A Real-Time Ergonomic Coaching System for Neurosurgeons Using Virtual Reality and Machine Learning-Based Posture Analysis

Authors

  • Bayan Bagasi Computer Science Department, Faculty of Computer and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia
  • Wadee Alhalabi Computer Science Department, Faculty of Computer and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia
  • Abdulrahman J Sabbagh Division of Neurosurgery, Department of Surgery, College of Medicine, King Abdulaziz University, Jeddah, Saudi Arabia
  • Nada Bajnaid Computer Science Department, Faculty of Computer and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia
  • Khalid Bajunaid Department of Surgery, Faculty of Medicine, University of Jeddah, Jeddah, Saudi Arabia
  • Alaa M Arafah Department of Occupational Therapy, Faculty of Medical Rehabilitation Sciences, King Abdulaziz University, Jeddah, Saudi Arabia
  • Maram Alaslani Computer Science Department, Faculty of Computer and Information Technology, King Abdulaziz University, Rabig, Saudi Arabia
  • Shroog Alghamdi Computer Science Department, Faculty of Computer and Information Technology, King Abdulaziz University, Rabig, Saudi Arabia
  • Hanaa Aljehani Computer Science Department, Faculty of Computer and Information Technology, King Abdulaziz University, Rabig, Saudi Arabia
  • Ghada Enani Department of surgery, King Abdulaziz university. Jeddah Saudi Arabia
  • Daan Bagasi Faculty of Medicine, King Abdulaziz university. Jeddah Saudi Arabia

DOI:

https://doi.org/10.63278/1439

Keywords:

Ergonomics, Virtual Reality (VR), Machine Learning (ML), Neurosurgery, Pose Estimation, Surgical Training.

Abstract

Background: Musculoskeletal disorders continue to affect neurosurgeons with the prevalence of work-related musculoskeletal disorders exacerbated by long hours of static postures in performing delicate and precise surgeries. Ergonomics training, despite its increasing emphasis, is still not adequately integrated within the structure of neurosurgical education.

Objective: In this paper, we present to you the Automated Ergonomics Coaching System (AECS)- a virtual reality-based training platform with Artificial Intelligence-powered pose estimation that enables real-time feedback in creating ergonomic awareness during neurosurgical simulations.

Methods: Twenty-four neurosurgical residents were randomly divided into two groups, an AECS group and a control group. All participants underwent three sessions of simulation training on spine surgery. The quantification of posture deviations was carried out by the model pose and was supplemented by pre- and post-usability questionnaires to assess usability and ergonomics awareness

Results: Though not proven statistically, there was a difference in the ergonomic error rates between the two groups (p=0.278). AECS members showed steady progress from one trial to the next. They had good posture check, were more confident in their ability to correct ergonomics, and gave the system high marks for usability. A large percentage, 73.91%, said that they now have better knowledge as to the strains that come with postures.

Conclusions: AECS shows potential as a practical, feedback-rich training system that enhances ergonomic posture in surgical education. Real-time pose estimation and interactive guidance support a safer, more sustainable learning pathway for surgeons. Future work will explore long-term retention and cross-institutional validation.

Downloads

Published

2025-04-16

How to Cite

Bayan Bagasi, Wadee Alhalabi, Abdulrahman J Sabbagh, Nada Bajnaid, Khalid Bajunaid, Alaa M Arafah, Maram Alaslani, et al. 2025. “A Real-Time Ergonomic Coaching System for Neurosurgeons Using Virtual Reality and Machine Learning-Based Posture Analysis ”. Metallurgical and Materials Engineering 31 (4):299-317. https://doi.org/10.63278/1439.

Issue

Vol. 31 No. 4 (2025)

Section

Research

License

Copyright (c) 2025 Bayan Bagasi, Wadee Alhalabi, Abdulrahman J Sabbagh, Nada Bajnaid, Khalid Bajunaid, Alaa M Arafah, Maram Alaslani, Shroog Alghamdi, Hanaa Aljehani, Ghada Enani, Daan Bagasi

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  • Authors are permitted and encouraged to post their published articles online (e.g., in institutional repositories or on their website, social networks like ResearchGate or Academia), as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

 

Creative Commons License
Except where otherwise noted, the content on this site is licensed under a Creative Commons Attribution 4.0 International License.