EUVIMEDEUVIMED entdecken
Crossref

Evaluating Open-Source LLMs for Thai Clinical Information Extraction

Somkiat Kosolsombat, Phatnattachat Chatsiraphon, Taratep Si-Aksorn, Chiabwoot Ratanavilisagul

International Journal of Advanced Computer Science and Applications · 2026 · 17 (4)

DOI: 10.14569/ijacsa.2026.0170460 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advanced Computer Science and Applications, 2026. Verfasst von Somkiat Kosolsombat und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electronic medical records (EMRs) in sports medicine contain rich clinical insights but often remain in unstructured, bilingual formats. While locally-deployed large language models (LLMs) offer a privacy-preserving solution for data extraction, their performance in handling Thai-English clinical shorthand remains under-explored. This study evaluated five open-source LLMs for extracting structured clinical data from Thai sports medicine records and assessed the reliability of human-AI collaborative annotation. Mistral-7B, Qwen2.5-7B, Gemma2-9B, LLaMA3.1-8B, and Typhoon2-3.1 were deployed locally. We evaluated the extraction of four clinical fields against a ground truth of 444 records. A standardized JSON schema was utilized to ensure data interoperability. Inter-annotator agreement (IAA) was measured using Cohen’s kappa on a 100-record sample. Mistral-7B achieved the highest F1-score (92.2%), followed by Qwen2.5-7B (91.9%). Typhoon2-3.1 underperformed (32.9%) due to bilingual format mismatches and difficulties in shorthand normalization. IAA for treatment was moderate (kappa=0.43), whereas diagnosis showed near-zero agreement (kappa=-0.04) due to non-standardized institutional shorthand. Locally-deployed LLMs can effectively transform unstructured bilingual EMRs into structured JSON formats, ensuring data privacy and readiness for clinical analytics. However, the lack of standardized clinical coding in Thai EMRs remains a significant barrier. Future digital health initiatives should integrate LLMs with standardized terminologies like ICD-11 to enhance data reliability.

Zitieren

APA

Kosolsombat, S., Chatsiraphon, P., Si-Aksorn, T., & Ratanavilisagul, C. (2026). Evaluating Open-Source LLMs for Thai Clinical Information Extraction. International Journal of Advanced Computer Science and Applications, 17(4). https://doi.org/10.14569/ijacsa.2026.0170460

Vancouver

Kosolsombat S, Chatsiraphon P, Si-Aksorn T, Ratanavilisagul C. Evaluating Open-Source LLMs for Thai Clinical Information Extraction. International Journal of Advanced Computer Science and Applications. 2026;17(4). doi:10.14569/ijacsa.2026.0170460

BibTeX
@article{Kosolsombat2026,
  author = {Kosolsombat, Somkiat and Chatsiraphon, Phatnattachat and Si-Aksorn, Taratep and Ratanavilisagul, Chiabwoot},
  title = {Evaluating Open-Source LLMs for Thai Clinical Information Extraction},
  journal = {International Journal of Advanced Computer Science and Applications},
  year = {2026},
  volume = {17},
  number = {4},
  doi = {10.14569/ijacsa.2026.0170460}
}
Kostenlos starten →