Using Consumer-grade Wearable Devices for Fall Risk Evaluation and Alerts

Overview

Creation and use of a smartphone application for older adults to assess the participants' risk of fall. Phase 1: Compare the accuracy and validity of accelerometer and gyroscopic data from a smartphone and gold-standard, wearable sensors gathered during balance and gait activities. Phase 2: Develop a model that integrates wearable sensor data and individual characteristics, such as age, medical conditions, exercises, previous falls, fear of falls, along with gait and balance outcome measurements, to evaluate fall risk in older adults. Phase 3: Integrate the computational model in the design of a mobile app for wearable devices for older adults to self-administer fall risk assessments and provide individualized risk of fall information.

Falls are prevalent among older adults and can cause serious problems. Falls in older adults can cause serious injuries that negatively impact their quality of life and can be life-threatening. Evaluating an individual's risk of fall is, typically, an important first step in preventing falls. Fall risk is commonly evaluated through clinical measurement scales, such as the Tinetti Performance Oriented Mobility Assessment (POMA) and Berg Balance Scale (BBS). Physical measurements using instruments, such as inertial measurement units (IMUs; accelerometers and gyroscopes) and force plates, can also be employed to evaluate an individual's fall risk. However, both clinical and instrumented measures are often only collected in clinical or research settings, thus making them less accessible to older adults and their care providers. Additionally, fall risk can only be evaluated infrequently, which can be a problem as health and environmental changes in the life of an older adult can necessitate more frequent measurement of fall risk. The research team proposes consumer-grade wearable devices (e.g. smartphones and watches) to fill the gap in current fall risk assessment. This approach has great potential as quick, simple, timely, and frequent measures of fall risk can help to reduce fall risk in older adults. The proposed research investigates older adults' gait and balance to identify potential links between wearable sensor measurements and fall risk. The types and granularity of data on physical activities that can be collected by consumer-grade wearable devices are more limited than using research-grade measurement. The investigators plan to use research-grade sensors to validate measures of gait and balance via consumer-grade wearable devices. Signal processing algorithms will be employed to extract the critical patterns from wearable device measurements that could be used for regular fall risk monitoring. A machine-learning computational model will also be developed to correlate the wearable data to clinical scales. This data will be used to design and build a mobile app for older adults to self-administer the fall risk test at home. The application design will be informed by factors such as one's physical environment, health condition, fear of falls, etc. and the goal is to develop an integrated system that offers fall risk assessment and provides alerts for older adults.