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

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Organism concepts: 92.8% strict accuracy; Allergy concepts: 84.7%; Assessment concepts: 72.1%

• Primary Outcome: Overall mapping accuracy: 72.8% strict, 76.1% weighted, 83.1% top-3

• Nnt Or Sensitivity: Healthcare locations and laboratory samples showed lower performance (57.5% and 57.1% strict accuracy)

• Confidence Interval: Not reported

Clinical Application

Requires technical infrastructure for LLM deployment and expert validation workflows Highly relevant for Australian Digital Health initiatives and My Health Record interoperability requirements under SNOMED CT-AU Healthcare institutions implementing SNOMED CT standardization for clinical data lakes

Abstract

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.

References

1. 1.Ehrler, F., Singer, F., Geçer, D., Houeix, J., & Durand, E. (2026). Leveraging Large Language Models with Retrieval-Augmented Generation for Semantic Mapping of Clinical Data Lakes to SNOMED CT. Studies in Health Technology and Informatics. https://doi.org/10.3233/SHTI260288