Association between wrist-worn actigraphy and the MDS-UPDRS Parkinson’s disease rating scale through machine learning: an exploratory study - Takeaways - MDSpire

Association between wrist-worn actigraphy and the MDS-UPDRS Parkinson’s disease rating scale through machine learning: an exploratory study

  • By

  • Gent Ymeri

  • Sara Caramaschi

  • Alban Haton

  • Carl Magnus Olsson

  • Myrthe Wassenburg

  • Per Svenningsson

  • Dario Salvi

  • July 13, 2026

Share

  • 1

    Wrist-worn actigraphy can provide continuous monitoring of motor behavior in Parkinson's disease, potentially capturing fluctuations missed in clinical assessments.

  • 2

    The study utilized GeneActiv devices to collect accelerometer data over 28 days, deriving various feature representations for analysis.

  • 3

    Estimation performance for MDS-UPDRS scores varied, with the best results for Part IV using non-embedding features, achieving a correlation of 0.83.

  • 4

    The combined feature set performed best for MDS-UPDRS Part I, Part III, and total scores, while non-embedding features excelled for Part II.

  • 5

    Results indicate that wearable-derived measures may complement clinical assessments of Parkinson's disease severity, particularly for motor complications.

Original Source(s)

Association between wrist-worn actigraphy and the MDS-UPDRS Parkinson’s disease rating scale through machine learning: an exploratory study

  • by Gent Ymeri, Sara Caramaschi, Alban Haton, Carl Magnus Olsson, Myrthe Wassenburg, Per Svenningsson, Dario Salvi

  • July 13, 2026

Related Content

Effect of transcranial direct current stimulation on psychomotor skill acquisition during laparoscopic training: a randomized controlled trial

Case Report: Albumin combined with plasma exchange in the treatment of refractory thrombotic thrombocytopenic purpura

Multifactorial stratified analysis of two novel metabolism-related indices for predicting stroke in mild cognitive impairment