biostudies-literatureUnknown9(1)Anjos de Almeida V<h4>Objectives</h4>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.<h4>Materials and methods</h4>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.<h4>Results</h4>Twenty-eightJAMIA openooag017https://www.ebi.ac.uk/biostudies/studies/S-EPMC12924630biostudies-literatureLarge language models as medical code selectors: a benchmark using the International Classification of Primary Care.PMC12924630de Camargo VGomez-Bravo RFernandez Lopez LFinger Mvan der Haring EAnjos de Almeida Vvan Boven KfalseLarge language models as medical code selectors: a benchmark using the International Classification of Primary Care.<h4>Objectives</h4>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.<h4>Materials and methods</h4>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.<h4>Results</h4>Twenty-eight2026-01-01T00:00:00Z2026 Feb2026-07-09T12:08:56.656Z2026-07-09T11:10:12.375ZS-EPMC129246304172741410.1093/jamiaopen/ooag017