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 Experiment Videos

Optimizing Automated KCD Coding: A Retrieval-Verification Approach.

Sangji Lee1, Won Chul Cha2

  • 1Department of Digital Health, Samsung Advanced Institute for Health Science & Technology (SAIHST), Sungkyunkwan University, Seoul, Republic of Korea.

Studies in Health Technology and Informatics
|May 17, 2025
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

FT-Transformer DeepSurv: A Novel Approach to Predicting Post-Discharge Mortality in Older Adults.

Studies in health technology and informatics·2026
Same author

Automated Information Extraction Pipeline for Constructing ED Knowledge Graphs from Korean Clinical Problem Lists.

Studies in health technology and informatics·2026
Same author

A critical review of potential modifiers of air pollutant associations with dementia and related outcomes.

Neurotoxicology·2026
Same author

Multimodal AI-based 28-day mortality prediction of pneumonia patients at ED discharge: a multicenter study.

Scientific reports·2026
Same author

Assessing emergency department physician workload: A NASA-TLX analysis by experience and care type.

Clinical and experimental emergency medicine·2026
Same author

Pregnant Women's Experience and Perceptions of Seatbelt Education: Assessing the Impact of Maternity Seatbelt Safety Interventions.

Clinical and experimental emergency medicine·2026

This study introduces an automated system for assigning Korean Standard Classification of Diseases (KCD) codes to medical diagnoses. Combining SapBERT-XLMR and Llama 3.1 models achieved 82.3% accuracy in this task.

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Health Information Management

Background:

  • Accurate disease coding is crucial for healthcare statistics, billing, and research.
  • Manual assignment of Korean Standard Classification of Diseases (KCD) codes to free-text diagnoses is time-consuming and prone to errors.

Purpose of the Study:

  • To develop and evaluate a two-step automated system for assigning KCD codes to free-text clinical diagnoses.
  • To improve the efficiency and accuracy of the KCD coding process.

Main Methods:

  • A two-step retrieval-verification system was proposed.
  • SapBERT-XLMR was utilized for the initial retrieval of potential KCD codes.
  • Llama 3.1 was employed for the final verification and selection of the most appropriate KCD code.
Keywords:
Clinical codingEmbeddingKCDLanguage models

Related Experiment Videos

Main Results:

  • The combined two-step system achieved a notable accuracy of 82.3% in assigning KCD codes.
  • The integration of retrieval and verification models demonstrated improved performance over single-model approaches.

Conclusions:

  • The proposed two-step Retrieval-Verification system offers a promising automated solution for KCD code assignment.
  • Future research should focus on enhancing performance with medical abbreviations and validating with larger datasets.