View in EDS

Translating Natural Language Questions into SNOMED Expression Constraint Language.

Saved in:
Bibliographic Details
Title: Translating Natural Language Questions into SNOMED Expression Constraint Language.
Authors: Ngo H; The Australian E-Health Research Centre, CSIRO.
Source: Studies in health technology and informatics [Stud Health Technol Inform] 2025 Nov 12; Vol. 333, pp. 58-63.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: IOS Press Country of Publication: Netherlands NLM ID: 9214582 Publication Model: Print Cited Medium: Internet ISSN: 1879-8365 (Electronic) Linking ISSN: 09269630 NLM ISO Abbreviation: Stud Health Technol Inform Subsets: MEDLINE
Imprint Name(s): Original Publication: Amsterdam ; Washington, DC : IOS Press, 1991-
MeSH Terms: Natural Language Processing* , Systematized Nomenclature of Medicine* , Translating*, Humans
Abstract: The SNOMED Expression Constraint Language (ECL) is a powerful but complex tool for querying clinical concepts within SNOMED CT, playing a critical role in clinical decision support, data analysis, and healthcare interoperability. However, its steep learning curve - requiring both syntactic expertise and in-depth knowledge of SNOMED CT's coding system - creates significant challenges for non-specialists. To address this issue, a novel approach is proposed that leverages state-of-the-art Large Language Models (LLMs) to translate natural language questions into ECL queries. The model is designed to perform bidirectional tasks: generating ECL queries from user questions and providing natural language explanations for ECL queries, making the language more accessible and easier to understand. This work represents the first research effort to tackle this specific translation challenge, supported by the development of custom datasets and a novel pipeline that integrates multiple AI agents. Evaluation results demonstrate that the proposed model achieves 83.78% accuracy, highlighting the significant potential of LLMs for translating natural language questions into SNOMED ECL.
Contributed Indexing: Keywords: SNOMED CT; expression constraint language (ECL); large language model (LLM); natural language processing (NLP)
Entry Date(s): Date Created: 20251114 Date Completed: 20251114 Latest Revision: 20251114
Update Code: 20251114
DOI: 10.3233/SHTI251576
PMID: 41235493
Database: MEDLINE
Description
Abstract:The SNOMED Expression Constraint Language (ECL) is a powerful but complex tool for querying clinical concepts within SNOMED CT, playing a critical role in clinical decision support, data analysis, and healthcare interoperability. However, its steep learning curve - requiring both syntactic expertise and in-depth knowledge of SNOMED CT's coding system - creates significant challenges for non-specialists. To address this issue, a novel approach is proposed that leverages state-of-the-art Large Language Models (LLMs) to translate natural language questions into ECL queries. The model is designed to perform bidirectional tasks: generating ECL queries from user questions and providing natural language explanations for ECL queries, making the language more accessible and easier to understand. This work represents the first research effort to tackle this specific translation challenge, supported by the development of custom datasets and a novel pipeline that integrates multiple AI agents. Evaluation results demonstrate that the proposed model achieves 83.78% accuracy, highlighting the significant potential of LLMs for translating natural language questions into SNOMED ECL.
ISSN:1879-8365
DOI:10.3233/SHTI251576