Evidence Hub

Surface Electromyography Combined with Artificial Intelligence in Predicting Neuromuscular Falls in the Elderly: A Narrative Review of Present Applications and Future Perspectives

Yuandan Liao, Gang Tan, Hui Zhang

Healthcare, 2025

4 citations

Abstract

Background: Falls among the elderly are a major public health concern, leading to increased disability and mortality. Traditional protective measures are important, but early detection and prevention are equally critical. Surface electromyography (sEMG) signals, which assess muscle electrical activity, can indicate a fall risk by detecting muscle weakness or instability. Objective: This narrative review synthesizes the research progress of sEMG in predicting neuromuscular falls among the elderly. Our goal is to explore the innovative application and development potential of the integration of sEMG and artificial intelligence (AI) in fall prevention among the elderly. Methods: A systematic search of PubMed, IEEE Xplore, and Web of Science (2013–2023) was conducted using the following keywords: artificial intelligence, wearable, sEMG, neuromuscular, and fall prediction. The inclusion criteria prioritized studies integrating sEMG with AI for elderly fall risk assessments, while non-empirical or non-English studies were excluded. Results: AI algorithms hold significant potential in medical applications, and studies on predicting neuromuscular falls in the elderly using sEMG signals have made notable progress. However, limitations include a reliance on simulated data, a lack of standardized models, sensor inaccuracies, and a focus on prediction rather than prevention. To address these challenges, this study proposes collecting authentic sEMG signals from elderly individuals with…

Read the paper

Related studies

Go deeper in Evidence Hub

Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.

Open this study Sign up free