JMIR Publications

ABSTRACT

Background:

Falls and their consequences are a serious public health problem worldwide. Each year, 37.3 million falls requiring medical attention occur. Therefore, the analysis of fall risk is of great importance for prevention. Artificial intelligence, on the other hand, represents an innovative tool for creating predictive statistical models of fall risk through data analysis.

Objective:

The aim of this review was to analyze the available evidence on the applications of artificial intelligence in the analysis of data related to postural control and fall risk.

Methods:

A literature search was conducted in six databases with the inclusion criteria: (i) published within the last 5 years (from 2018 to the present); (ii) they had to apply some method of artificial intelligence; (iii) artificial intelligence analyses had to be applied to data from samples consisting of humans; (iv) the analyzed sample had to consist of individuals with independent walking with or without the assistance of external orthopedic devices.

Results:

A total of 2987 articles were obtained, of which 22 articles were finally selected. Data extraction for subsequent analysis varied in the different studies: 18 of them extracted data through tests or functional assessments, and the remaining four through existing medical records. Different artificial intelligence techniques were used throughout the articles. All the research included in the review obtained accuracy values of over 70% in the predictive models obtained through artificial intelligence.

Conclusions:

The use of artificial intelligence proves to be a valuable tool for creating predictive models of fall risk. The utilization of this tool could have a significant socio- economic impact as it enables the development of low-cost predictive models with a high level of accuracy. Clinical Trial: PROSPERO ID: CRD42023443277.