Deep Representation Learning for Multi-functional Degradation Modeling of Community-dwelling Aging Population

TL;DR

This paper addresses the challenge of modeling aging-related, multidimensional degradation across physical and cognitive domains by proposing a deep representation learning framework that captures latent heterogeneity in elderly trajectories. The method combines LSTM-based trajectory modeling with clustering of latent embeddings to identify heterogeneous subpopulations and predict multidimensional degradation scores. Case study on the Health and Retirement Study demonstrates superior predictive accuracy and reveals cluster-specific patterns in healthcare utilization, suggesting targeted resource allocation and personalized care strategies. The work advances aging analytics by moving beyond univariate, homogeneous models toward trajectory-aware, multi-function degradation modeling with practical implications for healthcare planning.

Abstract

As the aging population grows, particularly for the baby boomer generation, the United States is witnessing a significant increase in the elderly population experiencing multifunctional disabilities. These disabilities, stemming from a variety of chronic diseases, injuries, and impairments, present a complex challenge due to their multidimensional nature, encompassing both physical and cognitive aspects. Traditional methods often use univariate regression-based methods to model and predict single degradation conditions and assume population homogeneity, which is inadequate to address the complexity and diversity of aging-related degradation. This study introduces a novel framework for multi-functional degradation modeling that captures the multidimensional (e.g., physical and cognitive) and heterogeneous nature of elderly disabilities. Utilizing deep learning, our approach predicts health degradation scores and uncovers latent heterogeneity from elderly health histories, offering both efficient estimation and explainable insights into the diverse effects and causes of aging-related degradation. A real-case study demonstrates the effectiveness and marks a pivotal contribution to accurately modeling the intricate dynamics of elderly degradation, and addresses the healthcare challenges in the aging population.

Figures (4)

• Figure 1: Baseline vs Proposed Models
• Figure 2: Occurrence Ratios of health services utilizations regarding health degradations in ADL and COG
• Figure 3: Heterogeneous Clusters from multi-functional degradation embeddins
• Figure 4: Occurrence ratios of health service utilizations for heterogeneous degradation in ADL and COG