Multimodal sensor dataset for monitoring older adults post lower limb fractures in community settings
Ali Abedi, Charlene H. Chu, Shehroz S. Khan
Abstract
Lower limb fractures (LLF) significantly impact older adults, leading to reduced mobility, prolonged recovery, and impaired independence. During recovery, older adults frequently face social isolation and functional decline, complicating rehabilitation and adversely affecting their physical and mental health. Multimodal sensor platforms that continuously collect data and analyze it using machine learning algorithms can remotely monitor this population and infer health outcomes. These platforms can also alert clinicians to individuals at risk of social isolation and functional decline. This paper presents a new publicly available multimodal sensor dataset, MAISON-LLF, collected from older adults recovering from LLF in community settings. The dataset includes data from smartphone and smartwatch sensors, motion detection sensors, sleep-tracking mattresses, and clinical questionnaires on social isolation and functional 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, machine learning algorithms were developed using the sensor and clinical questionnaire data, providing a foundational comparison for the research community.