Sep 2026· Studies in Health Technology and Informatics· Vol 340, pp.
129-137
· 0 citations
Medicine
TL;DR
Combining domain-specific embedding-based retrieval with LLM-based reranking substantially improves MCN performance compared to a standalone LLM approach, and supports robust semantic matching between German clinical expressions and standardized terminology concepts, facilitating structured representation and enabling more effective secondary use of clinical text.
Abstract
INTRODUCTION
Clinical narratives in electronic health records frequently contain clinical expressions describing medical conditions. Their free-text format limits interoperability and automated processing. Medical concept normalization (MCN) addresses this challenge by mapping textual expressions to standardized terminology concepts, such as those from SNOMED CT. However, clinical language is characterized by abbreviations, spelling variants, and short forms, which complicate automatic normalization.
Methods
In this work, we investigate the MCN of short German clinical expressions to SNOMED CT by comparing a direct large language model (LLM)-based normalization approach using GPT-5.4 with a hybrid retrieval approach that combines a medBERT.de bi-encoder for embedding-based retrieval and retrieval-augmented generation (RAG) reranking using GPT-5 variants.
Results
The LLM-only baseline achieves a Recall@1 of 0.235, Recall@3 of 0.297, and Recall@5 of 0.303. In contrast, the embedding-based bi-encoder retrieval approach achieves a Recall@1 of 0.681, a Recall@3 of 0.783, and a Recall@5 of 0.812. Incorporating RAG-based LLM reranking further improves Recall@1 to 0.771, while Recall@3 and Recall@5 reach 0.809 and 0.812, respectively.
Conclusion
The results demonstrate that combining domain-specific embedding-based retrieval with LLM-based reranking substantially improves MCN performance compared to a standalone LLM approach. This hybrid strategy supports robust semantic matching between German clinical expressions and standardized terminology concepts, facilitating structured representation and enabling more effective secondary use of clinical text.
A benchmark-guided, scalable framework for automated medical terminology standardization that accepts heterogeneous short medical expressions without manual input pre-processing and automatically performs text refinement, semantic retrieval and terminology mapping to standardized concepts and vocabulary codes is establ...
Anshu Verma, Abhijay, Manan Vangani et al.· bioRxiv· 0 citations
The findings suggest that conventional readability metrics should be extended with domain-specific measures to more accurately assess comprehensibility in medical texts and that large Language Models show strong potential to enhance the accessibility of clinical documentation for patients.
M. Teichmann, Pelin Özkara Menekseoglu, Julian Schwarz et al.· Studies in Health Technology...· 0 citations
It is demonstrated that structured knowledge enrichment is critical for effective LLM-based multilingual concept normalization, while surface-form sensitivity and positional biases remain important challenges for fully automated clinical pipelines.
H. Rouhizadeh, A. Yazdani, Boya Zhang et al.· npj Digital Medicine· 0 citations
Systematized Nomenclature of Medicine–Clinical Terminology (SNOMED CT) is the principal international standard for semantic interoperability of clinical information, but mapping free-text clinical narratives to SNOMED CT concepts remains labor-intensive. We developed a large language model agent system for mapping bili...
H. Lee, Seon-Ah Choi, Duyeon Kim et al.· Journal of medical systems· 0 citations
Current LLMs do not achieve inter-rater reliability levels comparable to medical professionals in clinical information extraction from ENT documentation, suggesting they are best suited for initial extraction with human verification rather than autonomous operation.
L. Barrett, N. Joshi, A. S. North et al.· medRxiv· 0 citations
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT scientists developed a training method to generate models that simulate the effects of human activities on climate much more quickly than other approaches.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.