Under the leadership of Suvranu De, researchers at the FAMU-FSU College of Engineering in Florida, US, have developed an AI tool designed to provide real-time feedback to surgeons in training.
The tool, rooted in cutting-edge deep learning models, was detailed in a recent publication in JAMA Surgery.
VBA-Net is a video-based assessment network that can evaluate a surgeon’s technique by analysing full-length videos of surgical procedures.
By distinguishing between expert and novice performance, VBA-Net offers both final scores and ongoing feedback, automating the traditionally subjective and time-consuming task of surgical skill assessment.
Suvranu De explained: ‘The more training and feedback surgeons-in-training receive, the more their skills will improve. Our system is a major step towards automating the evaluation of surgical skills, which is crucial for fostering skill development. This tool can offer valuable support to evaluators and has the potential to ensure greater consistency in assessments. Our objective is to streamline the evaluation process by guiding trainees in their focus on the most critical facets of a surgical procedure.’
VBA-Net utilises deep neural networks (DNNs) to provide personalised, formative assessments to aspiring surgeons.
This AI-driven approach streamlines the evaluation process and aims to improve its consistency.
The technology is supported by explainable artificial intelligence (XAI), which allows users to understand the logic behind the AI’s evaluations, thereby increasing trust in the system.
It aligns with the American Board of Surgery’s initiative to integrate video-based assessments into surgical training programmes.
De’s team hopes VBA-Net will be widely adopted in training and credentialing programmes within the next decade, ultimately contributing to better-trained surgeons and improved patient outcomes.
He said: ‘We hope the insights from this research can pave the way for integrating this technology in training and credentialing programs in the next five to ten years. Our ultimate aspiration is to enhance patient outcomes, save lives and cultivate more well-trained surgeons in the future.’
The research team, which includes postdoctoral researcher Erim Yanik and Dr Steven Schwaitzberg, from the Jacob’s School of Medicine and Biomedical Sciences at the University at Buffalo, believes this AI tool could play a critical role in the future of surgical education.
