ActiTect: A Generalizable Machine Learning Pipeline for REM Sleep Behavior Disorder Screening through Standardized Actigraphy
Researchers have developed ActiTect, an open-source machine learning pipeline designed to screen for REM sleep behavior disorder (RBD) using actigraphy data. This tool aims to standardize and automate the analysis of abnormal nocturnal movements captured by wrist-worn devices, which are crucial for early detection of neurodegenerative diseases like Parkinson's. ActiTect demonstrated strong and generalizable performance across multiple cohorts, with AUROC scores ranging from 0.84 to 0.95, indicating its potential for widespread clinical adoption and validation. AI
IMPACT This tool could significantly improve early detection of neurodegenerative diseases by enabling large-scale screening via wearable devices.