Machine-learning multi-sensor fall risk screening for Duchenne muscular dystrophy
Quantitative Analysis of Upper Extremity Functional Movement of the Upper Extremity in Patients With Duchenne Muscular Dystrophy
This project will try machine-learning and video/sensor methods to track upper limb movement and see if they can help detect fall risk in children and young adults with Duchenne muscular dystrophy.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 30 (estimated) |
| Ages | 10 Years to 30 Years |
| Sex | All |
| Sponsor | Seoul National University Hospital Academic / other |
| Locations | 1 site (Seoul, Jongno) |
| Trial ID | NCT07015632 on ClinicalTrials.gov |
What this trial studies
This is a prospective observational study of 30 participants with genetically confirmed Duchenne muscular dystrophy who meet specific age and functional criteria. Participants will undergo clinical tests (PUL 2.0, Brooke Scale, and grip strength) and standardized video recordings at baseline, 6 months, and 12 months. Computer-vision analysis and machine-learning algorithms will be applied to the sensor and video data to quantify changes in upper-extremity function over time. The protocol includes safety monitoring, data confidentiality protections, and compensation provisions in the event of adverse effects.
Who should consider this trial
Good fit: Ideal participants are people aged >10 and <30 years with genetically confirmed DMD, Brooke Scale 2–5, and manual muscle test grade <3 for shoulder abduction who can provide informed consent and complete in-person visits and recordings.
Not a fit: Patients with Brooke Scale of 1 or 6, significant cognitive impairment that prevents participation, or who cannot or will not consent are unlikely to benefit from this protocol.
Why it matters
Potential benefit: If successful, the approach could provide more sensitive, objective ways to monitor upper-limb function and fall risk in non-ambulatory DMD patients, aiding clinical decisions and remote follow-up.
How similar studies have performed: Sensor- and machine-learning approaches have shown promising pilot results in neuromuscular and fall-risk research, but ML-based upper-limb evaluation specifically in non-ambulatory DMD remains relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. Individuals with a confirmed genetic diagnosis of Duchenne Muscular Dystrophy (DMD) 2. Age over 10 and under 30 years 3. Brooke Scale score between 2 and 5 4. Manual muscle test grade below 3 for shoulder abduction muscles Exclusion Criteria: 1. Individuals who are unable or unwilling to provide informed consent 2. Brooke Scale score of 1 or 6 3. Individuals with cognitive impairments that significantly limit their ability to participate in assessments
Where this trial is running
Seoul, Jongno
- Seoul National University Hospital — Seoul, Jongno, South Korea (Recruiting)
Study contacts
- 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.