JMIR Publications

ABSTRACT

Background:

Primary care in Thailand often uses mixed Thai-English free-text documentation for diagnoses and clinical problems limiting standardization, interoperability, and secondary data use. Interface terminologies like Systemized Nomenclature of Medicine – Clinical Terms (SNOMED CT) can bridge this gap through the use of structured clinical data. Mapping localized interface terminology is one of the key strategies for implementing SNOMED CT in real-world clinical settings.

Objective:

To develop a Thai interface terminology mapped to SNOMED CT codes.

Methods:

Frequently used clinical terms were extracted from outpatient medical records ascertained from family, emergency, and internal medicine departments using natural language processing and expert review, resulting in a list of 2,054 Thai-specific terms. These terms were normalized and mapped to SNOMED CT through manual expert-driven and semi-automated tools. Unmapped terms were analyzed to identify mapping barriers and solutions.

Results:

Of the 2,054 Thai-specific terms, 2,011 (97.94%) were successfully mapped to 2,042 SNOMED CT concepts. Most mappings were one-to-one (1,984), with 27 terms mapped to multiple concepts, covering 1,486 unique SNOMED CT concepts. The remaining 43 unmapped terms were mostly due to culturally specific expressions or concepts not yet represented in SNOMED CT. These were categorized for potential post-coordination, exclusion, or national extension development.

Conclusions:

This study demonstrates the feasibility of developing a localized Thai interface terminology mapped to SNOMED CT codes for outpatient care. The resulting terminology enhances semantic clarity in clinical documentation and supports better interoperability, clinical decision-making, and health data analytics within Thailand’s healthcare system.