Journal Article

A deep learning system for differential diagnosis of skin diseases

Kanada, Kimberly, Natarajan, Vivek, Dunn, R. Carter, Gabriele, Sara, Huang, Susan J., Peng, Lily H., Eng, Clara, Liu, Yun, Singh, Nalini, Corrado, Greg S., Way, David H., Bui, Peggy, Liu, Yuan, Hofmann-Wellenhof, Rainer, Lee, Kang, Gallegos, Jessica, Gupta, Vishakha, Ai, Dennis, Webster, Dale R., de Oliveira Marinho, Guilherme, Jain, Ayush, Coz, David

2020

Overview

Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. We present a deep learning system (DLS) to provide a differential diagnosis of skin conditions using 16,114 de-identified cases (photographs and clinical data) from a teledermatology practice serving 17 sites. The DLS distinguishes between 26 common skin conditions, representing 80% of cases seen in primary care, while also providing a secondary prediction covering 419 skin conditions. On 963 validation cases, where a rotating panel of three board-certified dermatologists defined the reference standard, the DLS was non-inferior to six other dermatologists and superior to six primary care physicians (PCPs) and six nurse practitioners (NPs) (top-1 accuracy: 0.66 DLS, 0.63 dermatologists, 0.44 PCPs and 0.40 NPs). These results highlight the potential of the DLS to assist general practitioners in diagnosing skin conditions. A deep learning system able to identify the most common skin conditions may help clinicians in making more accurate diagnoses in routine clinical practice

• Publisher: Nature Publishing Group US,Nature Publishing Group
• Subject: 692/1807/1812 / 692/700/1421 / Acne Vulgaris - diagnosis / Adult / Alaska Natives / Artificial intelligence / Asian / Biomedical and Life Sciences / Biomedicine / Black or African American / Cancer Research / Carcinoma, Basal Cell - diagnosis / Carcinoma, Squamous Cell - diagnosis / Deep Learning / Dermatitis, Seborrheic - diagnosis / Dermatologists / Dermatology / Diagnosis / Diagnosis, Differential / Diagnostic systems / Differential diagnosis / Eczema - diagnosis / Female / Folliculitis - diagnosis / Health aspects / Health care / Hispanic or Latino / Humans / Indians, North American / Infectious Diseases / Keratosis, Seborrheic - diagnosis / Machine learning / Male / Medical personnel / Melanoma - diagnosis / Metabolic Diseases / Methods / Middle Aged / Molecular Medicine / Native Hawaiian or Other Pacific Islander / Neurosciences / Nurse Practitioners / Photography / Physicians / Physicians, Primary Care / Primary care / Psoriasis - diagnosis / Skin diseases / Skin Diseases - diagnosis / Skin Neoplasms - diagnosis / Technology application / Telemedicine / Warts - diagnosis / White People