A two-stage positive-unlabeled learning framework that reconstructs a cleaner training set from a highly heterogeneous population, improving test accuracy while prioritizing fewer missed undiagnosed hypertension cases.
A single-center retrospective cohort study of enteric-release budesonide in Chinese patients with IgA nephropathy, using longitudinal mixed models to quantify proteinuria change while tracking kidney-function trajectories.
A concept-stage transformer framework for cfDNA methylation representation learning, extending read-level sequence context toward sample-level aggregation and prediction.
An open, structured benchmark dataset for through-silicon vias, integrating published and released measurements with simulation-derived multiphysics records for data mining, surrogate modeling and reproducible TSV design research.
