Eye-Tracking Metrics Predict Perceived Workload in Robotic Surgical Skills Training

Area of Science:

• Robotics
• Human Factors
• Surgical Training

Background:

• Robotic surgery offers advantages but presents complex challenges for surgeons.
• Objective quantification of workload in robotic surgery is limited.
• Eye-tracking metrics show promise for assessing workload in various domains.

Purpose of the Study:

• To assess the relationship between eye-tracking measures and perceived workload in robotic surgical tasks.
• To explore the potential of eye-tracking for objective workload assessment in surgical training.

Main Methods:

• Eight surgical trainees performed simulated robotic exercises.
• Correlation and mixed-effects analyses examined eye-tracking metrics and perceived workload.
• Machine learning classified workload levels using eye-tracking features.

Main Results:

• Gaze entropy positively correlated with perceived workload (r=0.51).
• Pupil diameter and gaze entropy indicated workload differences across task difficulties.
• An eye-tracking-based model achieved 84.7% accuracy in predicting workload levels.

Conclusions:

• Eye-tracking measures effectively detect perceived workload during robotic surgery.
• These metrics can identify workload contributors and inform robotic surgery training.
• Real-time workload monitoring can enhance surgical performance and learning assessments.