Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Drug Nomenclature01:17

Drug Nomenclature

3.6K
During the development of a new pharmaceutical, the manufacturer initially assigns a code name to the drug. Once approved, the drug receives a United States Adopted Name (USAN)—a generic, nonproprietary designation. Upon being listed in the United States Pharmacopeia, this nonproprietary name becomes the drug's official name. Additionally, the manufacturer assigns a proprietary name or trademark, which serves as the brand name under which the drug is marketed. It is worth noting that...
3.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Development of a predictive score for hypothermia risk during continuous kidney replacement therapy in critically ill patients.

Renal failure·2026
Same author

Out-of-hospital cardiac arrest in three EMS centers in northern and central Thailand: a mixed-methods call for a national data infrastructure.

BMC emergency medicine·2026
Same author

Intention to Receive the TAK-003 Dengue Vaccine and Associated Factors Among Adults in Rural Northern Thailand.

Vaccines·2026
Same author

Attitude and Environmental Factors Associated With Successful E-Cigarette Quitting Among Secondary School Students: A Cross-Sectional Observational Study.

Journal of primary care & community health·2026
Same author

A Temporal Validation Study of Diagnostic Prediction Models for the Screening of Elevated Low-Density and Non-High-Density Lipoprotein Cholesterol.

Journal of clinical medicine·2025
Same author

Machine Learning Models for Frailty Classification of Older Adults in Northern Thailand: Model Development and Validation Study.

JMIR aging·2025

Related Experiment Video

Updated: Mar 22, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.8K

Ontology-Based Medication Named Entity Recognition Using Pretrained Transformer Models From a Thai Hospital: Model

Natthanaphop Isaradech1,2, Wachiranun Sirikul2,3,4, Stefan Schulz5

  • 1Environmental and Occupational Medicine Excellence Center, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand.

JMIR Formative Research
|March 20, 2026
PubMed
Summary
This summary is machine-generated.

This study developed a named entity recognition (NER) framework using transformer models to extract medication information from Thai hospital records. ClinicalBERT achieved the highest performance, demonstrating potential for improved healthcare data standardization.

Keywords:
annotationsdeep learningelectronic medical prescriptionsinformation extractionknowledge representationnamed entity recognitionnatural language processingontology

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.4K

Related Experiment Videos

Last Updated: Mar 22, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.8K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.4K

Area of Science:

  • Natural Language Processing
  • Clinical Informatics
  • Health Data Science

Background:

  • Extracting medication data from Thai hospital records is challenging due to mixed Thai-English terminology and narrative notes.
  • Named Entity Recognition (NER) is crucial for clinical information extraction (IE), enabling tasks like medical concept normalization and relation extraction.
  • This research focuses on building a robust NER framework for medication information extraction using ontology-based annotation and transformer models.

Purpose of the Study:

  • To evaluate the performance of five fine-tuned pretrained transformer models (BioClinicalBERT, ClinicalBERT, PubMedBERT, MultilingualBERT, ThaiBERT) for structured medication information extraction.
  • To assess the models' ability to extract key medication entities from unstructured Thai hospital discharge summaries.
  • To identify the most effective transformer model for this specific clinical information extraction task.

Main Methods:

  • Collected 90 Thai hospital discharge summaries from Maharaj Nakhon Chiang Mai Hospital.
  • Annotated documents by physicians using guidelines based on SNOMED-CT and HL7 FHIR standards.
  • Fine-tuned and evaluated 5 BERT-based transformer models on a dataset split into training (70), validation (10), and testing (10) sets to identify medication entities (substance, route, unit, time, presentation).

Main Results:

  • All evaluated transformer models demonstrated strong NER performance on validation and test datasets.
  • ClinicalBERT achieved the highest exact F1-score (0.973) in the test set, closely followed by ThaiBERT (0.969) and BioClinicalBERT (0.968).
  • Models excelled at identifying "Substance" and "Dosage" but struggled with "Unit of Measure" due to implicit information in the source text.

Conclusions:

  • Ontology-based medication IE using transformer models shows significant promise for improving data standardization and interoperability in the Thai healthcare system.
  • The developed NER framework provides a foundation for advanced clinical information extraction tasks.
  • Future research will focus on medical concept normalization and relation extraction to build a complete IE system.