A recent study found a novel mobile health application may be a useful clinical tool for diagnosing skin diseases in patients with skin of color.
In the large-scale study, the researchers assessed the efficacy of the app to diagnose 40 common skin diseases in a clinical setting compared with dermatologists’ diagnoses. The app was generative and validated on 5014 patients who attended rural and urban outpatient dermatology departments in India.
The researchers found the machine learning model demonstrated an overall top-1 accuracy of 76.93 ± 0.88% and mean area‐under‐curve of 0.95 ± 0.02 on a set of clinical images in an in silico validation study. In the clinical study, they found the app achieved an overall top‐1 accuracy of 75.07% (95% CI, 73.75‐76.36), top‐3 accuracy of 89.62% (95% CI, 88.67‐90.52), and mean area‐under‐curve of 0.90 ± 0.07.
“This study underscores the utility of artificial intelligence‐driven smartphone applications as a point‐of‐care, clinical decision support tool for dermatological diagnosis for a wide spectrum of skin diseases in patients of the skin of color,” the researchers concluded.
Pangti R, Mathur J, Chouhan V, et al. A machine learning‐based, decision support, mobile phone application for diagnosis of common dermatological diseases. J Eur Acad Dermatol Venereol. Published online September 29, 2020. doi:10.1111/jdv.16967