Modeling Surgeons’ Mental Workload in Robot-Assisted Surgery: A Bidirectional Overload-Recovery Model Using Neurophysiological Measures

Robotic-assisted surgery (RAS) enhances dexterity, visualization, and ergonomics, and is widely adopted across urology, gynecology, and gastroenterology. However, RAS imposes high mental workload (MWL) on surgeons due to technical complexity, novel interfaces, and reduced team interaction. Mental overload depletes cognitive resources, slows responses, and impairs decision-making, which may result in performance degradation and threaten patient safety. Mitigating these risks requires effective MWL management through task redistribution, cognitive support, and neuroadaptive interventions, all of which depend on accurate, real-time MWL assessment. The objective of this work is to develop a reliable real-time MWL assessment framework by modeling MWL changes as bidirectional transitions between overload and recovery.