Related Experiment Video
Updated: May 7, 2026
13:45
Hybrid µCT-FMT imaging and image analysis
Published on: June 4, 2015
13.7K
Development and Evaluation of SNOMED CT Automated Mapping Tool: Advancing Terminology Standardization and Semantic
Youngsun Park1, Hannah Kang1, Jiwon Kim1
1Kakao Healthcare Corp, Seongnam-si, Republic of Korea.
JMIR Medical Informatics
|March 9, 2026
Summary
This study introduces an automated tool using large language models (LLMs) to streamline SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms) mapping and concept authoring, significantly improving efficiency and accuracy in healthcare data standardization.
Area of Science:
- Medical Informatics
- Computational Linguistics
- Health Data Science
Background:
- Healthcare data fragmentation hinders secondary use due to non-standardized terminologies.
- Manual SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms) mapping is labor-intensive and inconsistent.
- Automated solutions are crucial for scalable clinical terminology standardization.
Purpose of the Study:
- Develop a large language model (LLM)-assisted tool for efficient SNOMED CT terminology mapping and concept authoring.
- Enable seamless, standardized data integration across multi-institutional clinical datasets.
- Improve semantic interoperability in healthcare data.
Main Methods:
- A pipeline involving local term preprocessing, LLM-based vector similarity mapping, and iterative enrichment.
- Utilized GPT-4o for translation and semantic representation.
- Structured postcoordination for new concept authoring, with quantitative evaluation of efficiency and quality.
Main Results:
- Achieved high top-5 accuracy for diagnostic (up to 98.7%) and surgical procedural (up to 99.2%) mapping.
- Reduced manual mapping rates by 30% and overall workload by up to 90%.
- Decreased mapping/creation time by ~75% and errors (duplicates, rule violations) by 83% and 72%, respectively.
Conclusions:
- An automated, LLM-assisted SNOMED CT mapping tool significantly enhances efficiency, accuracy, and concept quality.
- Future work includes leveraging ontology structures, knowledge graphs, and automated rule enforcement for robust standardization.
- Addressing technical integration and translation quality are key limitations for broader adoption.
Related Concept Videos
01:20Anatomical Terminology
22.2K
Knowledge of anatomy is essential to understand human biology and medicine. Anatomists and health care professionals use standard terminology to describe the human body with more precision and no ambiguity. Anatomical terms have mostly Greek and Latin-derived roots. Because these languages are rarely used in conversation, the meaning of words remains the same. Each term is made up of a root in between the prefixes and suffixes. The root of a term often refers to an organ, tissue, or condition,...
22.2K
01:10Computed Tomography
7.6K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
7.6K