ActiTect: A Generalizable Machine Learning Pipeline for REM Sleep Behavior Disorder Screening through Standardized Actigraphy

2025-11-07

AI Summary

Isolated rapid eye movement sleep behavior disorder (iRBD) is an early prodromal marker of α-synucleinopathies, yet large-scale, non-invasive screening remains urgently needed. Method: We propose an automated wrist-actigraphy–based analytical framework featuring a standardized preprocessing pipeline integrating robust signal denoising, unsupervised sleep–wake staging, and physiologically interpretable motor feature extraction, coupled with nested cross-validation for training generalizable machine learning models. Contribution/Results: Our approach enables cross-device data harmonization and reproducible multi-center modeling, with all code and workflows openly shared. Evaluated across multi-center cohorts, the model achieves AUROC of 0.84–0.94; leave-one-dataset-out validation confirms strong generalizability, and key features demonstrate high test–retest reliability. This provides a robust, scalable, and clinically translatable technical pathway for population-level screening in the preclinical phase of neurodegenerative diseases.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Neuro-Symbolic Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Isolated rapid eye movement sleep behavior disorder (iRBD) is a major prodromal marker of $alpha$-synucleinopathies, often preceding the clinical onset of Parkinson's disease, dementia with Lewy bodies, or multiple system atrophy. While wrist-worn actimeters hold significant potential for detecting RBD in large-scale screening efforts by capturing abnormal nocturnal movements, they become inoperable without a reliable and efficient analysis pipeline. This study presents ActiTect, a fully automated, open-source machine learning tool to identify RBD from actigraphy recordings. To ensure generalizability across heterogeneous acquisition settings, our pipeline includes robust preprocessing and automated sleep-wake detection to harmonize multi-device data and extract physiologically interpretable motion features characterizing activity patterns. Model development was conducted on a cohort of 78 individuals, yielding strong discrimination under nested cross-validation (AUROC = 0.95). Generalization was confirmed on a blinded local test set (n = 31, AUROC = 0.86) and on two independent external cohorts (n = 113, AUROC = 0.84; n = 57, AUROC = 0.94). To assess real-world robustness, leave-one-dataset-out cross-validation across the internal and external cohorts demonstrated consistent performance (AUROC range = 0.84-0.89). A complementary stability analysis showed that key predictive features remained reproducible across datasets, supporting the final pooled multi-center model as a robust pre-trained resource for broader deployment. By being open-source and easy to use, our tool promotes widespread adoption and facilitates independent validation and collaborative improvements, thereby advancing the field toward a unified and generalizable RBD detection model using wearable devices.

Problem

• Developing automated pipeline for REM sleep behavior disorder screening
• Ensuring generalizability across heterogeneous actigraphy acquisition settings
• Creating open-source tool for large-scale RBD detection using wearables

Innovation

• Automated machine learning tool for RBD detection
• Robust preprocessing harmonizes multi-device data
• Open-source pipeline enables widespread adoption