A.I. Can Tell Good Surgeons Just By Scanning Their Brains

Can a brain scan be the best way to tell a top-surgeon? One type. Researchers at the Rensselaer Polytechnic Institute and the University of Buffalo have developed Brain-Net, an intensive learning AI tool that can accurately predict surgeon’s certification scores based on their neuroimaging data.

This certification score, known as the Fundamental of Laparoscopic Surgery Program (FLS), is currently calculated manually using a formula that is extremely time and labor-consuming. The idea behind this is to provide an objective assessment of surgical skills, which demonstrates effective training.

“The fundamental of the laparoscopic surgery program has been adopted nationally for surgical residents, peers, and physicians, who learn and practice laparoscopic skills, giving physicians the opportunity to precisely measure and document those skills,” Renselaar Xavier Intes, professor of biomedical engineering, told. Digital trends. “Such a major aspect [a] The program is a scoring metric calculated based on the timing of surgical performance as well as error estimation. “

The team of researchers on this project wanted to see if they could predict surgeons’ FLS scores using optical brain imaging. Thanks to concurrent neural networks, they showed that they were able to do so with a high degree of accuracy. The work is based on previous research showing functional near-infrared spectroscopy (FNIRS) effective for classifying various near-motor task types, providing a potential means of manual skill performance level. In this latest project, researchers used similar fNIRS data to predict the final performance score used in surgical certification.

“These results are making the move toward neuroimaging and intensive learning for neurofeedback to improve surgical skill acquisition, retention, and the certification process,” continued Intes. “The advantage of these approaches is that they should enable more personalized training with bedside feedback for optimal skill acquisition. Current approaches are focusing on task repetition, potentially for rapid and objective feedback. “

This work is part of an ongoing effort to enhance the way in which surgical skills are taught and evaluated. On its own, this latest piece of research is not going to change radically. However, going forward it can lay the foundation for new ways to improve surgical performance – and individual approaches to training – using neuroimaging assessment.

“We are currently using FLS scores as a means of assessing surgical skills,” Intes said. “We hope that, with further studies, we will be able to go beyond this metric and discover [a] New set of neurobiomarkers that will provide granular insights on learning and execution of surgical skills. “

A paper describing the research is available for reading in the journal IEEE Transactions on Biomedical Engineering.

Editors recommendations

Related Posts