Plain-English translation of NCT06380049 on ClinicalTrials.gov ↗ · Source last updated · Translation generated · How we translate trials
Read our Stroke research guide →Researchers are developing a computer learning system that uses small sensors placed on your leg muscles to predict whether you might fall after a stroke. The sensors measure how your muscles work when you move, and the computer analyzes this information to identify who is at higher risk of falling. This new approach could catch fall risks that traditional balance tests might miss.
Falls are a major problem for stroke patients and can lead to serious injuries and setbacks in recovery. Current methods for testing fall risk rely mainly on physical exams and patient history, which don't always catch who is most at risk. This study aims to create a better, more precise tool to identify patients who need extra help preventing falls.
You likely qualify if…
You likely don't qualify if…
You will have small sensors (electrodes) placed on the muscles in your lower legs. You'll then perform some simple, standardized movements while the sensors record how your muscles are working. The researchers will collect this information and use it to train their computer model, then follow up with you to see if the model accurately predicted who had falls. The whole process is non-invasive and designed to be safe and manageable.
AI-generated summary from trial data · Jun 7, 2026 · Not medical advice
South Korea
Collaborators
Ministry of Trade, Industry & Energy, Republic of Korea
Enrollment target
~90 participants
Started
May 2024
Primary completion
March 2025
This trial's estimated completion date has passed — the record may not be fully up to date.
Age range
19 Years and older
Last updated on clinicaltrials.gov in June 2025.
Reach out to the team running this trial. Response times vary — some teams are faster than others.
Central contact
JungHyun Kim, prof
Seoul National University Hospital
Tell us you're interested and we'll help connect you with the research team. We'll walk you through what to expect first — no email needed to get started.