Motion Sensor-Based Fall Prevention for Senior Care: A Hidden Markov Model with Generative Adversarial Network Approach

• 成果类型: Article
• 署名作者: Yu, Shuo; Chai, Yidong; Samtani, Sagar; Liu, Hongyan; Chen, Hsinchun
• 署名单位: Texas Tech University System; Texas Tech University; Hefei University of Technology; Indiana University System; Indiana University Bloomington; IU Kelley School of Business; Tsinghua University; University of Arizona
• 刊物名称: INFORMATION SYSTEMS RESEARCH
• ISSN/ISSBN: 1047-7047
• DOI: 10.1287/isre.2023.1203
• 发表日期: 2024

摘要

Whereas modern medicine has enabled humans to live longer and more robust lives, recent years have seen a significant increase in chronic care costs. The prevention of threats to mobility, such as falls, freezing of gait, and others, is critical for chronic disease management. Researchers and physicians often analyze data from wearable motion sensor-based information systems (IS) to prevent falls because of their convenience, low cost, and user privacy protection. However, prior studies on fall prevention often achieve suboptimal performance because of their limited capacities in modeling data distributions. In this study, we adopt the computational design science paradigm to develop a novel fall prevention framework, which includes the hidden Markov model with generative adversarial network (HMM-GAN) that extracts temporal and sequential patterns from sensor signals and recognizes snippet states, and a logistic regression that utilizes the snippet states and determines whether and when to trigger protective devices to prevent fall injuries. Drawing upon the HMM, deep learning, and a new expectation-maximization instantiation, the proposed framework addresses limitations of existing methods by automatically extracting features from motion sensor data, accounting for both independent and sequential information in data snippets, operating on sensor signals with varying distributions and sharp peaks and valleys, allowing lead times, and being applicable in both semisupervised and supervised modes. We evaluate the proposed fall prevention framework against prevailing fall prevention models and the HMM-GAN component against state-of-the-art sensor analytics models on selected large-scale ground truth data sets containing thousands of falls and normal activities. Through an in-depth case study, we demonstrate how the proposed framework can lead to significantly reduced potentially catastrophic falls by senior citizens and produce more than $33 million of economic benefits over competing models. Besides practical health information technology contributions, HMM-GAN offers methodological contributions to the IS knowledge base for scholars designing novel information technology artifacts for healthcare applications.