A Deep Learning approach for Depressive Symptoms assessment in Parkinson's disease patients using facial videos

Parkinson's disease (PD) is a neurodegenerative disorder, manifesting with motor and non-motor symptoms. Depressive symptoms are prevalent in PD, affecting up to 45% of patients. They are often underdiagnosed due to overlapping motor features, such as hypomimia. This study explores deep learning (DL) models-ViViT, Video Swin Tiny, and 3D CNN-LSTM with attention layers-to assess the presence and severity of depressive symptoms, as measured by the Geriatric Depression Scale (GDS), in PD patients through facial video analysis. A secondary analysis was conducted to evaluate the same parameters considering patients' medication states: one hour after dopaminergic medication intake (ON-medication) and 12 hours without medication (OFF-medication). Using a dataset of 1,875 videos from 178 patients, the Video Swin Tiny model achieved the highest performance, with up to 94% accuracy and 93.7% F1-score in binary classification (presence or absence of depressive symptoms) and 87.1% accuracy with an 85.4% F1-score in multiclass tasks (absence, mild, or severe depressive symptoms).Clinical relevance- This study underscores the potential of DL-based spatiotemporal analysis for scalable, noninvasive diagnosis and monitoring of depressive symptoms in PD patients. These findings highlight the potential of AI-driven facial analysis as a screening tool or a supplementary aid in depressive symptom assessment, supporting clinical diagnosis and treatment decisions. Integrating such methods into routine clinical practice could improve early detection and personalized treatment strategies, ultimately enhancing patients' care and quality of life.