Virtual Reality Simulators Help Determine Neurosurgeon Expertise
By HospiMedica International staff writers Posted on 14 Aug 2019 |
Image: A new study claims VR simulators can help categorize neurosurgeon expertise (Photo courtesy of Helmut Bernhard/ NEURO).
Virtual reality (VR) simulators may soon be capable of classifying surgical expertise with high precision, claims a new study.
Researchers at McGill University (Montreal, Canada) and Amirkabir University of Technology (Tehran, Iran) conducted a study that included 50 participants in order to identify surgical and operative factors--as selected by a machine learning algorithm--that could be used to quantify psychomotor skills and generate data sets that could be used classify levels of expertise in a VR surgical procedure. For the study, the participants conducted tumor resections using the NeuroVR, a VR simulator that records all instrument movements in 20 millisecond intervals.
Study participants were recruited from four stages of neurosurgical training. They were classified as expert (neurosurgery staff), seniors (neurosurgical fellows and senior residents), juniors (neurosurgical junior residents), and medical students, all of whom participated in 250 simulated resections. Through an iterative process, performance metrics associated with instrument movement and force, resection of tissues, and bleeding generated from the raw simulator data output were selected to most accurately determine group membership.
The results showed that a K-nearest neighbor algorithm had an accuracy of 90% (45 of 50), a naive Bayes algorithm had an accuracy of 84%, a discriminant analysis algorithm had an accuracy of 78%, and a support vector machine algorithm had an accuracy of 76%. The K-nearest neighbor algorithm used six performance metrics to classify participants, the naive Bayes algorithm used 9 performance metrics, the discriminant analysis algorithm used 8 performance metrics, and the support vector machine algorithm used 8 performance metrics. The study was published on August 2, 2019, in the Journal of the American Medical Association (JAMA).
“Physician educators are facing increased time pressure to balance their commitment to both patients and learners,” said senior author Rolando Del Maestro, PhD, of the McGill Neurosurgical Simulation and Artificial Intelligence Learning Centre (NEURO). “Our study proves that we can design systems that deliver on-demand surgical assessments at the convenience of the learner and with less input from instructors. It may also lead to better patient safety by reducing the chance for human error both while assessing surgeons and in the operating room.”
Current training for surgeons is largely confined to classroom lessons and viewing cadaver-based teaching, with limited hands-on time actually spent on cadavers by students themselves.
Related Links:
McGill University
Amirkabir University of Technology
Researchers at McGill University (Montreal, Canada) and Amirkabir University of Technology (Tehran, Iran) conducted a study that included 50 participants in order to identify surgical and operative factors--as selected by a machine learning algorithm--that could be used to quantify psychomotor skills and generate data sets that could be used classify levels of expertise in a VR surgical procedure. For the study, the participants conducted tumor resections using the NeuroVR, a VR simulator that records all instrument movements in 20 millisecond intervals.
Study participants were recruited from four stages of neurosurgical training. They were classified as expert (neurosurgery staff), seniors (neurosurgical fellows and senior residents), juniors (neurosurgical junior residents), and medical students, all of whom participated in 250 simulated resections. Through an iterative process, performance metrics associated with instrument movement and force, resection of tissues, and bleeding generated from the raw simulator data output were selected to most accurately determine group membership.
The results showed that a K-nearest neighbor algorithm had an accuracy of 90% (45 of 50), a naive Bayes algorithm had an accuracy of 84%, a discriminant analysis algorithm had an accuracy of 78%, and a support vector machine algorithm had an accuracy of 76%. The K-nearest neighbor algorithm used six performance metrics to classify participants, the naive Bayes algorithm used 9 performance metrics, the discriminant analysis algorithm used 8 performance metrics, and the support vector machine algorithm used 8 performance metrics. The study was published on August 2, 2019, in the Journal of the American Medical Association (JAMA).
“Physician educators are facing increased time pressure to balance their commitment to both patients and learners,” said senior author Rolando Del Maestro, PhD, of the McGill Neurosurgical Simulation and Artificial Intelligence Learning Centre (NEURO). “Our study proves that we can design systems that deliver on-demand surgical assessments at the convenience of the learner and with less input from instructors. It may also lead to better patient safety by reducing the chance for human error both while assessing surgeons and in the operating room.”
Current training for surgeons is largely confined to classroom lessons and viewing cadaver-based teaching, with limited hands-on time actually spent on cadavers by students themselves.
Related Links:
McGill University
Amirkabir University of Technology
Latest Surgical Techniques News
- Cutting-Edge Robotic Bronchial Endoscopic System Provides Prompt Intervention during Emergencies
- Handheld Device for Fluorescence-Guided Surgery a Game Changer for Removal of High-Grade Glioma Brain Tumors
- Porous Gel Sponge Facilitates Rapid Hemostasis and Wound Healing
- Novel Rigid Endoscope System Enables Deep Tissue Imaging During Surgery
- Robotic Nerve ‘Cuffs’ Could Treat Various Neurological Conditions
- Flexible Microdisplay Visualizes Brain Activity in Real-Time To Guide Neurosurgeons
- Next-Gen Computer Assisted Vacuum Thrombectomy Technology Rapidly Removes Blood Clots
- Hydrogel-Based Miniaturized Electric Generators to Power Biomedical Devices
- Custom 3D-Printed Orthopedic Implants Transform Joint Replacement Surgery
- Wearable Technology Monitors and Analyzes Surgeons' Posture during Long Surgical Procedures
- Cutting-Edge Imaging Platform Detects Residual Breast Cancer Missed During Lumpectomy Surgery
- Computational Models Predict Heart Valve Leakage in Children
- Breakthrough Device Enables Clear and Real-Time Visual Guidance for Effective Cardiovascular Interventions
- World’s First Microscopic Probe to Revolutionize Early Cancer Diagnosis
- World’s Smallest Implantable Brain Stimulator Demonstrated in Human Patient
- Robotically Assisted Lung Transplants Could Soon Become a Reality