Exploring Facial Biomarkers for Depression through Temporal Analysis of Action Units

2024-07-18

arXiv.org

AI Summary

Objective biological biomarkers are urgently needed for depression diagnosis. This study proposes a novel, dual-dimensional biomarker framework based on temporal dynamics of facial Action Units (AUs) and associated emotional states. Using naturalistic dialogue videos from depressed patients and healthy controls, we extracted intensity time series for 17 AUs. Applying principal component analysis, clustering, and statistical modeling, we systematically identified depression-specific temporal abnormalities—particularly elevated intensities in sadness-related AUs (AU1+4+15) and reduced intensities in happiness-related AUs (AU6+12)—for the first time. Furthermore, we developed a temporal classification model that significantly outperformed static-feature baselines (p < 0.01). These findings empirically validate dynamic facial features as objective, quantifiable, and clinically promising biomarkers for depression.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Computer Vision: Biometrics, Face, Gesture & Pose
• Humans and AI: Emotional Intelligence

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Depression is characterized by persistent sadness and loss of interest, significantly impairing daily functioning and now a widespread mental disorder. Traditional diagnostic methods rely on subjective assessments, necessitating objective approaches for accurate diagnosis. Our study investigates the use of facial action units (AUs) and emotions as biomarkers for depression. We analyzed facial expressions from video data of participants classified with or without depression. Our methodology involved detailed feature extraction, mean intensity comparisons of key AUs, and the application of time series classification models. Furthermore, we employed Principal Component Analysis (PCA) and various clustering algorithms to explore the variability in emotional expression patterns. Results indicate significant differences in the intensities of AUs associated with sadness and happiness between the groups, highlighting the potential of facial analysis in depression assessment.

Problem

• Investigating facial action units as depression biomarkers
• Developing objective diagnosis methods using temporal analysis
• Identifying emotional expression differences between depressed groups

Innovation

• Analyzing facial action units for depression biomarkers
• Applying time series classification to emotional patterns
• Using PCA and clustering for expression variability analysis