AI-assisted MDS-UPDRS assessment in Parkinson’s disease
Official title: Artificial Intelligence-assisted MDS-UPDRS Assessment for Parkinson's Disease
Run by Hong Kong University of Science and Technology · NCT07381751 · Data updated 2026-11-12
This study tests whether an AI system can estimate Parkinson’s disease motor scores from RGB video of patients, compared with clinician ratings.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years to 95 Years |
| Sex | All |
| Enrollment | 500 (estimated) |
| Sponsor | Hong Kong University of Science and Technology Academic / other |
| Locations | 2 sites (Hong Kong and 1 other locations) |
| Status | Recruiting |
| Started | June 1, 2026 |
| Main results expected | February 28, 2029 |
| Study ends | February 28, 2029 |
| Registry record updated | July 8, 2026 |
| Trial ID | NCT07381751 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults (18+) with clinically established Parkinson’s disease who can consent and participate in video-recorded motor assessments and do not have conditions that would interfere with video evaluation.
✕Probably not a fit
Individuals without significant motor impairment changes or those unable to participate in video-recorded assessments may not benefit from AI scoring.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This is a single-center, prospective observational study conducted at Queen Elizabeth Hospital in Hong Kong to develop and validate an AI-based MDS-UPDRS Part III scoring system using synchronized RGB video data. Participants will receive standard MDS-UPDRS III assessments by a clinician or physiotherapist while being video-recorded, and the AI system will generate scores from the video. Blinded comparisons will evaluate agreement between AI-derived scores and ground-truth clinician ratings, with analyses including inter-rater reliability, sensitivity to change, and subgroup analyses. The study aims to determine if video-based AI scoring can reliably reflect motor severity in idiopathic Parkinson’s disease. Eligibility requires adults with clinically established PD who consent to video-recorded assessments and have no impairments interfering with video-based evaluation.
Why it matters
Potential benefit: If successful, the AI system could enable scalable, objective motor assessments for Parkinson’s patients, potentially reducing clinic time and enabling remote monitoring.
How similar studies have gone: Previous work in AI-driven motor assessment for PD has shown promise with good agreement to clinician scores in some settings, but broader, prospective validation remains important.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. Age ≥18 years 2. Diagnosis of "Clinically Established PD" as defined by the Movement Disorder Society Clinical Diagnostic Criteria for Parkinson's disease (MDS-PD criteria) \[12\] 3. Able to provide informed consent and willing to participate in video-recorded MDS-UPDRS Part III assessments 4. No significant visual, auditory, or musculoskeletal impairments that would interfere with video-based motor assessments Exclusion Criteria: 1. Unwillingness to be video recorded for study purposes 2. History of neurodevelopmental disorder, neurodegenerative disease other than PD, CNS infection, neuroinflammatory disease (e.g. multiple sclerosis, CNS lupus), malignancy within the last 10 years, cerebrovascular accident, HIV infection, systemic autoimmune disease, alcohol dependence or other substance use
Where it's running
-
Queen Elizabeth Hospital
Hong Kong, Hong Kong Recruiting -
Hong Kong University of Science and Technology
Hong Kong, China Not yet recruiting
Study contacts
- Principal investigator: Qian Zhang, PhD — Hong Kong University of Science and Technology
- Study coordinator: Qian Zhang, PhD
- Email: qianzh@ust.hk
- Phone: +852-23588766
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
One-day exercise test to see how brain and body react in epilepsy, cognitive disorders, Parkinson's, dementia, and related conditions
A one-day study tests how an acute bout of exercise changes brain function and bodily signals in people with certain neurological conditions compared with healthy individuals.
-
Tributyrin for PSP: a virtual, early-phase study
This study tests whether tributyrin is safe and tolerable in people with Progressive Supranuclear Palsy who are 45 or older, using virtual visits.
-
A look at why Lewy body conditions cause visual hallucinations
This study tests brain‑imaging in people with Lewy body diseases who do or don’t experience visual hallucinations, and in healthy volunteers, to see how brain networks might create these images.
-
How physical activity might help people with Parkinson’s disease who have DBS-STN implants
This study tests whether adding regular physical activity can help people with Parkinson’s who have DBS-STN stimulation by trying a structured physiotherapy approach alongside standard care.
-
Can hippotherapy improve mobility, gait, balance, and quality of life in people with Parkinson's disease?
This pilot trial tests whether adding horse-assisted therapy to standard rehab helps mobility, gait, balance, and perceived health in adults with Parkinson's disease.
-
Gut methane and Parkinson's: measuring if a probiotic helps people with Parkinson's, REM sleep behavior disorder, or cognitive concerns
This study tests whether a probiotic containing Limosilactobacillus reuteri can help people with Parkinson's disease, those at high risk for PD, and related cognitive issues by potentially improving gut methane levels and overall symptoms.
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.