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

Area of Science:

• Dermatology and Surgical Oncology
• Medical Artificial Intelligence
• Computational Pathology

Background:

• Artificial intelligence (AI) has demonstrated potential in dermatology, yet its specific application in Mohs micrographic surgery (MMS) lacks systematic review.
• Nonmelanoma skin cancers (NMSC) represent a significant clinical challenge where advanced surgical techniques are paramount.

Approach:

• A comprehensive systematic review and meta-analysis was performed adhering to PRISMA guidelines.
• Literature search encompassed major databases (PubMed/MEDLINE, Embase, Cochrane) using keywords for AI and Mohs surgery in NMSC treatment.
• A registered protocol in PROSPERO ensured methodological rigor.

Key Points:

• AI demonstrates potential as a predictive tool for accurate NMSC identification in tissue sections during MMS.
• High Area Under the Curve (AUC) and concordance values were observed for AI applications in margin control, surgical recommendations, and complexity prediction.
• AI applications span various aspects of MMS, including similarity metrics and staging.

Conclusions:

• AI holds considerable promise for improving the accuracy and efficiency of Mohs surgery for NMSC.
• Further research and integration of AI tools could significantly advance NMSC treatment outcomes.