Code Like Humans: A Multi-Agent Solution for Medical Coding
Andreas Geert Motzfeldt, Joakim Edin, Casper L. Christensen, Christian Hardmeier, Lars Maal{\o}e, Anna Rogers
Abstract
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).
BibTeX
@inproceedings{emnlp2025_codelikehumansam,
title = {Code Like Humans: A Multi-Agent Solution for Medical Coding},
author = {Andreas Geert Motzfeldt and Joakim Edin and Casper L. Christensen and Christian Hardmeier and Lars Maal{\o}e and Anna Rogers},
booktitle = {EMNLP 2025},
year = {2025}
}