Movement Disorders Analysis Using a Deep Learning Approach
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Bradykinesia
- Sponsor
- Hospital Avicenne
- Enrollment
- 50
- Locations
- 1
- Primary Endpoint
- Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) part III score
- Status
- Completed
- Last Updated
- 4 years ago
Overview
Brief Summary
Bradykinesia is a key parkinsonian feature yet subjectively assessed by the MDS-UPDRS score, making reproducible measurements and follow-up challenging.
In a Movement Disorder Unit, the investigators acquired a large database of videos showing parkinsonian patients performing Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) part III protocols.
Using a Deep Learning approach on these videos, the investigators aimed to develop a tool to compute an objective score of bradykinesia from the three upper limb tests described in the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) part III.
Investigators
Desjardins Clement
Neurology Resident
Hospital Avicenne
Eligibility Criteria
Inclusion Criteria
- •Age \> 18 years
Exclusion Criteria
- •Refusal of participation
Outcomes
Primary Outcomes
Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) part III score
Time Frame: 1 day
Automatic Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) part III for hand bradykinesia including the three following specific tasks (finger tapping, hand movements and pronation-supination movements of hand). The minimum score is 0. The maximum score is 12 Higher scores mean wors outcome