Effectiveness of an Artificial Intelligent Tutoring System in Simulation Training

Design: A three-arm partially blinded randomized controlled trial of VOA training versus remote-based expert instruction versus control. Setting: Neurosurgical Simulation and Artificial Intelligence Learning Centre, Montreal Neurological Institute. Participants: Eligible first- and second-year medical students from across the province of Quebec. Task: Complete removal of a simulated tumour - distinguishable by colour and haptic properties - with minimal bleeding and damage to surrounding healthy brain using two surgical instruments (Cavitron Ultrasonic Aspirator and Bipolar pincers) of the NeuroVR (CAE Healthcare) surgical simulator. Intervention: A single 75-minute training session, including six virtual subpial tumour resection attempts (five simple practice scenarios and one complex realistic scenario) with assessment and feedback from either: 1. the VOA intelligent tutoring system (Group 2) or 2. a remote-based expert instructor (Group 3) Both compared to: 3. control group (Group 1) that receives no assessment or performance feedback. To our knowledge this will be the first study to compare the effectiveness of an AI-powered intelligent tutoring system to expert instruction in the context of medical and surgical virtual reality simulation and assess the emotional response to such instruction. This study aims to begin to identify successful approaches to use this innovative technology in the medical educational curriculum and improve patient outcomes by augmenting safety, efficiency and competency of surgeons and other healthcare providers.