Leveraging Large Language Models with Retrieval-Augmented Generation for Semantic Mapping of Clinical Data Lakes to SNOMED CT

Mapping local clinical concepts to standardized terminologies such as SNOMED CT is essential for semantic interoperability and large-scale research, but manual mapping is labor-intensive and difficult to scale. We report a preliminary evaluation of a hybrid approach combining retrieval-augmented generation (RAG) and a large language model (LLM) to support the mapping of hospital datalake concepts to SNOMED CT. Using a dataset of 2,768 concepts annotated by the SIMED across five semantic categories (organisms, healthcare locations, laboratory samples, allergies, and clinical assessments), the pipeline consistently outperformed retrieval-only baselines. For organism concepts, strict accuracy reached 92.8% (weighted 98.0%, top-3 96.7%), while allergy and assessment concepts achieved 84.7% and 72.1% strict accuracy, respectively. Healthcare location and laboratory sample concepts remained more challenging, with strict accuracies of 57.5% and 57.1%, and weighted accuracy varied strongly depending on frequency distributions. Overall, strict accuracy was 72.8%, weighted accuracy 76.1%, and top-3 accuracy 83.1%. These findings suggest that combining RAG with LLM-based reasoning can reduce expert workload while maintaining accuracy, representing a step toward scalable, AI-assisted semantic interoperability in healthcare. The approach relies on a retrieval-augmented generation pipeline using embedding-based candidate retrieval followed by LLM-based disambiguation (GPT-4.1-mini), and is evaluated against a retrieval-only baseline. By improving semantic consistency in clinical data lakes, it indirectly supports interoperable access to patient-level health data.