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).
@article{arxiv.2509.05378,
title = {Code Like Humans: A Multi-Agent Solution for Medical Coding},
author = {Andreas Motzfeldt and Joakim Edin and Casper L. Christensen and Christian Hardmeier and Lars Maaløe and Anna Rogers},
journal= {arXiv preprint arXiv:2509.05378},
year = {2025}
}