Code Like Humans: A Multi-Agent Solution for Medical Coding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Motzfeldt, Andreas, Edin, Joakim, Christensen, Casper L., Hardmeier, Christian, Maaløe, Lars, Rogers, Anna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911196740845568
author Motzfeldt, Andreas
Edin, Joakim
Christensen, Casper L.
Hardmeier, Christian
Maaløe, Lars
Rogers, Anna
author_facet Motzfeldt, Andreas
Edin, Joakim
Christensen, Casper L.
Hardmeier, Christian
Maaløe, Lars
Rogers, Anna
contents In medical coding, experts map unstructured clinical notes to alphanumeric codes for diagnoses and procedures. We introduce Code Like Humans: a new agentic framework for medical coding with large language models. It implements official coding guidelines for human experts, and it is the first solution that can support the full ICD-10 coding system (+70K labels). It achieves the best performance to date on rare diagnosis codes (fine-tuned discriminative classifiers retain an advantage for high-frequency codes, to which they are limited). Towards future work, we also contribute an analysis of system performance and identify its `blind spots' (codes that are systematically undercoded).
format Preprint
id arxiv_https___arxiv_org_abs_2509_05378
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Code Like Humans: A Multi-Agent Solution for Medical Coding
Motzfeldt, Andreas
Edin, Joakim
Christensen, Casper L.
Hardmeier, Christian
Maaløe, Lars
Rogers, Anna
Artificial Intelligence
Multiagent Systems
In medical coding, experts map unstructured clinical notes to alphanumeric codes for diagnoses and procedures. We introduce Code Like Humans: a new agentic framework for medical coding with large language models. It implements official coding guidelines for human experts, and it is the first solution that can support the full ICD-10 coding system (+70K labels). It achieves the best performance to date on rare diagnosis codes (fine-tuned discriminative classifiers retain an advantage for high-frequency codes, to which they are limited). Towards future work, we also contribute an analysis of system performance and identify its `blind spots' (codes that are systematically undercoded).
title Code Like Humans: A Multi-Agent Solution for Medical Coding
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2509.05378