Metraipolis › archive › dc_2b97ae240d4d
CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems — arXiv:2609.30714
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30714
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:38:15.626Z
- SHA-256 of the archived text
5c0aad8af56cde1ca7004ff8e7c7cb1d85f21a2d4618642f24ad0852658008a3- Stable URL of this page
https://metraipolis.com/documento/dc_2b97ae240d4d
How to cite
CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems — arXiv:2609.30714 — arXiv (en), https://arxiv.org/abs/2609.30714 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b97ae240d4d (Metraipolis archive dc_2b97ae240d4d, sha256 5c0aad8af56cde1ca7004ff8e7c7cb1d85f21a2d4618642f24ad0852658008a3)
BibTeX
@misc{dc2b97ae240d4d,
title = {CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems — arXiv:2609.30714},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30714},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b97ae240d4d; sha256 5c0aad8af56cde1ca7004ff8e7c7cb1d85f21a2d4618642f24ad0852658008a3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30714. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic AI systems are increasingly being explored in medical imaging to improve throughput and reduce clinician workload; however, safe deployment remains challenging because autonomous errors may propagate into downstream clinical decisions. A central requirement is therefore not only strong predictive performance, but also a reliable routing mechanism that determines when the system should proceed autonomously and when a case should be escalated for further review. To address this gap, we propose CRC-Router, a risk-constrained, uncertainty-aware routing module that is applicable to both conventional medical prediction models and agentic medical AI systems. CRC-Router combines multiple complementary uncertainty signals with the predictive score to construct a per-finding routing feature vector, maps this vector to an estimated wrong-accept risk using a lightweight per-finding risk model, and then applies Conformal Risk Control (CRC) to calibrate acceptance thresholds under a user-specified risk target. Instantiated on chest X-ray multi-finding triage using the NIH ChestX-ray14 dataset, CRC-Router achieves the strongest empirical risk--coverage trade-off among the evaluated baselines, both as a standalone routing layer and as a plug-in module integrated with the state-of-the-art MedRAX agent. These results demonstrate both the effectiveness of CRC-Router in selective medical automation and its modular, model-agnostic compatibility with existing predictive and agentic medical pipelines. Code is publicly available at this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.30714 — 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 2026-10-08T01:12:14.266Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).