Artificial Intelligence Distinguishes Surgical Training Levels in a Virtual Reality Spinal Task

EN BREF ...

« With the shift toward competency-based curricula, surgical educational paradigms are evolving to include new methods of assessment and training. Whereas current assessments rely on subjective methods, new technologies offer the potential for more objective approaches to surgical skill evaluation1. Simulation has become important in surgical education, with many programs implementing courses involving animal models, cadavers, benchtop models, and virtual reality sim- ulators2. Virtual reality simulators provide opportunities for repeat practice in risk-free environments and can quantify multiple aspects of psychomotor performance during surgi- cal procedures3. The large amount of data collected from an individual’s technical performance during a simulated task can be distilled into specific metrics. Metrics can be considered standards of reference to quantitate performance, efficiency, and progress4,5. Individual metrics often are incapable of effectively assessing surgical expertise since many procedures involve mul- tiple complex psychomotor skills. The requirement of efficiently combining multiple metrics has resulted in the need to assess systems that are capable of analyzing extensive amounts of infor- mation from multivariate data sets. » En bref issu de l’étude.