Accelerometry-Derived REM Sleep Behavior Disorder Score Is Associated with Incident Parkinson’s Disease in the UK Biobank
Authors:
Preprint
Abstract
Estimating Parkinson’s disease (PD) risk years before diagnosis remains an unmet need. We applied a validated machine learning classifier for REM sleep behavior disorder (RBD) detection to 7-day wrist accelerometry data in 87,975 UK Biobank participants followed for 10 years. Participants in the highest RBD risk stratum (>99 th percentile) had an approximately fivefold increased hazard of incident PD compared with the lowest-risk group (0–90 th percentile), with a dose-dependent relationship across the full score distribution. Among non-converters, higher RBD-classifier scores were associated with baseline cognitive deficits and greater burden of autonomic and psychiatric prodromal features. The association with incident PD remained independent of PD polygenic risk score, while RBD-classifier score and genetic risk were synergistic. The combined high-risk group achieved a positive likelihood ratio of 7.91, approximately threefold higher than questionnaire-based RBD screening. At this High-risk threshold over the 10-year horizon, the classifier showed a sensitivity of 7.4%, specificity of 99.2%, positive predictive value of 7.5%, and negative predictive value of 99.2% for incident PD (N=50,816). These findings support wrist accelerometry as a scalable, high-specificity approach for prodromal PD risk enrichment.Keywords
This publication has 63 references indexed in Scilit:
- Obstructive Sleep Apnea, Positive Airway Pressure, and Implications of Early Treatment in Parkinson DiseaseJAMA Neurology, 2026
- FDA Perspective on the Regulation of Artificial Intelligence in Health Care and BiomedicineJAMA, 2025
- Actigraphy Enables Home Screening of Rapid Eye Movement Behavior Disorder in Parkinson's DiseaseAnnals of Neurology, 2022
- Ambulatory Detection of Isolated Rapid‐Eye‐Movement Sleep Behavior Disorder Combining Actigraphy and QuestionnaireMovement Disorders, 2022
- Update of the MDS research criteria for prodromal Parkinson's diseaseMovement Disorders, 2019
- MDS research criteria for prodromal Parkinson's diseaseMovement Disorders, 2015
- Regression Modeling Strategies2015
- Meta‐analysis of early nonmotor features and risk factors for Parkinson diseaseAnnals of Neurology, 2012
- MULTIVARIABLE PROGNOSTIC MODELS: ISSUES IN DEVELOPING MODELS, EVALUATING ASSUMPTIONS AND ADEQUACY, AND MEASURING AND REDUCING ERRORSStatistics in Medicine, 1996
- Relationships between Parts A and B of the Trail Making TestJournal of Clinical Psychology, 1987