Artificial Intelligence for Mohs and Dermatologic Surgery: A Systematic Review and Meta-Analysis

Abstract

BACKGROUND Over the past decade, several studies have shown that potential of artificial intelligence (AI) in dermatology. However, there has yet to be a systematic review evaluating the usage of AI specifically within the field of Mohs micrographic surgery (MMS). OBJECTIVE In this review, we aimed to comprehensively evaluate the current state, efficacy, and future implications of AI when applied to MMS for the treatment of nonmelanoma skin cancers (NMSC). MATERIALS AND METHODS A systematic review and meta-analysis was conducted following PRISMA guidelines across several databases, including PubMed/MEDLINE, Embase, and Cochrane libraries. A predefined protocol was registered in PROSPERO, with literature search involving specific keywords related to AI and Mohs surgery for NMSC. RESULTS From 23 studies evaluated, our results find that AI shows promise as a prediction tool for precisely identifying NMSC in tissue sections during MMS. Furthermore, high AUC and concordance values were also found across the various usages of AI in MMS, including margin control, surgical recommendations, similarity metrics, and in the prediction of stage and construction complexity. CONCLUSION The findings of this review suggest promising potential for AI to enhance the accuracy and efficiency of Mohs surgery, particularly for NMSC.