Predicting fall risk in stroke patients using machine learning on multi-sensor EMG data
Development and Validation of a Machine Learning-based Model to Predict a High-risk Group for Falls Using Multi-sensor Signals in Stroke Patients
Seoul National University Hospital · NCT06380049
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 |
|---|---|
| Enrollment | 90 (estimated) |
| Ages | 19 Years and up |
| Sex | All |
| Sponsor | Seoul National University Hospital (other) |
| Locations | 1 site (Seoul, Jongno) |
| Trial ID | NCT06380049 on ClinicalTrials.gov |
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.
Who should consider this trial
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.
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.
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 performed: 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.
Eligibility criteria
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 this trial is running
Seoul, Jongno
- 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
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Stroke, Fall, Predict model, Machin leanning, Electromyography