open.

“Second opinions in clinical medicine can increase accuracy, which is a win-win for patients and providers—better diagnoses lead to better outcomes and efficient use of our health-care expenditures,” Joann G. Elmore, MD, MPH, of the University of California, Los Angeles (UCLA), stated in a UCLA press release.

Using 240 skin biopsy lesion samples from the Melanoma Pathology Study, the team evaluated the impact of obtaining second opinions during diagnosis. Among the 187 pathologists from the United States, 113 were general pathologists and 74 were dermatopathologists. 

The misclassification rate was highest (52.8%) when second opinions were not requested and the initial reviewers were general pathologists who lacked subspecialty training. The average misclassification rate was lowest (36.7%) when the first, second, and third reviewers had specialized training and there were second opinions for all lesions. The study showed that some second-opinion strategies significantly improved misclassification rates according to the study, although none of the strategies eliminated diagnostic misclassification altogether. The most difficult melanocytic lesions to diagnose with the highest misclassification rates included those in the middle of the diagnostic spectrum, including moderately or severely dysplastic nevus, Spitz nevus, melanoma in situ, and pathologic stage [p]T1a invasive melanoma.

Dr. Elmore is now studying the potential impact of computer machine learning as a tool to improve diagnostic accuracy. She is partnering with computer scientists who specialize in computer visualization of complex image information, as well as leading pathologists around the globe to develop an artificial intelligence–based diagnostic system.

Disclosure: For full disclosures of the study authors, visit

By continuing to browse this site you permit us and our partners to place identification cookies on your browser and agree to our use of cookies to identify you for marketing. Read our Privacy Policy to learn more.