Metraipolis › archive › dc_a3087cd7f156

Certify, Report, or Refuse: Harm-Constrained Conformal Prediction for Clinical Actions — arXiv:2611.12662

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.12662
License (as archived)
CC0-1.0
Archived
2026-11-10T18:44:13.806Z
SHA-256 of the archived text
f8209432797cceff9f0e65936640fb09f721087a4a5723cff9087b034c7bc472
Stable URL of this page
https://metraipolis.com/documento/dc_a3087cd7f156

How to cite

Certify, Report, or Refuse: Harm-Constrained Conformal Prediction for Clinical Actions — arXiv:2611.12662 — arXiv (en), https://arxiv.org/abs/2611.12662 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3087cd7f156 (Metraipolis archive dc_a3087cd7f156, sha256 f8209432797cceff9f0e65936640fb09f721087a4a5723cff9087b034c7bc472)
BibTeX
@misc{dca3087cd7f156,
  title = {Certify, Report, or Refuse: Harm-Constrained Conformal Prediction for Clinical Actions — arXiv:2611.12662},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12662},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3087cd7f156; sha256 f8209432797cceff9f0e65936640fb09f721087a4a5723cff9087b034c7bc472},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12662. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Routing a melanoma case to routine follow-up is a serious action error that diagnostic coverage alone does not rule out. We present Harm-Constrained Risk-Optimal Conformal Prediction (HC-ROCP), a training-free framework that uses frozen classifier probabilities and adds a harm penalty when choosing prediction sets and actions. We test the resulting policies on disjoint calibration splits with multiplicity adjustment. HC-ROCP certifies supported claims, reports descriptive fallback policies, and refuses unsupported subgroup claims. We evaluate these outputs retrospectively on COVID-19 radiographs, ISIC 2019 dermoscopy, and EyePACS-to-APTOS retinopathy transfer. Across ten calibration seeds, HC-ROCP reduces COVID-19 severe-action errors from the exact risk-optimal baseline's 4.68\% to 0.54\%. At a 5\% budget, global claims are certified for COVID-19 and ISIC, but the rare squamous-cell-carcinoma claim is refused. At 1\%, all settings receive descriptive reports. For each budget, we also report the minimum severe-case count needed to pass the global harm gate with zero errors, providing a starting point for further data collection.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.12662 — 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 2026-11-10T18:37:37.701Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).