Browser-Based Video Supports Scalable Computer Vision Analysis for Open Surgical Skill Assessment

Purpose: Objective assessment of open surgical skills remains limited by expert availability. Machine learning (ML)-based hand keypoint detection offers potential for automated, on-demand assessment, but performance in accessible browser-based recording environments (laptop-webcam video recorded in a web browser) is unknown. We hypothesized that browser-based recordings would achieve acceptable keypoint localization (percentage of correct keypoints [PCK] >70%). Methods: Retrospective technical validation of prospectively collected video from 14 PGY-1 interns at one academic center (July to Aug

This content is for informational purposes only and is not medical advice. It is not intended to diagnose, treat, cure, or prevent any disease. Consult a healthcare professional before starting any supplement, treatment, or program: especially if you are pregnant, nursing, taking medication, or managing a health condition.