EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating Agentic Artificial Intelligence to Automate International Classification of Diseases, Tenth Revision, Medical Coding

Kitti Akkhawatthanakun, Lalita Narupiyakul, Konlakorn Wongpatikaseree, Narit Hnoohom, Chakkrit Termritthikun, Paisarn Muneesawang

Informatics · 04.03.2026 · 13 (3) · 39

DOI: 10.3390/informatics13030039 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Informatics, online erschienen am 04.03.2026. Verfasst von Kitti Akkhawatthanakun und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Reinventing University Funding (2024) from the Office of the Permanent Secretary, Ministry of Higher Education, Science, Research and Innovation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automating ICD-10 coding from discharge summaries remains demanding because coders analyze clinical narratives while justifying decisions. This study compares three automation patterns: PLM-ICD as a standalone deep learning system emitting 15 codes per case, LLM-only generation with full autonomy, and a hybrid approach where PLM-ICD drafts candidates for an agentic LLM audit to accept or reject. All strategies were evaluated on 19,801 MIMIC-IV summaries using four LLMs spanning compact (Qwen2.5-3B-Instruct, Llama-3.2-3B-Instruct, Phi-4-mini-instruct) to large-scale (Sonnet-4.5). Precision guided evaluation because coders still supply any missing diagnoses. PLM-ICD alone reached 55.8% precision while always surfacing 15 suggestions. LLM-only generation lagged severely (1.5–34.6% precision) and produced inconsistent output sizes. The agentic audit delivered the best trade-off: compact LLMs reviewed the 15 candidates, discarded weak evidence, and returned 2–8 high-confidence codes. Llama-3.2-3B-Instruct, for example, improved from 1.5% as a generator to 55.1% as a verifier while trimming false positives by 73%. These results show that positioning LLMs as quality controllers, rather than primary generators, yields reliable support for clinical coding teams, while formal recall/F1 reporting remains future work for fully autonomous implementations.

Förderung

  • Reinventing University Funding (2024) from the Office of the Permanent Secretary, Ministry of Higher Education, Science, Research and Innovation

Zitieren

APA

Akkhawatthanakun, K., Narupiyakul, L., Wongpatikaseree, K., Hnoohom, N., Termritthikun, C., & Muneesawang, P. (2026). Integrating Agentic Artificial Intelligence to Automate International Classification of Diseases, Tenth Revision, Medical Coding. Informatics, 13(3), 39. https://doi.org/10.3390/informatics13030039

Vancouver

Akkhawatthanakun K, Narupiyakul L, Wongpatikaseree K, Hnoohom N, Termritthikun C, Muneesawang P. Integrating Agentic Artificial Intelligence to Automate International Classification of Diseases, Tenth Revision, Medical Coding. Informatics. 2026;13(3):39. doi:10.3390/informatics13030039

BibTeX
@article{Akkhawatthanakun2026,
  author = {Akkhawatthanakun, Kitti and Narupiyakul, Lalita and Wongpatikaseree, Konlakorn and Hnoohom, Narit and Termritthikun, Chakkrit and Muneesawang, Paisarn},
  title = {Integrating Agentic Artificial Intelligence to Automate International Classification of Diseases, Tenth Revision, Medical Coding},
  journal = {Informatics},
  year = {2026},
  volume = {13},
  number = {3},
  pages = {39},
  doi = {10.3390/informatics13030039}
}
Kostenlos starten →