Reproduce “Learning Explainable Treatment Policies with Clinician-Informed Representations: A Practical Approach” 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
Johannes O. Ferstad, Emily B. Fox, David Scheinker, Ramesh Johari
The authors evaluate policies that prioritize youth with type 1 diabetes for remote-monitoring messages under limited clinical capacity. Policies represent glucose states and message actions using raw-data or clinician-informed features, then rank patients by estimated treatment benefit. In records from 281 youth across three trials, policies beat random targeting only when both representations were clinician-informed, but remain observational estimates.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.