Reproduce “Agentic discovery of blood biomarker from distilled private health records” 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
Seffi Cohen, Liat Antwarg Friedman, Amir Anisman, Ruth Johnson, Michelle M. Li, Ayush Noori, Ben Reis, Ran Balicer and 2 more
The authors train a private-cohort scorer to rank blood-count expressions by predicted case-control discrimination. It exports weights, not patient records, for outside agents to prioritize expressions. Across 13 disease searches, selected expressions improved on starting expressions by a median 4.18 AUC points, including an unstable estimate from three familial Mediterranean fever cases; results support prioritization, not clinical benefit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.