Analyzing mental disorders with a CNN-GRU deep learning model on motor activity

Mood disorders can significantly interfere with daily life, ranging from mild to severe, impacting relationships, work, and overall well-being. Globally, the scarcity of mental health resources and the stigma attached to mental illness are significant obstacles. Existing approaches for mood disorder detection often rely on static clinical data or other modalities (e.g., imaging or questionnaires), and the potential of continuous motor activity data remains underexplored. Continuous wearable motor activity recordings represent an objective, non-invasive method that tracks an individual's behavioral patterns relevant to their mood states, while enabling ongoing monitoring in contrast to the episodic clinical assessments. Our primary goal in this paper is to employ a Deep Learning Model utilizing CNN-GRU architecture for analyzing motor activity sequences. Through rigorous experimentation on Depresjon datasets recorded via wrist worn actigraphy, our approach achieves an accuracy of 98.1%, surpassing the accuracy levels achieved by state-of-the-art techniques.