Towards Automated Fatigue Assessment using Wearable Sensing and Mixed-Effects Models

TL;DR

This paper presents an automated fatigue assessment method using multi-modal physiological data and mixed-effects models, aiming to improve accuracy over traditional self-reporting methods.

Contribution

It introduces a novel approach combining wearable sensing data with mixed-effects models that incorporate demographic information for better fatigue assessment.

Findings

ECG significantly contributes to fatigue detection

Mixed-effects models outperform baseline methods

Promising preliminary results achieved on collected dataset

Abstract

Fatigue is a broad, multifactorial concept that includes the subjective perception of reduced physical and mental energy levels. It is also one of the key factors that strongly affect patients' health-related quality of life. To date, most fatigue assessment methods were based on self-reporting, which may suffer from many factors such as recall bias. To address this issue, in this work, we recorded multi-modal physiological data (including ECG, accelerometer, skin temperature and respiratory rate, as well as demographic information such as age, BMI) in free-living environments and developed automated fatigue assessment models. Specifically, we extracted features from each modality and employed the random forest-based mixed-effects models, which can take advantage of the demographic information for improved performance. We conducted experiments on our collected dataset, and very promising preliminary results were achieved. Our results suggested ECG played an important role in the fatigue assessment tasks.