2604.00864 Leakage-Safe Cross-Cohort Alzheimer’s Blood Transcriptomic Prediction on Open Data: Consistent Permutation Nulls, AMP-AD Feature Ablations, and Sensitivity Analyses
Cross-cohort Alzheimer’s disease (AD) blood transcriptomic prediction is sensitive to cohort shift and can be misinterpreted without strict evaluation controls. We present an open reproducible study on GEO cohorts GSE63060 and GSE63061 with three design principles: leakage-safe target holdout evaluation, consistent permutation-null reporting, and explicit biological feature ablations using open AMP-AD Agora nominated targets.