Sinai researchers have demonstrated the difficult procedures using artificial intelligence (AI) algorithms and the effectiveness of teaching surgical trainees an augmented reality headset without the presence of instructors. All 17 trainees in the study achieved surgical success.
A new study published in the Journal of Medical Extended Reality elicited highly favorable reviews from student participants who tested deep learning models. The results have great implications for future training for residents and surgeons, as well as for the broader fields of autonomous learning within medicine.
“For the first time, we have created an AI model linked to an extended reality headset to prove that we can achieve key steps in the kidney cancer procedure with 99.9% accuracy,” said Nelson Stone (MD), a clinical clinical professor of urology, radiation oncology and oncology science, as the Icahn School of Sinai in Sanai and the corresponding author. “We believe that our research is early on that AI programs that replace Proctors who teach residents can reduce training costs and ultimately improve the quality, efficiency and standardization of their teaching.”
Surgical training of residents has traditionally required the presence of teaching proctors along with student doctors in the operating room. Dr. Stone and his team included researchers from the Department of Neurosurgery at the University of Rochester Medical Center in upstate New York, and investigated alternative training systems using the AI program they developed, including ESIST (Educational System for Surgery Training without Teaching). The model featured a custom designed augmented reality headset worn by 17 participants, as well as streaming surgical instructions and video content right in front of them, allowing them to practice complex procedures freely.
This surgery simulated a partial nephrectomy procedure designed to remove cancerous areas of the kidney, such as placing clamps in the renal artery. For this replication, researchers created a “phantom” kidney from a 3D printed cast of computed tomography (CT) scans of anonymous patients. The cast was filled with water-based polymer and assembled to create a partial nephrectomy model with kidney tumors. While students were practicing, the system's sophisticated first-person cameras continuously monitored the training and projected real-time feedback and corrective prompts as part of their skill assessment capabilities.
“More than anything, our research has proven that, without the presence of an instructor, simulated models can be used to effectively teach surgical trainees complex procedures, such as partial nephrectomy, effectively,” Dr. Stone said. “This discovery comes from serious time constraints on reaching doctors who will address the urgent need resulting from a lack of trainers and supervisors to educate doctors on new medical devices and technologies, and training residents to pursue surgical careers.”
Another major advantage of advanced education techniques is that what we add to Dr. Stone is that it will help future surgeons become proficient in procedures outside the operating room and reduce the risk of surgical errors. “From a patient's perspective, we hope that this study will reassure you that the technology can be utilized to significantly improve surgical capabilities while reducing surgical errors,” Dr. Stone said.
The next step for Mount Sinai researchers is to build more complex synthetic corpse models, using AI algorithm technology developed to build more complex synthetic corpse models, rather than just one component, as reported in the study. The team was encouraged by the investigation they conducted after training. In this study, 100% of participants thought the program had great educational value.
“Our research suggests that AI systems can play an important complementary role in shaping the future of surgical education in this country,” argues Dr. Stone. “The public should be reassuring that the pathways to autonomous learning we investigated in this small study could ultimately lead to significant cost savings and improved patient outcomes and, importantly, to cultivate a new generation of highly skilled surgeons.”
The authors of the studies described in the journal are Jonathan J. Stone, Nelson N. Stone, Stephen H. Griffiths, Kyle Zeller, and Michael P. Wilson.
All authors except Kyle Zeller retain the fairness of Viomerse.
This study was funded by the National Institute of Biomedical Imaging and Bioengineering (Grant 1R41EB026358-01A1) and the National Science Foundation (Grant 1913911).
About Mount Sinai Health System
Mount Sinai Health System is one of the largest academic health systems in New York's metropolitan area, employing 48,000 employees across seven hospitals, and is an advanced school for over 400 outpatient practices, over 600 research and clinical laboratories, a nursing school, and medical and graduate education. Mount Sinai advances the health of all people by taking on the most complex healthcare challenges of our time. Discover and apply new scientific learning and knowledge. Develop safer and more effective treatments. Educate the next generation of medical leaders and innovators. And we support our community by providing high quality care to everyone who needs it.
Through the integration of hospitals, labs and schools, Mount Sinai offers comprehensive healthcare solutions from birth to geriatric medicine, leveraging innovative approaches such as artificial intelligence and informatics, keeping the medical and emotional needs of patients at the heart of all treatments. The health system includes approximately 9,000 primary care physicians and 11 independent joint venture centers across five districts: New York City, Westchester, Long Island and Florida. Hospitals in the system are consistently ranked by Newsweek's® “The World's Best Smart Hospital, State Hospital, World's Best Hospital, Best Specialist Hospital”, and US News & World Report's® “Best Hospitals” and “Best Children's Hospitals.” Mount Sinai Hospital is in the Honorary Roll of the US News & World Report “Best Hospital” on 2025-2026.
/Public release. This material of the Organization of Origin/Author is a point-in-time nature and may be edited for clarity, style and length. Mirage.news does not take any institutional position or aspect, and all views, positions and conclusions expressed here are the views of the authors alone.
