Measuring Anxiety Levels with Head Motion Patterns in Severe Depression Population

2025-02-12

AI Summary

Current clinical assessment of anxiety in major depressive disorder (MDD) relies heavily on subjective self-reports and clinician-rated scales, lacking objective, quantifiable biological markers. Method: This study proposes a non-invasive, video-based computational approach that extracts fine-grained head motion dynamics—including velocity, acceleration, and angular displacement—from facial landmark trajectories during clinical interviews. Leveraging the CALYPSO depression dataset, we develop an interpretable multivariate linear regression model linking these kinematic features to standardized clinical anxiety scores (e.g., HAMA). Contribution/Results: The model achieves a mean absolute error (MAE) of 0.35 on clinical validation—significantly outperforming existing behavioral biomarkers. By bridging computer vision and biomechanical motion analysis, this work establishes the first interpretable, deployable, and objective anxiety quantification framework for MDD, moving beyond traditional scale-dependent paradigms toward personalized, data-driven clinical assessment.

Technology Category

• Computer Vision: Motion & Tracking
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Depression and anxiety are prevalent mental health disorders that frequently cooccur, with anxiety significantly influencing both the manifestation and treatment of depression. An accurate assessment of anxiety levels in individuals with depression is crucial to develop effective and personalized treatment plans. This study proposes a new noninvasive method for quantifying anxiety severity by analyzing head movements -specifically speed, acceleration, and angular displacement - during video-recorded interviews with patients suffering from severe depression. Using data from a new CALYPSO Depression Dataset, we extracted head motion characteristics and applied regression analysis to predict clinically evaluated anxiety levels. Our results demonstrate a high level of precision, achieving a mean absolute error (MAE) of 0.35 in predicting the severity of psychological anxiety based on head movement patterns. This indicates that our approach can enhance the understanding of anxiety's role in depression and assist psychiatrists in refining treatment strategies for individuals.

Problem

• Quantify anxiety severity noninvasively
• Analyze head movements in depression
• Predict anxiety levels using regression

Innovation

• Noninvasive head motion analysis
• Regression-based anxiety prediction
• High precision anxiety assessment