1 Applied Perception Lab, Department of Computer Science and Software Engineering, Concordia University, Montreal, QC, Canada.
2 University of Maryland Medical Center, Baltimore, MD, United States.
3 Surgical Artificial Intelligence Research Academy, University Health Network, Toronto, ON, Canada.
4 Department of Surgery, University of Toronto, Toronto, ON, Canada.
5 DATA Team, University Health Network, Toronto, ON, Canada.

Background: Major bile duct injuries during laparoscopic cholecystectomy (LC), often stemming from errors in surgical judgment and visual misperception of critical anatomy, significantly impact morbidity, mortality, disability, and health care costs.

Objective: To enhance safe LC learning, we developed an educational mobile game, LapBot Safe Chole, which uses an artificial intelligence (AI) model to provide real-time coaching and feedback, improving intraoperative decision-making.

Methods: LapBot Safe Chole offers a free, accessible simulated learning experience with real-time AI feedback. Players engage with intraoperative LC scenarios (short video clips) and identify ideal dissection zones. After the response, users receive an accuracy score from a validated AI algorithm. The game consists of 5 levels of increasing difficulty based on the Parkland grading scale for cholecystitis.

Results: Beta testing (n=29) showed score improvements with each round, with attendings and senior trainees achieving top scores faster than junior residents. Learning curves and progression distinguished candidates, with a significant association between user level and scores (P=.003). Players found LapBot enjoyable and educational.

Conclusions: LapBot Safe Chole effectively integrates safe LC principles into a fun, accessible, and educational game using AI-generated feedback. Initial beta testing supports the validity of the assessment scores and suggests high adoption and engagement potential among surgical trainees.