This article is more than 5 years old. Information may no longer be current.
Smartphone apps varied in assessing melanomas
Click Here to Manage Email Alerts
Smartphone applications varied greatly in accurately assessing melanoma risk, with the majority incorrectly classifying 30% of melanomas as benign and possibly delaying clinical diagnoses and potentially lifesaving treatments, according to study results.
In a case-control diagnostic accuracy study, researchers at the University of Pittsburgh evaluated digital clinical images of pigmented cutaneous lesions, including 60 melanoma (44 invasive and 16 in situ) and 128 benign lesions. A board-certified dermatopathologist conducted histologic diagnoses of images obtained before biopsy from patients who underwent lesion removal. Researchers searched for smartphone applications that claimed or suggested an ability to assist nonclinicians in determining whether lesions might be malignant. Four smartphone applications were tested for sensitivity, specificity and positive and negative predictive values as the main outcome measures.
Click below to watch related video
Photographs considered evaluable ranged from 84.6% to 98.4% by the test applications; only those images were used to calculate overall sensitivity and specificity. The four applications had sensitivity ranging from 6.8% to 98.1% and specificity from 30.4% to 93.7%. Positive predictive values ranged from 33.3% to 42.1% and negative predictive values, 65.4% to 97%. An application that sent an image directly to a board-certified dermatologist had the highest sensitivity, while applications that used automated algorithms for photographic analysis rendered the lowest.
“Three of the four applications we evaluated do not involve a physician at any point in the evaluation,” the researchers reported, saying that could delay accurate diagnoses and possibly lifesaving therapies. “Even the best performing among these three applications classified 18 of 60 melanomas (30%) as benign.”
“Smartphone usage is rapidly increasing, and the applications available to consumers have moved beyond communication and entertainment to … [include] health care,” researcher Laura K. Ferris, MD, PhD, assistant professor in the department of dermatology at the University of Pittsburgh School of Medicine, said in a press release. “These tools may help patients be more mindful about their health care … but it’s important that users don’t allow their ‘apps’ to take the place of medical advice and physician diagnosis.”
Disclosure: Dr. Ferris reported having served as an investigator and consultant for MELA Sciences.
Perspective
Back to Top
Wen-Jen Hwu, MD, PhD
This is an interesting pilot study designed to measure the sensitivity, specificity and predictive values of four different smartphone applications in melanoma detection. The sensitivity of the applications ranged from 6.8% to 98.1%. The highest sensitivity for melanoma was noted when a dermatologist was involved.
This study raises concerns about the performance and reliability of these smartphone apps. The take home message is that these applications have the potential to harm the users not only by misdiagnosing melanoma but also by substituting for standard medical care. As outlined in this article, this is even more important in underserved areas or uninsured population. The major concern is that the widespread use of non-FDA approved devices/applications for the detection and diagnosis of skin lesions may result in an increased number of advanced melanoma cases in the future.
It is critical to emphasize that these technologies should not substitute for standard medical care in all consumers, including those actively using these apps to self-diagnose potentially lethal skin lesions.
Click Here to Manage Email Alerts