Parkinson Disease
Conditions
Keywords
artificial intelligence, MDS-UPDRS, Parkinson's disease
Brief summary
Idiopathic Parkinson's disease (PD) is a neurodegenerative disease that progressively causes both motor and non-motor symptoms. As the second most common neurodegenerative disease and most common movement disorder, it affects over 8.5 million people worldwide and 13,000 people in Hong Kong. The most classical symptoms of PD are resting tremors, rigidity of the muscles, bradykinesia (slowing of movement), and gait difficulty. Other symptoms include sleep disorders, psychiatric symptoms, cognitive impairment, and autonomic dysfunction. Its pathophysiology is marked by the loss of dopaminergic neurons and the accumulation of aggregates called Lewy bodies. The severity of PD-related motor symptoms is usually semi-quantitatively ("normal", "slight", "mild", "moderate", and "severe") evaluated by expert physicians and physiotherapists according to the Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale Part III (MDS-UPDRS III). However, the MDS-UPDRS III is semiquantitative and subjective, which might mask mild treatment effects or even provide false-positive results. Moreover, it takes significant time and effort for assessment with expected inter-observer variations. To address these issues, various artificial intelligence (AI) technologies and telemedicine approaches have been investigated for patient evaluation. However, previous studies did not incorporate items assessing rigidity and postural stability, which require physical contact as per the MDS-UPDRS III instructions. Zhu et al. explored a motor symptom machine-rating system for the complete MDS-UPDRS III. Nevertheless, they employed a depth camera and conducted the tests within a strictly controlled ideal laboratory environment. For the widespread implementation of AI-assisted rating, the RGB camera is a more accessible alternative.
Detailed description
This is a single-center, prospective, observational study designed to develop and validate an AI-based MDS-UPDRS III assessment system using RGB camera data. Participants will be recruited from Queen Elizabeth Hospital's neurology outpatient clinic. Each subject will undergo standard MDS-UPDRS III evaluation by a certified clinician or physiotherapist, alongside synchronized RGB-D video recording. The videos will be processed through a deep learning pipeline trained to estimate the MDS-UPDRS III scores. Blinded evaluations will be performed to compare AI-generated scores with ground truth clinician ratings. Statistical analysis will include inter-rater agreement metrics (e.g., ICC, Cohen's kappa), sensitivity to change, and subgroup analyses.
Interventions
OTHERObservational
clinical profile, MDS-UPDRS III, Video Recording
Sponsors
Hong Kong University of Science and Technology
The Queen Elizabeth Hospital
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to 95 Years
Healthy volunteers
No
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
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| AI-based motor assessment tool | Baseline to 3 years | AI-based motor assessment tool utilizing RGB video for reliable and objective ratings of MDS-UPDRS III motor symptoms, including rigidity and postural stability. |
| Feasibility of implementing RGB camera-based assessments | 3 years | Feasibility of implementing RGB camera-based assessments in routine clinical settings will be assessed by the proportion of assessments in which the AI system is able to generate an estimated MDS-UPDRS Part III total score based on RGB video that can be directly compared with clinician-rated MDS-UPDRS Part III scores. Patients perform standardized motor tasks under physician guidance while RGB video is recorded using a smartphone. Clinician-rated MDS-UPDRS Part III scores are used as the ground truth. Feasibility outcomes will be reported as the percentage (%) of assessments with valid AI-generated scores over a 3-year study period. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| System's effectiveness | 3 years | System effectiveness in estimating motor symptom severity will be measured by the agreement between AI-predicted and clinician-rated MDS-UPDRS Part III scores. RGB video is recorded using a smartphone while patients perform standardized motor tasks under physician supervision. Clinician-rated MDS-UPDRS Part III scores are used as the ground truth. The AI system generates predicted MDS-UPDRS Part III total scores (range 0-108, with higher scores indicating more severe motor impairment). System effectiveness will be evaluated using F1 score, correlation between predicted and clinician-rated scores, and sensitivity and specificity for the detection of clinically significant motor impairment based on predefined score thresholds. Effectiveness outcomes will be reported over a 3-year study period. |
| Patient and clinician satisfaction | baseline to 3 years | Patient satisfaction with the AI-assisted assessment system will be assessed using a study-specific questionnaire administered after completion of RGB camera-based motor tasks. Questionnaire items are rated on a Likert scale, with higher scores indicating greater satisfaction. Clinician evaluation of the AI-assisted assessment system will be assessed using a study-specific questionnaire evaluating perceived credibility, perceived effectiveness, and overall satisfaction with the system. Questionnaire items are rated on a Likert scale, with higher scores indicating more positive evaluations. Patient and clinician evaluation outcomes will be reported as mean ± standard deviation over the study period. |
| System's performance | baseline to 3 years | System performance will be measured by the accuracy and mean absolute error (MAE) of AI-predicted MDS-UPDRS Part III total scores compared with clinician-rated scores. Patients perform standardized motor tasks under physician supervision while RGB video is recorded using a smartphone. Clinician-rated MDS-UPDRS Part III scores are used as the ground truth. System performance is defined as the accuracy and MAE of AI predictions. Performance outcomes will be summarized over the study period. |
Countries
China, Hong Kong
Contacts
CONTACTQian Zhang, PhD
CONTACTHiu Yi Wong, PhD
PRINCIPAL_INVESTIGATORQian Zhang, PhD
Hong Kong University of Science and Technology
Outcome results
None listed