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

TL;DR

This paper introduces MAISON-LLF, a comprehensive multimodal sensor dataset collected from older adults recovering from lower-limb fractures, enabling remote health monitoring and analysis of recovery and social factors.

Contribution

It provides a new publicly available multimodal sensor dataset for older adults post-LLF recovery, including sensor data and clinical questionnaires, along with baseline machine learning validation.

Findings

Sensor data collected over 560 days from 10 participants.

Supervised and deep learning models demonstrate potential for health outcome inference.

Dataset supports research on social isolation and functional decline detection.

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.