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

Abstract

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.

Non-Technical Skill Assessment and Mental Load Evaluation in Robot-Assisted Minimally Invasive Surgery

“…Workload can be defined with self-rating techniques, where a subject fills a questionnaire about his/her personal experience about the task workload. It is naturally a subjective technique, however, there are works in the literature which studied both subjective workload measurements and objective non-technical skill assessment metrics [ 32 , 40 ], or objective physiological parameters [ 30 , 34 , 41 , 42 , 43 , 44 , 45 , 46 ]. Workload measurements do not only help to assess the personal workload index, but also to define the main stressors and disturbing factors in surgery in general, furthermore, to provide personal training for novices as well.…”

“…NASA-TLX is a widely used technique for workload measurement in aviation, military and healthcare. NASA-TLX can be found in traditional MIS mental workload estimation [ 48 , 49 , 50 , 51 , 52 ], and employed in the case of surgical robotics workload assessment as well [ 8 , 32 , 34 , 40 , 41 , 43 , 45 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 ]. There are additional mental workload assessment techniques that are not originally created for surgery, and used in workload assessment for RAMIS.…”

“…With self-rating tools, the real stressors of the surgery can be observed, and other approaches have to fit to the clinical relevance. Self-rating studies can be found in Table 5 under the following references: [ 30 , 31 , 32 , 34 , 40 , 41 , 42 , 43 , 44 , 50 , 56 , 57 , 59 , 60 , 61 , 62 , 63 , 64 , 66 , 68 , 69 , 70 , 71 , 72 , 75 , 76 , 81 , 85 , 93 , 94 , 95 ].…”

“…As shown in this article, this research field is not studied widely yet. Automated technology-based studies can be found in Table 5 under the following references: [ 7 , 30 , 34 , 41 , 42 , 43 , 44 , 45 , 46 , 69 , 70 , 72 , 85 , 93 , 111 , 114 , 115 ].…”

Identifying mental health status using deep neural network trained by visual metrics

“…Prior studies have also shown that after an unpleasant-stimulus, emotions were indexed by eye-blink startle, and left-sided frontal EEG activation occurred 36 . Visual metrics have also been proposed for detection of human physiological changes including mental fatigue 37 , cognition and cognitive development 38 , mental workload evaluation 39,40 , stress level in students 41 , threat-related emotional facial expressions in infancy 42 , shared attention for virtual agent 43 , and emotional arousal and autonomic activation 44 .…”