Large language models as medical code selectors: a benchmark using the International Classification of Primary Care.

Objectives: Medical coding structures health-care data for research, quality monitoring, and policy. This study assesses the potential of large language models (LLMs) to assign International Classification of Primary Care, 2nd edition (ICPC-2) codes using the output of a domain-specific search engine. Materials and Methods: A dataset of 437 Brazilian Portuguese clinical expressions, each annotated with ICPC-2 codes, was used. A semantic search engine (OpenAI's text-embedding-3-large) retrieved candidates from 73 563 labeled concepts. Thirty-three LLMs were prompted with each query and retrieved results to select the best-matching ICPC-2 code. Performance was evaluated using F1-score, along with token usage, cost, response time, and format adherence. Results: Twenty-eight models achieved F1-score>0.8; 10 exceeded 0.85. Top performers included gpt-4.5-preview, o3, and gemini-2.5-pro. Retriever optimization can improve performance by up to 4 points. Most models returned valid codes in the expected format, with reduced hallucinations. Smaller models (<3B parameters) struggled with formatting and input length. Conclusion: Large language models show strong potential for automating ICPC-2 coding, even without fine-tuning. This work offers a benchmark and highlights challenges, but findings are limited by dataset scope and setup. Broader, multilingual, end-to-end evaluations are needed for clinical validation.