Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s disease

Abstract We developed VisionMD, an AI computer vision platform, analyzing over 1200 clinical videos of Parkinson’s patients’ hand movements across 13 years. This large-scale, markerless analysis identified three kinematic domains (speed, consistency, timing/scale) reliably improved by levodopa. Our...

Full description

Saved in:
Bibliographic Details
Main Authors: Florian Lange, Diego L. Guarin, Esther Ademola, Dalia Mahdy, Gabriela Acevedo, Thorsten Odorfer, Joshua K. Wong, Jens Volkmann, Robert Peach, Martin Reich
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:npj Parkinson's Disease
Online Access:https://doi.org/10.1038/s41531-025-00999-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850243396851990528
author Florian Lange
Diego L. Guarin
Esther Ademola
Dalia Mahdy
Gabriela Acevedo
Thorsten Odorfer
Joshua K. Wong
Jens Volkmann
Robert Peach
Martin Reich
author_facet Florian Lange
Diego L. Guarin
Esther Ademola
Dalia Mahdy
Gabriela Acevedo
Thorsten Odorfer
Joshua K. Wong
Jens Volkmann
Robert Peach
Martin Reich
author_sort Florian Lange
collection DOAJ
description Abstract We developed VisionMD, an AI computer vision platform, analyzing over 1200 clinical videos of Parkinson’s patients’ hand movements across 13 years. This large-scale, markerless analysis identified three kinematic domains (speed, consistency, timing/scale) reliably improved by levodopa. Our method offers objective, quantitative motor assessment, reducing subjectivity and enhancing reproducibility compared to traditional scales.
format Article
id doaj-art-2b0d6d8b22aa4948905464fa1e79c7c7
institution OA Journals
issn 2373-8057
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series npj Parkinson's Disease
spelling doaj-art-2b0d6d8b22aa4948905464fa1e79c7c72025-08-20T02:00:00ZengNature Portfolionpj Parkinson's Disease2373-80572025-05-011111710.1038/s41531-025-00999-wComputer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s diseaseFlorian Lange0Diego L. Guarin1Esther Ademola2Dalia Mahdy3Gabriela Acevedo4Thorsten Odorfer5Joshua K. Wong6Jens Volkmann7Robert Peach8Martin Reich9Department of Neurology, University of WürzburgMovement Estimation and Analysis Laboratory, Department of Applied Physiology and Kinesiology, University of FloridaDepartment of Neurology, University of WürzburgDepartment of Neurology, University of WürzburgMovement Estimation and Analysis Laboratory, Department of Applied Physiology and Kinesiology, University of FloridaDepartment of Neurology, University of WürzburgFixel Institute for Neurological Disease, College of Medicine, University of FloridaDepartment of Neurology, University of WürzburgDepartment of Neurology, University of WürzburgDepartment of Neurology, University of WürzburgAbstract We developed VisionMD, an AI computer vision platform, analyzing over 1200 clinical videos of Parkinson’s patients’ hand movements across 13 years. This large-scale, markerless analysis identified three kinematic domains (speed, consistency, timing/scale) reliably improved by levodopa. Our method offers objective, quantitative motor assessment, reducing subjectivity and enhancing reproducibility compared to traditional scales.https://doi.org/10.1038/s41531-025-00999-w
spellingShingle Florian Lange
Diego L. Guarin
Esther Ademola
Dalia Mahdy
Gabriela Acevedo
Thorsten Odorfer
Joshua K. Wong
Jens Volkmann
Robert Peach
Martin Reich
Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s disease
npj Parkinson's Disease
title Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s disease
title_full Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s disease
title_fullStr Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s disease
title_full_unstemmed Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s disease
title_short Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s disease
title_sort computer vision uncovers three fundamental dimensions of levodopa responsive motor improvement in parkinson s disease
url https://doi.org/10.1038/s41531-025-00999-w
work_keys_str_mv AT florianlange computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT diegolguarin computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT estherademola computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT daliamahdy computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT gabrielaacevedo computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT thorstenodorfer computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT joshuakwong computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT jensvolkmann computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT robertpeach computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease
AT martinreich computervisionuncoversthreefundamentaldimensionsoflevodoparesponsivemotorimprovementinparkinsonsdisease