Mental fatigue (MF) negatively affects both cognitive and physical performance, increasing the risk of errors in high-stakes environments such as sports and surgery. Traditional methods to assess MF rely on subjective self-report scales, which are prone to bias, or on complex brain measurements (e.g. EEG) that are impractical outside laboratory settings. This study aims to develop a real-time, objective monitoring method for MF using wearable physiological sensors. The study will recruit healthy, trained runners (18-35 years old) who will complete both an MF-inducing cognitive task (Stroop test) and a control condition (watching a documentary) in a randomized, counterbalanced, crossover design. Heart rate variability, respiration rate, and pupil metrics will be continuously recorded using wearable devices. Machine learning models will be used to predict MF-level as well as the effect of MF on physical performance (5-km time trial on a treadmill) using the physiological data as input.
Healthy (no neurological, cardiovascular or musculoskeletal disorders of any kind)
Male or female
No prior knowledge of the concept of MF
No medication
Injuries in the past 6 months, affecting running performance
Suffering from a chronic health condition (could be neurological, cardiovascular, internal or musculoskeletal)
Participating in any concomitant care or research trials
History of suffering from any mental/psychiatric disorders