Automatic surgical skill assessment using AI

Editor's Note

This Japanese study finds that an automatic surgical skill assessment with artificial intelligence (AI) is more objective than a manual video review-based skill assessment, and it can reduce the time consuming and labor intensive human burden of manual review..

A total of 120 intraoperative videos of laparoscopic colorectal surgery by expert surgeons were used to construct and validate a deep learning model able to recognize a standardized surgical field and output its similarity to standardized surgical field development as an AI confidence score that was strongly correlated with Endoscopic Surgica Skill Qualification System scores.

The model could automatically screen for the low-score group with 93.3% specificity and 82.2% sensitivity and for the high-score group with 93.3% specificity and 86.7% sensitivity.

The results suggest that an automatic surgical skill assessment with surgical field recognition is feasible, and that the methods of this study can be applied to other types of endoscopic procedures, the researches say.