Missing predictor data increases the minimum sample size needed for stable, well-calibrated clinical prediction models, with context-specific inflation factors up to 2x, via adaptations to posterior sampling calculations.
(39) Reilly, B
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3roles
method 1polarities
use method 1representative citing papers
Simulation on GUSTO-I data shows class imbalance corrections fail to boost discrimination and impair calibration plus stability in clinical prediction models.
A fine-tuned deep learning model using systemic EHR data achieved AUROC 0.883 and PPV 0.657 for identifying glaucoma in a held-out Stanford cohort of over 20,000 patients.
citing papers explorer
-
Validating a Deep Learning Algorithm to Identify Patients with Glaucoma using Systemic Electronic Health Records
A fine-tuned deep learning model using systemic EHR data achieved AUROC 0.883 and PPV 0.657 for identifying glaucoma in a held-out Stanford cohort of over 20,000 patients.