Multimodal Sensor Dataset for Monitoring Older Adults Post Lower-Limb Fractures in Community Settings

2025-01-23

AI Summary

Elderly patients with lower-limb fractures face challenges in dynamically monitoring mobility limitations, social isolation, and functional decline during home-based rehabilitation. Method: We introduce MAISON-LLF—the first multimodal home-rehabilitation dataset tailored to community-dwelling older adults living alone—comprising synchronized 24-hour physiological and behavioral data from smartphone IMUs, smartwatch PPG/ACC sensors, infrared motion detectors, piezoelectric sleep mattresses, and clinical assessments, collected longitudinally over eight weeks (560 days) from ten participants. We propose a suite of risk-prediction models (SVM, XGBoost, LSTM, CNN) integrating heterogeneous sensor and clinical data within a real-world community setting. Results: Our models achieve early identification of social isolation and functional decline risk with AUCs of 0.82–0.89. We publicly release the dataset and baseline code, addressing critical gaps in both data resources and analytical methodologies for dynamic geriatric fracture rehabilitation assessment.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Lower-Limb Fractures (LLF) are a major health concern for older adults, often leading to reduced mobility and prolonged recovery, potentially impairing daily activities and independence. During recovery, older adults frequently face social isolation and functional decline, complicating rehabilitation and adversely affecting physical and mental health. Multi-modal sensor platforms that continuously collect data and analyze it using machine-learning algorithms can remotely monitor this population and infer health outcomes. They can also alert clinicians to individuals at risk of isolation and decline. This paper presents a new publicly available multi-modal sensor dataset, MAISON-LLF, collected from older adults recovering from LLF in community settings. The dataset includes data from smartphone and smartwatch sensors, motion detectors, sleep-tracking mattresses, and clinical questionnaires on isolation and decline. The dataset was collected from ten older adults living alone at home for eight weeks each, totaling 560 days of 24-hour sensor data. For technical validation, supervised machine-learning and deep-learning models were developed using the sensor and clinical questionnaire data, providing a foundational comparison for the research community.

Problem

• Geriatric rehabilitation
• Lower limb fracture
• Remote healthcare monitoring

Innovation

• MAISON-LLF dataset
• multisource information
• elderly rehabilitation monitoring