Surgical skill level classification model development using EEG and eye-gaze data and machine learning algorithms
Problem
Surgical expertise in robot-assisted surgery is difficult to assess objectively; the study aimed to automatically classify surgeons' skill levels.
Why it matters
Surgeon skill directly affects patient safety and outcomes in robot-assisted operations.
What the AI did
Machine learning models (multinomial logistic regression, random forest, gradient boosting) classified skill levels from EEG and eye-gaze features recorded during da Vinci surgery subtasks, graded against expert GEARS scores.
Results
GB model with EEG features: 83% accuracy (blunt dissection), 85% (retraction), 81% (burn dissection).
Impact
Demonstrates feasibility of objective automated skill assessment, but only in an 11-participant study.
Record
| Venue | Journal of Robotic Surgery |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Somayeh B. Shafiei, Saeed Shadpour, James Lloyd Mohler, Farzan Sasangohar, Camille Gutierrez, Mehdi Seilanian Toussi, Ambreen Shafqat |
| Citations | 25 (OpenAlex, at import time) |
| References | 32 |
| Model or method | Gradient boosting (best), also multinomial logistic regression and random forest |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1007/s11701-023-01722-8 |
| Open access | hybrid |
| Keywords | surgical skill, EEG, eye-gaze, machine learning, robot-assisted surgery, gradient boosting |
Importance rating
incremental / niche
Objective surgical skill assessment could aid training and safety, but evidence is an 11-participant feasibility study; incremental/niche at this stage.