Automatic and Efficient Fall Risk Assessment Based on Machine Learning

Abstract

Automating fall risk assessment, in an efficient, non-invasive manner, specifically in the elderly population, serves as an efficient means for implementing wide screening of individuals for fall risk and determining their need for participation in fall prevention programs. We present an automated and efficient system for fall risk assessment based on a multi-depth camera human motion tracking system, which captures patients performing the well-known and validated Berg Balance Scale (BBS). Trained machine learning classifiers predict the patient’s 14 scores of the BBS by extracting spatio-temporal features from the captured human motion records. Additionally, we used machine learning tools to develop fall risk predictors that enable reducing the number of BBS tasks required to assess fall risk, from 14 to 4–6 tasks, without compromising the quality and accuracy of the BBS assessment. The reduced battery, termed Efficient-BBS (E-BBS), can be performed by physiotherapists in a traditional setting or deployed using our automated system, allowing an efficient and effective BBS evaluation. We report on a pilot study, run in a major hospital, including accuracy and statistical evaluations. We show the accuracy and confidence levels of the E-BBS, as well as the average number of BBS tasks required to reach the accuracy thresholds. The trained E-BBS system was shown to reduce the number of tasks in the BBS test by approximately 50% while maintaining 97% accuracy. The presented approach enables a wide screening of individuals for fall risk in a manner that does not require significant time or resources from the medical community. Furthermore, the technology and machine learning algorithms can be implemented on other batteries of medical tests and evaluations.

Using machine learning to modify and enhance the daily living questionnaire

“…To allow an adaptive testing protocol, we follow a CAT scheme. 27 Our approach is based on a novel machine learning-based CAT algorithm 28 we term ML-CAT. The algorithm iteratively selects the next DLQ question to be administered to the subject based on the subject's responses.…”

Providing an Approach for Early Prediction of Fall in Human Activities Based on Wearable Sensor Data and the Use of Deep Learning Algorithms

“…There are several general approaches, including threshold-based and machine learning algorithms. Of course, machine learning algorithms have become the mainstream algorithms for crash detection systems in recent years [9,16,32].…”

Preventing falls: the use of machine learning for the prediction of future falls in individuals without history of fall

“…The studies of Speiser et al [50], Eichler et al [62], Bargiotas et al [48,57,59], Su et al [60], Liu et al [63] also used shallow learning classifiers and most of them the Random forest (RF) [64] that, similar to the work of Audiffren et al [47], aggregates the decision rules of several decision trees, to evaluate the risk of falling. Su et al [60] proposed a more direct predictive modeling with encouraging results, reporting the importance of every feature in evaluating risk.…”