Metraipolis › archive › dc_96a05cb85527
Decomposing Error and Style in Automated Clinical Coding — arXiv:2609.24877
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24877
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:50:14.824Z
- SHA-256 of the archived text
81c762d1a221773939ad0a6cf4ac038037711251f913722a6cebdfd8d868ec08- Stable URL of this page
https://metraipolis.com/documento/dc_96a05cb85527
How to cite
Decomposing Error and Style in Automated Clinical Coding — arXiv:2609.24877 — arXiv (en), https://arxiv.org/abs/2609.24877 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96a05cb85527 (Metraipolis archive dc_96a05cb85527, sha256 81c762d1a221773939ad0a6cf4ac038037711251f913722a6cebdfd8d868ec08)
BibTeX
@misc{dc96a05cb85527,
title = {Decomposing Error and Style in Automated Clinical Coding — arXiv:2609.24877},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24877},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96a05cb85527; sha256 81c762d1a221773939ad0a6cf4ac038037711251f913722a6cebdfd8d868ec08},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24877. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In automated clinical coding, where the label space spans tens of thousands of diagnosis and procedure codes, models are currently evaluated against a single gold annotation, treating any deviation as error. But we find when two teams code the same 110 ACI-Bench encounters, they agree on only 73% of codes (Jaccard similarity) for the same note; even after an independent clinical audit removes erroneous codes, agreement rises only to 77%. Is that gap error or something systematic? We model the systematic component as coding style $\psi$, a coder- or site-specific policy over what to code and how much to document, and recast coding as $p(\mathrm{code}\mid\mathrm{note},\psi)$, estimating $\psi$ with a 10-dimension rubric. If style were noise, conditioning on it would do nothing. Instead, across five datasets a model conditioned with a data-matching style raises ICD F1 by up to 26 points and an extreme mismatched one lowers it by up to 21. Four prompt based coding methods spanning 39-49 F1 converge to 52-56 once style is supplied (All p<0.05). Much of what single-gold evaluation charges to model error is recoverable, unmodeled style.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.24877 — 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 2026-10-09T06:48:45.066Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).