Validity Gates Expose Limits of Longitudinal Multimodal Parkinson Disease Prediction
- 1university oh texas at austin
Abstract
Multimodal Parkinson disease models can improve internally while obscuring why patients differ and whether a gain is deployable. We separated clinical trajectories, dated biological sources, observation process and cohort-relative, age-weighted evidence for dopaminergic, injury/glial, cognitive co-pathology and lysosomal burden across 5,404 cutoffs in 1,058 Parkinsons Progression Markers Initiative participants. DaT-SPECT and MoCA history produced a small 12-month motor-change gain ({Delta}R2 = 0.015; delta MAE=-0.060) that failed prespecified magnitude and strict-calendar criteria. Continuous evidence retained overlapping support but showed no detectable predictive increment beyond raw sources. Source-aware intervals achieved 90.6% simultaneous participant coverage yet failed selective prediction, yielding ABSTAIN. In 8,000 semisynthetic experiments, the gate limited null promotion to 0.35%, detected leakage and blocked 94.75% of calendar reversals; PDBP clinical transport and multimodal eligibility failed. The framework reveals state support, stale or missing evidence, and unjustified prognostic, uncertainty or transport claims.
Related
- Prediction of cognitive impairment in Parkinson’s disease using TabPFN: an integrative analysis of clinical data, longitudinal trajectories, and lipidomics
- Prediction of Parkinson disease progression from sparse longitudinal trajectories using multiclass likelihood contrast learning
- Reliability and validity of the one-minute sit-to-stand test in Parkinson’s disease
- Migration, attrition and internal validity in longitudinal study of chronic kidney disease of unknown aetiology in Nicaragua
- A Reduced Digital Motor Assessment using Multimodal Biomarkers in Parkinson's Disease
BibTeX
@misc{tirhekar2026validity,
title = {{Validity Gates Expose Limits of Longitudinal Multimodal Parkinson Disease Prediction}},
author = {H. Tirhekar and P. Yadav and C. L. bajaj},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.23.26363849},
url = {https://www.medrxiv.org/content/10.64898/2026.09.23.26363849v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Validity Gates Expose Limits of Longitudinal Multimodal Parkinson Disease Prediction
AU - H. Tirhekar
AU - P. Yadav
AU - C. L. bajaj
PY - 2026
DA - 2026/09/23
PB - medRxiv
DO - 10.64898/2026.09.23.26363849
UR - https://www.medrxiv.org/content/10.64898/2026.09.23.26363849v1
AB - Multimodal Parkinson disease models can improve internally while obscuring why patients differ and whether a gain is deployable. We separated clinical trajectories, dated biological sources, observation process and cohort-relative, age-weighted evidence for dopaminergic, injury/glial, cognitive co-pathology and lysosomal burden across 5,404 cutoffs in 1,058 Parkinsons Progression Markers Initiative participants. DaT-SPECT and MoCA history produced a small 12-month motor-change gain ({Delta}R2 = 0.015; delta MAE=-0.060) that failed prespecified magnitude and strict-calendar criteria. Continuous evidence retained overlapping support but showed no detectable predictive increment beyond raw sources. Source-aware intervals achieved 90.6% simultaneous participant coverage yet failed selective prediction, yielding ABSTAIN. In 8,000 semisynthetic experiments, the gate limited null promotion to 0.35%, detected leakage and blocked 94.75% of calendar reversals; PDBP clinical transport and multimodal eligibility failed. The framework reveals state support, stale or missing evidence, and unjustified prognostic, uncertainty or transport claims.
ER -