Detecting Sensitive Mobility Features for Parkinson's Disease Stages Via Machine Learning

Anat Mirelman*, Mor Ben Or Frank, Michal Melamed, Lena Granovsky, Alice Nieuwboer, Lynn Rochester, Silvia Del Din, Laura Avanzino, Elisa Pelosin, Bastiaan R. Bloem, Ugo Della Croce, Andrea Cereatti, Paolo Bonato, Richard Camicioli, Theresa Ellis, Jamie L. Hamilton, Chris J. Hass, Quincy J. Almeida, Maidan Inbal, Avner ThalerJulia Shirvan, Jesse M. Cedarbaum, Nir Giladi, Jeffrey M. Hausdorff

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

52 Scopus citations

Abstract

Background: It is not clear how specific gait measures reflect disease severity across the disease spectrum in Parkinson's disease (PD). Objective: To identify the gait and mobility measures that are most sensitive and reflective of PD motor stages and determine the optimal sensor location in each disease stage. Methods: Cross-sectional wearable-sensor records were collected in 332 patients with PD (Hoehn and Yahr scale I−III) and 100 age-matched healthy controls. Sensors were adhered to the participant's lower back, bilateral ankles, and wrists. Study participants walked in a ~15-meter corridor for 1 minute under two walking conditions: (1) preferred, usual walking speed and (2) walking while engaging in a cognitive task (dual-task). A subgroup (n = 303, 67% PD) also performed the Timed Up and Go test. Multiple machine-learning feature selection and classification algorithms were applied to discriminate between controls and PD and between the different PD severity stages. Results: High discriminatory values were found between motor disease stages with mean sensitivity in the range 72%–83%, specificity 69%–80%, and area under the curve (AUC) 0.76–0.90. Measures from upper-limb sensors best discriminated controls from early PD, turning measures obtained from the trunk sensor were prominent in mid-stage PD, and stride timing and regularity were discriminative in more advanced stages. Conclusions: Applying machine-learning to multiple, wearable-derived features reveals that different measures of gait and mobility are associated with and discriminate distinct stages of PD. These disparate feature sets can augment the objective monitoring of disease progression and may be useful for cohort selection and power analyses in clinical trials of PD.

Original languageEnglish
Pages (from-to)2144-2155
Number of pages12
JournalMovement Disorders
Volume36
Issue number9
DOIs
StatePublished - Sep 2021

Funding

FundersFunder number
Biogen Ltd
Stichting Parkinson Funds
Verily Life Sciences, Horizon 2020, the Topsector Life Sciences and Health
Michael J. Fox Foundation for Parkinson's Research
Roche
Biogen
AbbVie
GE Healthcare
Seventh Framework ProgrammeV‐TIME‐278169
Seventh Framework Programme
UCB
Parkinson's Foundation
European Federation of Pharmaceutical Industries and Associations
European Commission
Nederlandse Organisatie voor Wetenschappelijk Onderzoek
Hersenstichting
Innovative Medicines Initiative820820
Innovative Medicines Initiative

    Keywords

    • Parkinson's disease
    • accelerometer
    • gait
    • machine learning
    • wearables

    Fingerprint

    Dive into the research topics of 'Detecting Sensitive Mobility Features for Parkinson's Disease Stages Via Machine Learning'. Together they form a unique fingerprint.

    Cite this