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

• Published in: Human factors 2020-12, Vol.62 (8), p.1365-1386
• Main Authors: Wu, Chuhao, Cha, Jackie, Sulek, Jay, Zhou, Tian, Sundaram, Chandru P., Wachs, Juan, Yu, Denny
• Format: Article
• Language: English
• Subjects: Benchmarking; Clinical Competence; Control systems; Correlation analysis; Diameters; Entropy; Eye movements; Eye-Tracking Technology; Humans; Interfaces; Laparoscopy; Learning algorithms; Machine learning; Model accuracy; Robotic surgery; Robotic Surgical Procedures; Skills; Stereoscopic vision; Surgery; Tracking; Training; Training, Education, Instructional Systems; Workload; Workloads
• ISSN: 0018-7208; 1547-8181
• DOI: 10.1177/0018720819874544

Objective The aim of this study is to assess the relationship between eye-tracking measures and perceived workload in robotic surgical tasks. Background Robotic techniques provide improved dexterity, stereoscopic vision, and ergonomic control system over laparoscopic surgery, but the complexity of the interfaces and operations may pose new challenges to surgeons and compromise patient safety. Limited studies have objectively quantified workload and its impact on performance in robotic surgery. Although not yet implemented in robotic surgery, minimally intrusive and continuous eye-tracking metrics have been shown to be sensitive to changes in workload in other domains. Methods Eight surgical trainees participated in 15 robotic skills simulation sessions. In each session, participants performed up to 12 simulated exercises. Correlation and mixed-effects analyses were conducted to explore the relationships between eye-tracking metrics and perceived workload. Machine learning classifiers were used to determine the sensitivity of differentiating between low and high workload with eye-tracking features. Results Gaze entropy increased as perceived workload increased, with a correlation of .51. Pupil diameter and gaze entropy distinguished differences in workload between task difficulty levels, and both metrics increased as task level difficulty increased. The classification model using eye-tracking features achieved an accuracy of 84.7% in predicting workload levels. Conclusion Eye-tracking measures can detect perceived workload during robotic tasks. They can potentially be used to identify task contributors to high workload and provide measures for robotic surgery training. Application Workload assessment can be used for real-time monitoring of workload in robotic surgical training and provide assessments for performance and learning.