Predicting fall risk in stroke patients using machine learning on multi-sensor EMG data
Official title: Development and Validation of a Machine Learning-based Model to Predict a High-risk Group for Falls Using Multi-sensor Signals in Stroke Patients
Run by Seoul National University Hospital · NCT06380049 · Data updated 2026-11-12
This project tests whether a machine-learning model that analyzes EMG sensor signals can tell which stroke patients are at high risk of falling.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 19 Years and up |
| Sex | All |
| Enrollment | 90 (estimated) |
| Sponsor | Seoul National University Hospital Academic / other |
| Locations | 1 site (Seoul, Jongno) |
| Status | Recruiting |
| Started | May 20, 2024 |
| Main results expected | March 12, 2025 |
| Study ends | April 28, 2026 |
| Registry record updated | June 2, 2025 |
| Trial ID | NCT06380049 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults aged 19 or older within three months of a first stroke with lower-extremity weakness (MMT ≤ 4) who can follow commands are the intended participants.
✕Probably not a fit
Patients with recurrent stroke, other major neurological disorders (e.g., Parkinson's), severe cognitive impairment, serious comorbidities, or implanted electronic devices are excluded and are unlikely to benefit from this validation.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This prospective, multicenter, open-label effort collects lower-limb EMG signals from 80 recent stroke patients and 10 healthy adults while they perform standardized movements. Features extracted from the multi-sensor recordings will train and validate a machine-learning model to classify patients as high or low fall risk. The model's sensitivity and specificity will be compared against conventional clinical tools such as the Berg Balance Scale. The goal is a confirmatory validation of an EMG-based predictive tool suitable for clinical use.
Why it matters
Potential benefit: If successful, the model could identify high-risk stroke survivors earlier so clinicians can target fall-prevention interventions and potentially reduce fall-related injuries.
How similar studies have gone: Previous work using wearable sensors and machine learning has shown promise for fall-risk prediction, but multicenter EMG-based confirmatory validation in early post-stroke patients remains relatively novel.
Who can join: the full rules
Show full inclusion / exclusion criteria
Stroke Participants Inclusion Criteria: * 19 years and older * the onset of the stroke is less than 3months ago * Lower extremity weakness due to stroke (MMT =\< 4 grade) * Cognitive ability to follow commands Exclusion Criteria: * stroke recurrence * other neurological abnormalities (e.g. parkinson's disease). * severely impaired cognition * serious and complex medical conditions(e.g. active cancer) * cardiac pacemaker or other implanted electronic system Health Participants Inclusion Criteria: * 19 years and older * Individuals who fully understand the necessity of the study and have voluntarily consented to participate as subjects Exclusion Criteria: * other neurological abnormalities (e.g. parkinson's disease). * severely impaired cognition * serious and complex medical conditions(e.g. active cancer) * cardiac pacemaker or other implanted electronic system
Where it's running
-
Seoul National University Hospital
Seoul, Jongno, South Korea Recruiting
Study contacts
- Principal investigator: Woo Hyung Lee, prof — Seoul National University Hospital
- Study coordinator: JungHyun Kim, prof
- Email: kiking0@naver.com
- Phone: 82+1088632341
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Deep phenotyping to explore recovery in young adults after stroke
This project will test whether a detailed health and sample-collection approach (deep phenotyping) is practical and acceptable for people aged 18–55 who have had a stroke.
-
Stem cell therapy for chronic stroke recovery
This study is testing whether using a patient's own stem cells can help people with long-term stroke recovery feel better and improve their daily functioning.
-
AI-based tools to help diagnose, treat and predict stroke outcomes across multiple hospitals
This study tests AI-powered tools on real-world stroke patients to see if they can improve pre-hospital triage, diagnosis, and outcome prediction while data stay securely within each hospital.
-
Web-based therapy using action observation and mirror therapy for arm weakness after stroke
This trial tests whether a mobile telerehabilitation app delivering action observation therapy (AOT) alone or combined AOT with mirror therapy (AOT-MT) can improve upper limb function in people with subacute stroke.
-
Remote Ischaemic Conditioning for Fatigue After Stroke 2
Aat least 12 weeks after stroke, adults with post-stroke fatigue will try a simple hand-arm cuff treatment at home to see if it helps reduce fatigue.
-
Dual-task balance training plus computer-based cognitive training after stroke
In adults who recently had a stroke, the study tests whether adding computerized cognitive exercises to balance training improves balance and other recovery outcomes.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.