DepressionMIGNN: A Multiple-Instance Learning-Based Depression Detection Model with Graph Neural Networks

The global prevalence of depression necessitates the application of technological solutions, particularly sensor-based systems, to augment scarce resources for early diagnostic purposes. In this study, we use benchmark datasets that contain multimodal data including video, audio, and transcribed tex...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Vol. 25; no. 14; p. 4520
Main Authors: Zhao, Shiwen, Zhang, Yunze, Su, Yikai, Su, Kaifeng, Liu, Jiemin, Wang, Tao, Yu, Shiqi
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 21.07.2025
MDPI
Subjects:
Algorithms
Artificial intelligence
Comparative analysis
Computer-aided medical diagnosis
Data processing
Depression - diagnosis
depression recognition
Depression, Mental
Diagnosis
Graph Neural Networks
Human acts
Human behavior
Humans
Identification and classification
Mental depression
Mental disorders
Mental health care
Methods
multi-dimensional edge
multimodality
Multiple-Instance Learning Algorithms
Neural networks
Neural Networks, Computer
China
graph neural networks
multimodality
depression recognition
multi-dimensional edge
ISSN:1424-8220, 1424-8220
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The global prevalence of depression necessitates the application of technological solutions, particularly sensor-based systems, to augment scarce resources for early diagnostic purposes. In this study, we use benchmark datasets that contain multimodal data including video, audio, and transcribed text. To address depression detection as a chronic long-term disorder reflected by temporal behavioral patterns, we propose a novel framework that segments videos into utterance-level instances using GRU for contextual representation, and then constructs graphs where utterance embeddings serve as nodes connected through dual relationships capturing both chronological development and intermittent relevant information. Graph neural networks are employed to learn multi-dimensional edge relationships and align multimodal representations across different temporal dependencies. Our approach achieves superior performance with an MAE of 5.25 and RMSE of 6.75 on AVEC2014, and CCC of 0.554 and RMSE of 4.61 on AVEC2019, demonstrating significant improvements over existing methods that focus primarily on momentary expressions.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s25144520