Bogar PZ, Virag M, Bene M, Hardi P, Matuz A, Schlegl AT, Toth L, Molnar F, Nagy B, Rendeki S, Berner-Juhos K, Ferencz A, Fischer K, Maroti P. Validation of a novel, low-fidelity virtual reality simulator and an artificial intelligence assessment approach for peg transfer laparoscopic training. Sci Rep. 2024 Jul 19;14(1):16702. doi: 10.1038/s41598-024-67435-6

PMID: 39030307

Abstract

Simulators are widely used in medical education, but objective and automatic assessment is not feasible with low-fidelity simulators, which can be solved with artificial intelligence (AI) and virtual reality (VR) solutions. The effectiveness of a custom-made VR simulator and an AI-based evaluator of a laparoscopic peg transfer exercise was investigated. Sixty medical students were involved in a single-blinded randomised controlled study to compare the VR simulator with the traditional box trainer. A total of 240 peg transfer exercises from the Fundamentals of Laparoscopic Surgery programme were analysed. The experts and AI-based software used the same criteria for evaluation. The algorithm detected pitfalls and measured exercise duration. Skill improvement showed no significant difference between the VR and control groups. The AI-based evaluator exhibited 95% agreement with the manual assessment. The average difference between the exercise durations measured by the two evaluation methods was 2.61 s. The duration of the algorithmic assessment was 59.47 s faster than the manual assessment. The VR simulator was an effective alternative practice compared with the training box simulator. The AI-based evaluation produced similar results compared with the manual assessment, and it could significantly reduce the evaluation time. AI and VR could improve the effectiveness of basic laparoscopic training.