Longitudinal assessment of chorea in Huntington's disease using digital passive monitoring.
prospective_cohort · Level II
Where this comes from
- Record sourced from PubMed, PMID 42032152.
- Also identified by DOI 10.1038/s41746-026-02661-y.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Chorea is a hallmark of Huntington's disease (HD), yet its clinical assessment is of limited reliability, impairing our ability to sensitively evaluate its progression. We evaluated passive monitoring for estimating the two-year evolution of upper limb chorea in HD. Across four studies, 1025 participants collected smartwatch accelerometer data during their everyday life. We developed a machine learning model anchored to in-clinic upper limb chorea and trained cross-sectionally on disease-relevant features. The final model, selected using nested cross-validation, allowed estimating the longitudinal evolution of chorea. The resulting digital passive monitoring chorea score shows a progression of 0.13 points per year (95% CI: [0.08, 0.17]), and a robust sensitivity to change across studies, avoiding biases related to in-clinic measurements. High-resolution accelerometer data collected passively during daily life can improve the measurement of chorea in HD. Clinical Trial Registry Name: ClinicalTrials.gov; Study IDs: NCT03761849 registered 2018-11-30 and NCT03664804 registered 2018-09-07.