The abstract is read at the publisher; the summary is JClub's.
Clinical measures predict next-year incident falls in Parkinson’s disease with moderate discrimination, with AUROC 0.704 in PPMI and 0.630 in UPenn.
- Why it matters: Falls are common in Parkinson’s disease, and clinicians need models that generalize beyond a single cohort to identify patients at risk for the coming year.
- What they did: Incident models were built in PPMI using 773 visit-pairs and externally validated in UPenn using 589 visit-pairs, using MDS-UPDRS Part III, MoCA, and GDS.
- The result: In UPenn, incident fall risk rose from 7.1% to 18.5% across low- to high-risk strata, while exploratory imaging/fluid biomarkers added only modest discrimination in PPMI and not reliably in external validation.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.