In a new study, researchers at McGill University found that medical students trained with AI-augmented human instruction showed superior performance in neurosurgery. This innovative approach could revolutionize medical training across various high-stake fields.
Artificial intelligence is significantly enhancing training and education in diverse fields, including neurosurgery. A new study from The Neuro (Montreal Neurological Institute-Hospital) at McGill University has demonstrated that combining AI tutoring with human instruction yields the best results in neurosurgical training.
Researchers at The Neuro’s Neurosurgical Simulation and Artificial Intelligence Learning Centre have been exploring how AI and virtual reality (VR) can transform the training of brain surgeons. Utilizing VR simulations to mimic brain surgeries, AI meticulously monitors students’ performance and provides continuous verbal feedback aimed at performance improvement and error prevention.
Previous research demonstrated that an AI-powered intelligent tutoring system at the Centre outperformed human experts. However, these instructors were not given access to trainee AI performance data.
In their latest study, the researchers enlisted 87 medical students from four Quebec medical schools, dividing them into three groups: one receiving AI-only feedback, one with expert human feedback, and one with expert feedback informed by real-time AI performance data. The study meticulously recorded each group’s performance, focusing on both the rapidity and accuracy of their skill improvements.
The findings, published in the journal JAMA Surgery, revealed that the group receiving AI-augmented, personalized feedback from human instructors showed superior surgical performance and skill transfer compared to the other two groups. This group also excelled in managing risks related to bleeding and tissue injury — key indicators of surgical expertise.
“Our findings underscore the importance of human input in AI-driven surgical education,” lead author Bianca Giglio, a former graduate student at McGill, said in a news release. “When expert instructors used AI performance data to deliver tailored, real-time feedback, trainees learned faster and transferred their skills more effectively.”
Though the study concentrated on neurosurgical training, these results have broader implications. Similar combined AI and human instruction techniques could be applied to other fields requiring the mastery of complex skills in high-pressure environments.
“AI is not replacing educators — it’s empowering them,” added senior author Rolando Del Maestro, a neurosurgeon and current director of the Centre. “By merging AI’s analytical power with the critical guidance of experienced instructors, we are moving closer to creating the ‘Intelligent Operating Room’ of the future, capable of assessing and training learners while minimizing errors during human surgical procedures.”
Source: McGill University