Metraipolis › archive › dc_421a1f8dddb3
Agentic discovery of blood biomarker from distilled private health records — arXiv:2610.04749
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04749
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:24:46.290Z
- SHA-256 of the archived text
e00a8a802cd9ae124bd8b86802253c3eed18c09e5b5e5efa75994aea508d20f6- Stable URL of this page
https://metraipolis.com/documento/dc_421a1f8dddb3
How to cite
Agentic discovery of blood biomarker from distilled private health records — arXiv:2610.04749 — arXiv, https://arxiv.org/abs/2610.04749 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_421a1f8dddb3 (Metraipolis archive dc_421a1f8dddb3, sha256 e00a8a802cd9ae124bd8b86802253c3eed18c09e5b5e5efa75994aea508d20f6)
BibTeX
@misc{dc421a1f8dddb3,
title = {Agentic discovery of blood biomarker from distilled private health records — arXiv:2610.04749},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04749},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_421a1f8dddb3; sha256 e00a8a802cd9ae124bd8b86802253c3eed18c09e5b5e5efa75994aea508d20f6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04749. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Routine complete blood counts (CBCs) could yield new biomarkers, but the private records needed to evaluate candidates cannot be shared with frontier language model agents that excel at discovery. We distilled the evidence held in the Clalit Health Services panel of over 5.4 million patients into a released scoring tool: for each of 13 immune-mediated diseases, a graph attention network was trained inside the data boundary to predict the case-control AUC of candidate CBC expressions, and only the trained weights were released. The tool grounds an agent's propose-score-refine loop in real-world data without exposing any patient data. In external validation, agent-discovered expressions improved on their literature-seeded starting points by a median of 4.18 AUC percentage points, and across three independent cohorts, reranking the candidates of three frontier research tools improved on their first choices in most comparisons, with gains that varied by cohort. The released scorer supports privacy-preserving biomarker hypothesis generation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.04749 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:05.511Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).