Joint Surgeon Attributes Estimation in Robot-Assisted Surgery

Abstract

This paper proposes a computational framework to estimate surgeon attributes during Robot-Assisted Surgery (RAS). The three investigated attributes are workload, performance, and expertise levels. The framework leverages multimodal sensing and joint estimation and was evaluated with twelve surgeons operating on the da Vinci Skills Simulator. The multimodal signals include heart rate variability, wrist motion, electrodermal, electromyography, and electroencephalogram activity. The proposed framework reached an average estimation error of 11.05%, and jointly inferring surgeon attributes reduced estimation errors by 10.02%.