JMIR Publications

ABSTRACT

Background:

Little is known about whether off-the-shelf wearable sensor data can contribute to fall risk classification or complement clinical assessment tools like the Resident Assessment Instrument-Home Care (RAI-HC).

Objective:

This study aimed to: 1) investigate the similarities and differences in physical activity, heart rate, and night sleep in a sample of community-dwelling older adults with varying fall histories, using a smart wrist-worn device; and 2) create and evaluate fall risk classification models based on: i) wearable data, ii) the RAI-HC, and iii) the combination of wearable and RAI-HC data.

Methods:

A prospective, observational study was conducted among three faller groups (G0, G1, G2+) based on the number of previous falls (0, 1, ≥2 falls) in a sample of older community-dwelling adults. The wearable and RAI-HC assessment data were analyzed and utilized to create fall risk classification models, with three supervised machine learning algorithms: logistic regression, decision tree, and random forest (RF).

Results:

Of 40 participants aged 65-93, 16 (40%) had no previous falls, while 8 (20%) and 16 (40%) had experienced one and multiple (≥2) falls, respectively. Level of physical activity as measured by average daily steps was significantly different between groups (p = .036). In the three faller group classification, RF achieved the best accuracy of 70.0% using both wearable and RAI-HC data. In discriminating between G0 and G1+G2+, RF achieved the best area under the receiver operating characteristic curve of 0.816 based on wearable data only. Discrimination between G0+G1 and G2+ did not result in better classification performance than that between G0 and G1+G2+.

Conclusions:

Both wearable data and the RAI-HC assessment can contribute to fall risk classification. Future studies in fall risk assessment should consider using wearable technologies to supplement resident assessment instruments.