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 typeObservational
Enrollment90 (estimated)
Ages19 Years and up
SexAll
SponsorSeoul National University Hospital (other)
Locations1 site (Seoul, Jongno)
Trial IDNCT06380049 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

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.

View on ClinicalTrials.gov →

Conditions: Stroke, Fall, Predict model, Machin leanning, Electromyography

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.