The abstract is read at the publisher; the summary is JClub's.
Passive wearable sleep and activity metrics trained into SAM-PD distinguish Parkinson’s disease from healthy controls with AUROC 0.93 and AUPRC 0.98 in a U.S. cohort.
- Why it matters: Early Parkinson’s disease involves sleep and motor changes, but scalable methods to detect disease and related dopaminergic deficit and -synuclein pathology are limited.
- What they did: The study derived sleep and activity metrics from free-living wrist accelerometry, trained a machine learning model (SAM-PD) on 133 persons with PD and 26 controls, then tested it in an independent European cohort (n = 40) using a different device.
- The result: SAM-PD generalized to Europe (AUROC 0.95; AUPRC 0.95) and, in a U.S. at-risk cohort, detected dopaminergic deficit (AUROC 0.86) and -synuclein pathology (AUROC 0.76), enabling biomarker enrichment and screening evaluation.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.