The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will lead to broader adoption of newer medical technologies and increased revenue for medical device companies, decreased training costs, and decreased liability from misuse or lack of appropriate training on medical devices. Research has shown that surgical skill is directly related to a variety of patient outcomes, yet there are few tools that can reliably and affordably measure surgical proficiency. Providing objective measurements of surgical proficiency is not enough; the assessment method must also identify areas of difficulty during a task to improve the surgeon's future performance. The proposed innovation is an objective and scalable way to measure procedural competency using head and hand motion-tracking data collected in a surgical simulation and applying novel, deep-learning algorithms to the analysis. By providing surgeons with real-time feedback during training, this project will allow surgeons to rapidly improve training on specialized devices, thus leading to wider adoption of new technology. Adoption of this surgical assessment platform in medical schools and operating rooms across the country will enable an objective assessment of surgical proficiency, thus reducing training time and costs and lowering risk of medical error due to underdeveloped skills.This Small Business Innovation Research (SBIR) Phase I project seeks to develop an innovative, deep-learning Surgical Training and Assessment Platform to increase the commercial viability of a Virtual Reality (VR) surgical training program. VR surgical training technology holds enormous potential in improving the efficiency of learning by allowing for unlimited practice and rehearsal of surgical procedures; however, without the ability to reliably assess performance, such platforms cannot be used to their full potential. This application will translate the simulation environment into a vehicle for technical skills assessment to prevent trainees from graduating to independent practice without first proving competency in critical areas. The novel, proprietary software algorithms developed in this proposal will allow for the above applications and broad improvements to training efficiency and patient safety through the tracking and analysis of hand and head motion as a surrogate measure for surgical expertise. The Surgeon Assessment Platform will be developed by determining the most vital head and hand motion data to collect and validating the resulting assessment dataset in a small proof-of-concept study, while meeting the challenge of collecting, storing, and analyzing such a large, high-fidelity dataset.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
