Predicting task performance in robot-assisted surgery using physiological stress and subjective workload: a case study with interpretable machine learning

Kaiqi Wei; Chika Kimura; Megumi Shimura; Yoshihiro Shimomura; Xue Zhao; Takaaki Tamura; Shinichi Sakamoto

doi:10.3389/fnhum.2025.1611524

Predicting task performance in robot-assisted surgery using physiological stress and subjective workload: a case study with interpretable machine learning

Front Hum Neurosci. 2025 Jun 18:19:1611524. doi: 10.3389/fnhum.2025.1611524. eCollection 2025.

Authors

Kaiqi Wei¹, Chika Kimura¹, Megumi Shimura¹, Yoshihiro Shimomura², Xue Zhao³, Takaaki Tamura³, Shinichi Sakamoto³

Affiliations

¹ Division of Creative Engineering, Department of Design, Graduate School of Science and Engineering, Chiba University, Chiba, Japan.
² Design Research Institute, Chiba University, Chiba, Japan.
³ Department of Urology, Graduate School of Medicine, Chiba University, Chiba, Japan.

Abstract

Robot-assisted surgery (RAS) enhances surgical precision and extends surgeons' capabilities. However, its effects on the cognitive and physical states of surgeons remain poorly understood. It is essential to investigate the workload and physiological stress surgeons experience during RAS. This case study employs a neuroergonomic approach to explore how these factors relate to task performance. A single expert surgeon performed simulated surgical tasks under systematically varied conditions (noise level, surgical posture and task type) to elicit variations in stress and workload. During the tasks, multiple physiological signals were recorded, including electroencephalography (EEG), electromyography (EMG), heart rate (HR), and electrodermal activity (EDA). Subjective workload was also assessed using the NASA-TLX and SURG-TLX. Several classification models, including CatBoost, random forest, logistic regression, and support vector machines, were trained to predict task performance. Among them, CatBoost demonstrated the highest predictive accuracy (79.5%) and achieved an area under the curve (AUC) of 0.807. The model interpretation was conducted using SHapley Additive exPlanations (SHAP). The analysis revealed that subjective workload, mean HR, and muscle activation were the most influential predictors. EEG-related features contributed variably across conditions. This study shows that integrating subjective assessments with physiological measures can effectively predict surgical task performance under stress.

Keywords: SHAP (SHapley Additive exPlanations); machine learning; neuroergonomics; physiological stress; robot-assisted surgery (RAS); surgeon workload; task performance prediction.