Clinical utility of a digital dermoscopy image-based artificial intelligence device in the diagnosis and management of skin cancer by dermatology health care providers, primary care providers, and nondermatology specialized physicians

Background: Patients with skin lesions suspicious of skin cancer or atypical nevi frequently present to dermatology health care providers (DHPs), primary care providers (PCPs), and nondermatology specialized physicians (NDSPs) who have variable training in the triage and diagnosis of skin cancers and atypical melanocytic nevi. Objective: To evaluate the clinical utility of a digital dermoscopy image-based artificial intelligence algorithm (DDI-AI device) on the diagnosis and management of skin cancers by DHPs, PCPs, and NDSPs. Study Design: Forty-three United States licensed DHPs, PCPs, and NDSPs evaluated 50 clinical images and 50 digital dermoscopy images (DDIs) of the same skin lesions (25 malignant and 25 benign), first without and then with knowledge of the DDI-AI device output. Participants selected whether they thought the lesion was likely benign or malignant. Results: The overall management sensitivity for participants was 94.2% with the DDI-AI device, 84.1% with DDI, and 72.9% with clinical images; overall diagnostic sensitivity for participants was 87.0%, 79.6%, and 64.7%, respectively. Diagnostic specificity increased over baseline to 75.0% with the DDI-AI device, while no significant difference was observed in management specificity. DHPs had a statistically significantly higher baseline clinical (68.5% sensitivity vs. 59.6%) and dermoscopy (84.3% sensitivity vs. 73.3%) performance than PCPs and NDSPs. DHPs also achieved the highest diagnostic performance (87.7% sensitivity vs. 86.2%) when using the DDI-AI device. Conclusions: The use of the DDI-AI device may quickly, safely, and effectively improve skin cancer management and diagnosis when used by DHPs, PCPs, and NDSPs, independent of variable training and clinical experience.