Reproduce “On Aligning Prediction Models with Clinical Experiential Learning: A Prostate Cancer Case Study” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jacqueline J. Vallon, William Overman, Wanqiao Xu, Neil Panjwani, Xi Ling, Sushmita Vij, Hilary P. Bagshaw, John T. Leppert and 6 more
The authors study whether clinician-defined monotonic constraints can change prostate-cancer survival model behavior without reducing predictive performance. They impose decreasing relationships for nine features in XGBoost and compare constrained with unconstrained models. Both achieve an AUC-ROC of 0.77 in one full-training-data illustration, and performance curves largely overlap across tested training sizes; this retrospective case study does not establish clinical safety or deployment readiness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.