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

TL;DR

This study develops deep learning models to assess depressive symptoms in Parkinson's disease patients through facial videos, achieving high accuracy and F1-scores, which could improve diagnosis and monitoring.

Contribution

It introduces and compares multiple deep learning models for facial video analysis to detect depression severity in PD patients, with the best model reaching 94% accuracy.

Findings

Video Swin Tiny achieved 94% accuracy in binary classification.

Models performed well in multiclass depression severity detection.

Medication state influenced the assessment results.

Abstract

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 detected by the Geriatric Depression Scale (GDS), in PD patients through facial video analysis. The same parameters were assessed in a secondary analysis taking into account whether patients were one hour after (ON-medication state) or 12 hours without (OFF-medication state) dopaminergic 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 of absence of depressive symptoms), and 87.1% accuracy with an 85.4% F1-score in multiclass tasks (absence or mild or severe depressive symptoms).