Application of Machine Learning Tools in the Evaluation of the Risk of Falls in the Elderly: An Integrative Review

Abstract

This integrative review seeks to present an overview of the application of machine learning (ML) tools in the assessment of the risk of falls in the elderly. We searched the CAPES and IEEE Xplore Periodical databases, articles published in English, Portuguese and Spanish, in the last eleven years. Thirteen articles were selected. Most studies use data from sensors to classify the risk of falling and compare the results obtained with results of clinical tests or history of falls. Some studies carried out the selection of characteristics of the collected signals. Research that compared CI tools and conventional scales pointed to a certain superiority of the former. In the selected articles, Multilayer Perceptron (MLP) neural networks were the most explored. It was possible to observe that the ML tools can be applied in the assessment of the risk of falls in the elderly as a classification resource, showing good results.