Metraipolis › archive › dc_7f66129df4af

Unmentioned Checklist Findings Change How Reinforcement Learning Appears to Improve Chest Radiograph Report Checking — arXiv:2610.05425

Source
arXiv
Original
https://arxiv.org/abs/2610.05425
License (as archived)
CC0-1.0
Archived
2026-10-06T05:28:51.344Z
SHA-256 of the archived text
31b66a6f97462e3c23abcabb3fa968a1c716c7c601767205d2a8e1eb9eb1705d
Stable URL of this page
https://metraipolis.com/documento/dc_7f66129df4af

How to cite

Unmentioned Checklist Findings Change How Reinforcement Learning Appears to Improve Chest Radiograph Report Checking — arXiv:2610.05425 — arXiv, https://arxiv.org/abs/2610.05425 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f66129df4af (Metraipolis archive dc_7f66129df4af, sha256 31b66a6f97462e3c23abcabb3fa968a1c716c7c601767205d2a8e1eb9eb1705d)
BibTeX
@misc{dc7f66129df4af,
  title = {Unmentioned Checklist Findings Change How Reinforcement Learning Appears to Improve Chest Radiograph Report Checking — arXiv:2610.05425},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05425},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f66129df4af; sha256 31b66a6f97462e3c23abcabb3fa968a1c716c7c601767205d2a8e1eb9eb1705d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05425. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated checks of radiology reports may rely on AI-generated checklists that leave findings unmentioned. We used reinforcement learning to train a vision-language model to fill in a 12-finding checklist from a chest radiograph without seeing the sentence under test; a separate checking model judged the sentence from the checklist. On held-out patients, a rule-based check and an independent medical checker, neither used in training, measured discrimination gains (Youden index) of 12.6% and 11.8%; only the rule-based check met the prespecified false-alarm criterion. Switching to the training format, which fixes finding order and enters unmentioned findings as absent, raised the training checker's measured gain and lowered the independent checker's, a prespecified comparison that yielded 6.2% (95% interval 2.0% to 10.5%) and, post hoc on held-out patients, 7.7%. Across 8 checking models, acceptance of a label-consistent negative statement about an unmentioned finding ranged from 1.0% to 97.0%. Labels were report-derived, not radiologist-adjudicated.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05425 — 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 2026-10-06T05:24:20.440Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).