JMIR Publications

ABSTRACT

Background:

Clinical mobility and balance assessments identify older adults who have a high risk of falls in clinics. In the past two decades, sensors have been a popular supplement to the mobility and balance assessment to provide quantitative information and cost-effective solution in the community environment. Nonetheless, the current sensor-based balance assessment relies on manual observation or motion-specific features to identify motions of research interest.

Objective:

The objective of this study is to develop an automatic motion data analytics framework using signal data collected from inertial sensor for balance activity analysis in community-dwelling older adults.

Methods:

Fifty-nine community-dwelling older adults (19 males and 40 females; mean age = 81.86 years, SD = 6.95 years) were recruited in this study. The data were collected using a body-worn inertial measurement unit (including an accelerometer and a gyroscope) at L4 vertebrae of individual. After data pre-processing and motion detection via a convolutional long short-term memory (LSTM) neural network, one-class support vector machine (SVM), linear discriminant analysis (LDA), and k-NN were adopted to classify the high-risk individuals.

Results:

The framework developed in this study yielded mean accuracies of 87%, 86%, and 89% in detecting sit-to-stand, turning, and stand-to-sit motions, respectively. The balance assessment classification showed the accuracies of 90%, 92%, and 86% in classifying abnormal sit-to-stand, turning, and stand-to-sit motions using Tinetti-POMA-B criteria by one-class SVM and k-NN.

Conclusions:

The sensor-based approach presented in this study provided a time-effective manner with less human efforts to identify and pre-process the inertial signal, and thus enabled an efficient balance assessment tool for medical professionals. In the long run, the approach may offer a flexible solution to relieve the community’s burden of continuous health monitoring.