Related Experiment Video
Updated: Jul 16, 2025
07:48
Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
Published on: April 4, 2025
369
Performance and learning rate prediction models development in FLS and RAS surgical tasks using electroencephalogram
Somayeh B Shafiei1, Saeed Shadpour2, Xavier Intes3
1Intelligent Cancer Care Laboratory, Department of Urology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, 14263, USA. Somayeh.BesharatShafiei@RoswellPark.org.
Surgical Endoscopy
|September 21, 2023
Summary
This study used electroencephalogram (EEG) and eye gaze to evaluate surgical skills in laparoscopic and robotic surgery. Machine learning models identified key features for assessing performance and learning rates in surgical trainees.
Area of Science:
- Surgical Education
- Medical Technology
- Machine Learning in Medicine
Background:
- Objective evaluation of surgical performance and learning is crucial for effective training.
- Traditional assessment methods may not fully capture the nuances of skill acquisition in complex procedures.
- Emerging technologies like electroencephalogram (EEG) and eye-tracking offer potential for more granular insights.
Purpose of the Study:
- To explore the utility of electroencephalogram (EEG) and eye gaze features, alongside experience metrics, for evaluating performance and learning rates.
- To apply machine learning techniques for objective assessment in Fundamentals of Laparoscopic Surgery (FLS) and Robotic-Assisted Surgery (RAS).
Main Methods:
- Collected EEG and eye-tracking data from participants performing FLS and RAS tasks.
- Developed generalized linear mixed models (L1-penalized) for performance evaluation using EEG and eye gaze.
- Utilized linear models to assess learning rates based on these features and initial performance.
- Incorporated experience metrics and analysis of variance (ANOVA) to examine their impact on learning.
Main Results:
- EEG and eye gaze features, along with experience, significantly contributed to performance evaluation in FLS and RAS.
- Demonstrated performance differences across experience levels, with residents, fellows, and faculty generally outperforming pre-medical students in various tasks.
- Specific p-values indicated statistically significant performance advantages for higher experience groups in FLS peg transfer, pattern cut, suturing, and RAS tissue dissection and pattern cut.
Conclusions:
- The findings support the use of EEG, eye gaze, and machine learning for objective surgical skill assessment.
- These methods can inform the development of targeted training interventions to enhance surgical proficiency.
- The study contributes to understanding motor learning in surgery and designing effective educational strategies.
