A Reliable Fall Detection System Based on Analyzing the Physical Activities of Older Adults Living in Long-Term Care Facilities

Fall detection systems are designed in view to reduce the serious consequences of falls thanks to the early automatic detection that enables a timely medical intervention. The majority of the state-of-the-art fall detection systems are based on machine learning (ML). For training and performance evaluation, they use some datasets that are collected following predefined simulation protocols i.e. subjects are asked to perform different types of activities and to repeat them several times. Apart from the quality of simulating the activities, protocol-based data collection results in big differences between the distribution of the activities of daily living (ADLs) in these datasets in comparison with the actual distribution in real life. In this work, we first show the effects of this problem on the sensitivity of the ML algorithms and on the interpretability of the reported specificity. Then, we propose a reliable design of an ML-based fall detection system that aims at discriminating falls from the ambiguous ADLs. The latter are extracted from 400 days of recorded activities of older adults experiencing their daily life. The proposed system can be used in neck- and wrist-worn fall detectors. In addition, it is invariant to the rotation of the wearable device. The proposed system shows 100% of sensitivity while it generates an average of one false positive every 25 days for the neck-worn device and an average of one false positive every 3 days for the wrist-worn device.

Automated summary

Fall detection systems aim to reduce the serious consequences of falls through early automatic detection, but existing systems may have differences in data distribution compared to real-life scenarios, impacting the performance of ML algorithms. A reliable design has been proposed to differentiate falls from activities of daily living.