Smartphone flop: Melanoma assessment apps may mislead patients

Twitter icon
Facebook icon
LinkedIn icon
e-mail icon
Google icon
 - smartphone

The diagnostic performance of smartphone applications designed to assess melanoma risk is generally poor and highly variable, according to a study published online Jan. 16 in JAMA Dermatology.

Several smartphone applications designed to analyze images of skin lesions and assist patients in determining whether a skin lesion is potentially a melanoma or otherwise concerning are marketed as educational tools. However, despite disclaimers specifying educational rather than diagnostic use, these apps might harm patients who mistakenly believe the evaluation serves as a substitute for medical advice, according to Joel A. Wolf, BA, from the University of Pittsburgh, and colleagues.

The researchers designed a study to measure the performance of smartphone apps that evaluate photographs of skin lesions and provide feedback to individuals. They focused on four apps and used them to evaluate digital clinical images of 188 lesions (60 melanoma and 128 benign control lesions) with a histopathologic diagnosis rendered by a board-certified dermatopathologist.

Wolf and colleagues selected sensitivity to melanoma categorization as the primary endpoint, and also measured specificity, positive predictive value and negative predictive value.

Sensitivity of the four apps ranged from 6.8 percent to 98.1 percent; specificity from 30.4 percent to 93.7 percent; positive predictive value from 33.3 percent to 42.1 percent and negative predictive value from 65.4 percent to 97 percent.

An app that sends the photography to a dermatologist for analysis provided the highest sensitivity, the researchers found. The remaining three apps relied on algorithms or automated analysis as the basis for evaluation.

Wolf and colleagues noted that the FDA announced plans to regulate smartphone apps paired with regulated medical devices, such as imaging systems, and some standalone apps in 2011 and 2012. However, the process and relevant apps and exemptions have not yet been identified.

They emphasized the potential for patient harm with such technologies, and wrote, “Physicians must be aware of these applications because the use of medical applications seems to be increasing over time; whether such applications may be subject to regulatory oversight, whether oversight is appropriate, and when oversight might be applied remain unclear.”