Objectives: Large language models (LLMs) have shown promise in creating clinical codelists for research purposes, a time-consuming task requiring expert domain knowledge. Here, we evaluate the performance and assess failure modes of a retrieval augmented generation (RAG) approach to creating clinical codelists for the large and complex medical terminology used by the Clinical Practice Research Datalink (CPRD). Materials & Methods: We set up a RAG system using a database of word embeddings of the medical terminology that we created using a general-purpose word embedding model (gemini-embedding). We developed 7 reference codelists presenting different challenges and tagged required and optional codes. We ran 168 evaluations (7 codelists, 2 different database subsets, 4 models, 3 epochs each). Scoring was based on the omission of required codes, and inclusion of irrelevant codes. We used model-grading (i.e., grading by another LLM with the reference codelists provided as context) to evaluate the output codelists (a score of 0% being all incorrect and 100% being all correct). Results: We saw varying accuracy across models and codelists, with Gemini 3 Pro (Score 43%) generally performing better than Claude Sonnet 4.6 (36%), Gemini 3 Flash, and OpenAI GPT 5.2 performing worst (14%). Models performed better with shorter target codelists (e.g., Eosinophilic esophagitis with four codes, and Hidradenitis suppurativa with 14 codes). For example, all models consistently failed to produce a complete Wrist fracture codelist (with 214 required codes). We further present evaluation summaries, and failure mode evaluations produced by parsing LLM chat logs. Discussion: Besides demonstrating that a single-shot RAG approach is currently not suitable for codelist generation, we demonstrate failure modes including hallucinations, retrieval failures and generation failures where retrieved codes are not used. Conclusions: Our findings suggest that while RAG systems using current frontier LLMs may create correct clinical codelists in some cases, they still struggle with large and complex terminologies and codelists with a large number of codes. The failure mode we highlight can inform the creation of future workflows to avoid failures.

AB and JP are employees of GSK. None of the authors report any conflicts of interest in regard to the findings of this manuscript.

This work was funded by a pump-priming grant awarded to Julian Matthewman by the faculty of Epidemiology and Population Health at the London School of Hygiene & Tropical Medicine.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

All evaluations are included in the study repository at https://github.com/julianmatthewman/llmcodelists_public and can be browsed with an evaluation viewer at https://julianmatthewman.github.io/llmcodelists_public/.

https://github.com/julianmatthewman/llmcodelists_public