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

2025/09/04 by Andreas Geert Motzfeldt, Motzfeldt, Andreas, Joakim Edin +9
Health Professions · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Medical Coding and Health Information #Multiagent Systems (cs.MA)

paper · pdf · doi:10.48550/arxiv.2509.05378

openalex publication_date 2025/09/04 · openalex created_date 2025/10/11 · openalex updated_date 2026/07/28

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).

Citations

• The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
• Reasoning Models Don't Always Say What They Think
• Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
• One ruler to measure them all: Benchmarking multilingual long-context language models
• s1: Simple test-time scaling
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• One Thousand and One Pairs: A "novel" challenge for long-context language models
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• Long-context LLMs Struggle with Long In-context Learning
• Efficient Memory Management for Large Language Model Serving with PagedAttention
• MDACE: MIMIC Documents Annotated with Code Evidence
• Self-Refine: Iterative Refinement with Self-Feedback
• Multi-label Few-shot ICD Coding as Autoregressive Generation with Prompt
• Automated Clinical Coding: What, Why, and Where We Are?
• Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding
• Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machines
• Towards BERT-based Automatic ICD Coding: Limitations and Opportunities
• Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation
• Problems and Barriers during the Process of Clinical Coding: a Focus Group Study of Coders’ Perceptions
• ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network
• Explainable Prediction of Medical Codes from Clinical Text
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Exploring LLM Multi-Agents for ICD Coding
• Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning
• Automated clinical coding using off-the-shelf large language models
• MedCodER: A Generative AI Assistant for Medical Coding
• Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machines