Movement Disorders Analysis Using a Deep Learning Approach

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.

Study Overview

• Status: Completed
• Conditions: Parkinson Disease; Parkinsonian Disorders; Hypokinesia; Parkinsonian Syndrome; Bradykinesia; Akinesia

• Study Type: Observational
• Enrollment (Actual): 50

Contacts and Locations

Study Locations

• France
  • Seine Saint Denis
    • Bobigny, Seine Saint Denis, France, 93000
      • Hospital AVICENNE

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

All patients seen by a neurologist in the department of Neurology at Avicenne Hospital (Bobigny, France) between June 2019 and December 2020 were recorded during MDS-UPDRS examination.

The investigators also included healthy volunteers on a voluntary basis.

Description

Inclusion Criteria:

• Age > 18 years

Exclusion Criteria:

• Refusal of participation

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) part III score	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	1 day

Collaborators and Investigators

• Sponsor: Hospital Avicenne
• Investigators: Principal Investigator: Clément Desjardins, MD, Hospital AVICENNE; Study Director: Bertrand Degos, MD,PhD, Hospital AVICENNE

Study record dates

Study Major Dates

• Study Start (Actual): June 1, 2019
• Primary Completion (Actual): November 18, 2020
• Study Completion (Actual): December 31, 2020

Study Registration Dates

• First Submitted: July 3, 2021
• First Submitted That Met QC Criteria: July 13, 2021
• First Posted (Actual): July 23, 2021

Study Record Updates

• Last Update Posted (Actual): July 23, 2021
• Last Update Submitted That Met QC Criteria: July 13, 2021
• Last Verified: July 1, 2021

More Information

Terms related to this study

• Keywords: Parkinson Disease; Deep Learning; Bradykinesia
• Additional Relevant MeSH Terms: Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Neurologic Manifestations; Basal Ganglia Diseases; Synucleinopathies; Neurodegenerative Diseases; Dyskinesias; Parkinson Disease; Movement Disorders; Parkinsonian Disorders; Hypokinesia
• Other Study ID Numbers: CLEA-2019-83

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No