A Novel Audio-Visual Information Fusion System for Mental Disorders Detection

TL;DR

This paper introduces a multimodal audio-visual system using attention networks for detecting multiple mental disorders, achieving high accuracy and reducing computational costs compared to traditional methods.

Contribution

It presents a novel, general-purpose diagnosis system based on emotional expression features, combining audio and visual data with efficient deep learning techniques.

Findings

Achieves over 80% accuracy on ADHD dataset

Sets new state-of-the-art results on AVEC 2014 depression dataset

Uses less computational resources than traditional fMRI and EEG methods

Abstract

Mental disorders are among the foremost contributors to the global healthcare challenge. Research indicates that timely diagnosis and intervention are vital in treating various mental disorders. However, the early somatization symptoms of certain mental disorders may not be immediately evident, often resulting in their oversight and misdiagnosis. Additionally, the traditional diagnosis methods incur high time and cost. Deep learning methods based on fMRI and EEG have improved the efficiency of the mental disorder detection process. However, the cost of the equipment and trained staff are generally huge. Moreover, most systems are only trained for a specific mental disorder and are not general-purpose. Recently, physiological studies have shown that there are some speech and facial-related symptoms in a few mental disorders (e.g., depression and ADHD). In this paper, we focus on the emotional expression features of mental disorders and introduce a multimodal mental disorder diagnosis system based on audio-visual information input. Our proposed system is based on spatial-temporal attention networks and innovative uses a less computationally intensive pre-train audio recognition network to fine-tune the video recognition module for better results. We also apply the unified system for multiple mental disorders (ADHD and depression) for the first time. The proposed system achieves over 80\% accuracy on the real multimodal ADHD dataset and achieves state-of-the-art results on the depression dataset AVEC 2014.