Computer-Based Tutoring Outperforms Training by Remote Instructors for Brain Tumor Surgery

A new study, published in JAMA Network Open, found that in a remote learning environment, an artificial-intelligence (AI) tutoring system outperformed remote training by expert human instructors. Medical students (n=70) received instruction on brain tumor resection via a neurosurgical simulator and received no feedback, human expert instructor feedback, or feedback from a virtual operative assistant (VOA). Those who had VOA feedback learned surgical skills 2.6 times faster and achieved 36% better performance compared with those who received instruction and feedback from remote human instructors. Researchers expected students instructed by VOA to experience greater stress and negative emotion, but they found no significant difference between the 2 groups.

“Artificially intelligent tutors like the VOA may become a valuable tool in the training of the next generation of neurosurgeons,” said Rolando Del Maestro, MD, PhD, McGill University. “The VOA significantly improved expertise while fostering an excellent learning environment. Ongoing studies are assessing how in-person instructors and AI-powered intelligent tutors can most effectively be used together to improve the mastery of neurosurgical skills.”
 
An AI-powered VOA used a machine learning algorithm to teach safe and efficient surgical technique and provided personalized feedback, while a deep learning Intelligent Continuous Expertise Monitoring System (ICEMS) and a panel of experts assessed student performance. In the other group, remote human instructors watched a live feed of the surgical simulations and provided feedback based on the students’ performance.