AI coach helps medical students learn suturing ^{CEFR B1}

A team at Johns Hopkins developed an explainable AI system that coaches medical students as they practice basic surgical tasks such as suturing. The system was trained on videos of expert surgeons and on tracked hand movements recorded while surgeons closed incisions. It can both rate a student’s technique and explain how to improve.

The AI gives immediate, personalized feedback by sending students a text message after practice. The messages compare a student’s movements to expert movements and point to specific changes to refine technique. The researchers say this approach could replace the labor-intensive process in which a busy attending surgeon watches practice sessions, scores students and then gives detailed feedback.

To evaluate the idea, the team ran a randomized study with 12 medical students who had some suturing experience. All practiced closing an incision with stitches. One group received immediate AI feedback and the other group learned from recorded videos and then practiced again. Students who already had a solid foundation learned faster with AI, while beginners struggled and showed less benefit. The researchers plan to refine the model and build a version for home use with a suturing kit and a smartphone. Additional coauthors are from Johns Hopkins and the University of Arkansas, and the work had grant support.