A Multimodal Nomogram Predicting the Risk of Cognitive Impairment in Parkinson Disease
Source check: Source checked. Not independent scientific confirmation.
Finding: A multimodal LASSO-Cox model estimated 3-, 5- and 8-year cognitive-impairment risk among Parkinson disease participants initially classified as cognitively normal. In 1,188 participants, 457 developed impairment; nested cross-validation C-index was 0.736 and optimism-corrected C-index 0.733. The model was internally validated in one selected cohort and has no external transport validation. This shares the broad task of Parkinson-related cognitive impairment with an existing diagnostic study, but is a distinct longitudinal prognostic risk model.
Technology: LASSO-Cox feature selection and prognostic modeling identify predictors of cognitive impairment.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- LASSO-Cox feature selection and prognostic modeling identify predictors of cognitive impairment.
- Test and result
- Nested cross-validation, bootstrap optimism correction, calibration and held-out time-dependent AUC analyses were reported.
- Limitation / still unknown
- Internal validation in one cohort only; external transportability and clinical benefit have not been established. It is related to active record 2022-05-accuracy-of-machine-learning-using-the-montreal-cognitive-assessment-f, which concerns diagnosis from MoCA rather than longitudinal risk prediction.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://onlinelibrary.wiley.com/doi/10.1002/mdc3.70884
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary full text, including Methods and Results; first result-bearing version and date verified from primary record..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.