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

Florian Lange; Diego L. Guarin; Esther Ademola; Dalia Mahdy; Gabriela Acevedo; Thorsten Odorfer; Joshua K. Wong; Jens Volkmann; Robert Peach; Martin Reich

doi:10.1038/s41531-025-00999-w

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

Florian Lange^*
, Diego L. Guarin
, Esther Ademola
, Dalia Mahdy
, Gabriela Acevedo
, Thorsten Odorfer
, Joshua K. Wong
, Jens Volkmann
, Robert Peach
, Martin Reich

^*Corresponding author for this work

Research output: Contribution to journal › Article › Research › peer-review

3 Citations (Scopus)

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.

Original language	English
Article number	140
Journal	npj Parkinson's Disease
Volume	11
Issue number	1
DOIs	https://doi.org/10.1038/s41531-025-00999-w
Publication status	Published - 28 May 2025
Externally published	Yes

Access to Document

10.1038/s41531-025-00999-w

Cite this

@article{ebdc7b5e558c4615a2e62cdba6ec2f42,

title = "Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson{\textquoteright}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 method offers objective, quantitative motor assessment, reducing subjectivity and enhancing reproducibility compared to traditional scales.",

author = "Florian Lange and Guarin, \{Diego L.\} and Esther Ademola and Dalia Mahdy and Gabriela Acevedo and Thorsten Odorfer and Wong, \{Joshua K.\} and Jens Volkmann and Robert Peach and Martin Reich",

note = "{\textcopyright} 2025. The Author(s).",

year = "2025",

month = may,

day = "28",

doi = "10.1038/s41531-025-00999-w",

language = "English",

volume = "11",

journal = "npj Parkinson's Disease",

issn = "2373-8057",

publisher = "Springer Nature",

number = "1",

}

TY - JOUR

T1 - Computer vision uncovers three fundamental dimensions of levodopa-responsive motor improvement in Parkinson’s disease

AU - Lange, Florian

AU - Guarin, Diego L.

AU - Ademola, Esther

AU - Mahdy, Dalia

AU - Acevedo, Gabriela

AU - Odorfer, Thorsten

AU - Wong, Joshua K.

AU - Volkmann, Jens

AU - Peach, Robert

AU - Reich, Martin

PY - 2025/5/28

Y1 - 2025/5/28

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/105006821455

U2 - 10.1038/s41531-025-00999-w

DO - 10.1038/s41531-025-00999-w

M3 - Article

C2 - 40436873

AN - SCOPUS:105006821455

SN - 2373-8057

VL - 11

JO - npj Parkinson's Disease

JF - npj Parkinson's Disease

IS - 1

M1 - 140

ER -

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

Abstract

Access to Document

Other files and links

Fingerprint

Cite this