Objective: To evaluate a wearable IMU-derived PD Similarity Index (PSI), a continuous monotonic score designed to position individuals along the spectrum from healthy controls (HC) through idiopathic rapid eye movement (REM) sleep behavior disorder (iRBD) to Parkinson disease (PD) using rater-independent inference from gait signals, with clinical ratings used only for anchoring and validation.

Background: iRBD is a major prodromal marker of PD. However, objective quantification of motor changes across the prodromal-to-manifest disease continuum remains challenging. Conventional clinical scales such as the Hoehn and Yahr (H&Y) stage and the Unified Parkinson’s Disease Rating Scale part III (UPDRS-III) are rater-based, episodic, and may be insensitive to subtle prodromal motor alterations. We hypothesized that a continuous machine-learning score derived from wearable gait data could capture the disease continuum more objectively

Method: We analyzed 301 participants: HC (n=102), iRBD (n=46), mild PD (H&Y 1–2, n=102), and moderate PD (H&Y 2.5–3, n=51). Participants performed a multi-speed 10-meter walking task (slow, preferred, and fast) while wearing shoe-outsole IMU sensors. A three-model cascade (HC vs PD; mild vs moderate PD; HC vs iRBD) was integrated into a single PSI score. The PSI was designed to enforce monotonic ordering across disease stages and anchored to group-level H&Y stage means.

Results: PSI increased monotonically across groups (mean±SD): HC 0.102±0.143, iRBD 0.358±0.276, mild PD 0.667±0.153, and moderate PD 0.890±0.184. Group differences were significant (Kruskal–Wallis H=231.3, p<0.001), and all pairwise comparisons remained significant after Bonferroni correction (p<0.001). PSI correlated strongly with H&Y stage (r=0.772, p<0.001) and UPDRS-III scores (ρ=0.793, p<0.001). Within the iRBD group, PSI showed substantial heterogeneity, revealing HC-like, iRBD-typical, and PD-like profiles.

Conclusion: A brief wearable IMU-based gait assessment can generate a continuous severity score aligned with clinical staging across the PD spectrum. PSI captures prodromal heterogeneity within iRBD and may serve as a promising digital biomarker for disease progression monitoring and studies targeting the prodromal-to-manifest transition.

References: 1. Postuma RB, et al. MDS clinical diagnostic criteria for Parkinson’s disease. Mov Disord. 2015;30(12):1591-1601.
2. Postuma RB, et al. Risk and predictors of dementia and parkinsonism in idiopathic REM sleep behaviour disorder: a multicentre study. Brain. 2019;142(3):744-759.
3. Maetzler W, Domingos J, Srulijes K, Ferreira JJ, Bloem BR. Quantitative wearable sensors for objective assessment of Parkinson’s disease. Mov Disord. 2013;28(12):1628-1637.

« Back to 2026 International Congress

MDS Abstracts - https://www.mdsabstracts.org/abstract/pd-similarity-index-a-wearable-gait-biomarker-capturing-the-continuum-from-irbd-to-parkinson-disease/