Collaborative Management for Chronic Diseases and Depression: A Double Heterogeneity-based Multi-Task Learning Method

2025-11-20

AI Summary

Chronic comorbidities—particularly depression co-occurring with chronic diseases—exhibit dual heterogeneity: disease-level heterogeneity (inter-disease variability) and patient-level heterogeneity (inter-individual response variability), posing significant challenges for accurate, generalizable assessment. Method: We propose a Dual-Heterogeneity Multi-Task Learning (DH-MTL) framework that (i) jointly models multiple disease assessment tasks to explicitly capture inter-disease dependencies; (ii) incorporates group-level modeling to enhance generalization to new patients; (iii) adopts parameter decomposition to reduce model complexity; and (iv) constructs a Bayesian network to characterize similarity and divergence among model components. The framework integrates wearable sensor data with deep learning. Results: Evaluated on real-world clinical data, DH-MTL significantly outperforms baseline models in prediction accuracy (p < 0.01); ablation studies confirm substantial contributions from each module. This work establishes a novel paradigm for comorbidity management—interpretable, generalizable, and supportive across the full clinical continuum.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Wearable sensor technologies and deep learning are transforming healthcare management. Yet, most health sensing studies focus narrowly on physical chronic diseases. This overlooks the critical need for joint assessment of comorbid physical chronic diseases and depression, which is essential for collaborative chronic care. We conceptualize multi-disease assessment, including both physical diseases and depression, as a multi-task learning (MTL) problem, where each disease assessment is modeled as a task. This joint formulation leverages inter-disease relationships to improve accuracy, but it also introduces the challenge of double heterogeneity: chronic diseases differ in their manifestation (disease heterogeneity), and patients with the same disease show varied patterns (patient heterogeneity). To address these issues, we first adopt existing techniques and propose a base method. Given the limitations of the base method, we further propose an Advanced Double Heterogeneity-based Multi-Task Learning (ADH-MTL) method that improves the base method through three innovations: (1) group-level modeling to support new patient predictions, (2) a decomposition strategy to reduce model complexity, and (3) a Bayesian network that explicitly captures dependencies while balancing similarities and differences across model components. Empirical evaluations on real-world wearable sensor data demonstrate that ADH-MTL significantly outperforms existing baselines, and each of its innovations is shown to be effective. This study contributes to health information systems by offering a computational solution for integrated physical and mental healthcare and provides design principles for advancing collaborative chronic disease management across the pre-treatment, treatment, and post-treatment phases.

Problem

• Jointly assessing comorbid chronic diseases and depression
• Addressing double heterogeneity in disease and patient manifestations
• Developing multi-task learning for integrated healthcare management

Innovation

• Group-level modeling supports new patient predictions
• Decomposition strategy reduces model complexity
• Bayesian network captures dependencies across components