CausalSymptom: Learning Causal Disentangled Representation for Depression Severity Estimation on Transcribed Clinical Interviews
- 23 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 17 (1) , 277-289
Abstract
Depression is one of the most prevalent mental disorders in the world. Although some researchers have applied deep learning to assess depression, understanding its pathogenesis remains challenging. Psychological research highlights the inherent correlations among several depression symptoms. However, existing methods often ignore causal connections, treating symptoms independently and relying on local relationships without identifying valid causal paths. In this paper, we propose a novel framework, CausalSymptom, based on a variational autoencoder, to predict the severity of depression and explore its pathogenesis. The framework incorporates causal representation learning to model latent symptom states. Crucially, we provide theoretical evidence that these symptom variables can be disentangled from others by using additional information as supervision. Once these representations are learned, we present a new framework that includes a novel module, the Graph Causal Effect Network (GCEN), for the estimation of depression. This module learns a causal graph representation based on a causal total effect mechanism, which integrates causal influences across all paths, leading to a more accurate estimation of depression severity. Our model achieves competitive performance on the DAIC-WOZ and E-DAIC datasets. Furthermore, the experimental study empirically shows that our model offers insight into the pathogenesis of depression.Keywords
Funding Information
- National Natural Science Foundation of China (U22A2094)
- Anhui Provincial Key Research and Development Project (202304a05020068)
- advanced computing resources provided by the Supercomputing Center of the USTC
This publication has 51 references indexed in Scilit:
- Multilevel depression status detection based on fine-grained prompt learningPattern Recognition Letters, 2024
- Exploring the Capabilities of a Language Model-Only Approach for Depression Detection in Text Data2023
- Multi-modal Depression Estimation Based on Sub-attentional Fusion2023
- Network analysis of depressive symptoms in Hong Kong residents during the COVID-19 pandemicTranslational Psychiatry, 2021
- CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models2021
- Causal Hidden Markov Model for Time Series Disease Forecasting2021
- Feature Augmenting Networks for Improving Depression Severity Estimation From Speech SignalsIEEE Access, 2020
- A network theory of mental disordersWorld Psychiatry, 2017
- The PHQ-8 as a measure of current depression in the general populationJournal of Affective Disorders, 2009
- Language use of depressed and depression-vulnerable college studentsCognition and Emotion, 2004