Wearable-Derived Behavioral and Physiological Biomarkers for Classifying Unipolar and Bipolar Depression Severity

2025-04-17

AI Summary

Traditional binary diagnostic frameworks (“healthy/depressed”) fail to distinguish unipolar from bipolar depression, hindering precise clinical stratification. Method: We collected multimodal physiological and behavioral signals—including photoplethysmography (PPG), electrodermal activity (EDA), skin temperature, and triaxial accelerometry—via wearable sensors, constructing CALYPSO, the first benchmark dataset specifically designed for depressive subtype identification. Contribution/Results: We systematically identified subtype-specific biomarkers: accelerometer-derived behavioral features and temperature-based physiological features. Leveraging time-frequency domain feature engineering and conventional machine learning models (e.g., SVM, Random Forest), we achieved fine-grained classification accuracy of 96.77% using acceleration features and 93.55% using temperature features—substantially outperforming existing binary depression detection methods. This work establishes a novel paradigm for objective, biobehaviorally grounded differential diagnosis and personalized intervention in mood disorders.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Depression is a complex mental disorder characterized by a diverse range of observable and measurable indicators that go beyond traditional subjective assessments. Recent research has increasingly focused on objective, passive, and continuous monitoring using wearable devices to gain more precise insights into the physiological and behavioral aspects of depression. However, most existing studies primarily distinguish between healthy and depressed individuals, adopting a binary classification that fails to capture the heterogeneity of depressive disorders. In this study, we leverage wearable devices to predict depression subtypes-specifically unipolar and bipolar depression-aiming to identify distinctive biomarkers that could enhance diagnostic precision and support personalized treatment strategies. To this end, we introduce the CALYPSO dataset, designed for non-invasive detection of depression subtypes and symptomatology through physiological and behavioral signals, including blood volume pulse, electrodermal activity, body temperature, and three-axis acceleration. Additionally, we establish a benchmark on the dataset using well-known features and standard machine learning methods. Preliminary results indicate that features related to physical activity, extracted from accelerometer data, are the most effective in distinguishing between unipolar and bipolar depression, achieving an accuracy of $96.77%$. Temperature-based features also showed high discriminative power, reaching an accuracy of $93.55%$. These findings highlight the potential of physiological and behavioral monitoring for improving the classification of depressive subtypes, paving the way for more tailored clinical interventions.

Problem

• Classifying unipolar and bipolar depression severity using wearable data
• Identifying biomarkers for precise depression subtype diagnosis
• Evaluating physiological and behavioral signals for depression classification

Innovation

• Wearable devices monitor depression biomarkers continuously
• Machine learning classifies unipolar and bipolar depression
• Physical activity and temperature features achieve high accuracy