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

Automatic ICD Code Assignment based on ICD's Hierarchy Structure for Chinese Electronic Medical Records.

Lingyu Cao1, Dazhong Gu1, Yuan Ni1

  • 1Ping An Health Technology, Shanghai, China.

AMIA Joint Summits on Translational Science Proceedings. AMIA Joint Summits on Translational Science
|July 2, 2019
PubMed
Summary

This study introduces an automated method using a 3-layer attentional convolutional network to predict International Classification of Diseases (ICD) codes from medical records, improving accuracy and efficiency in health statistics and billing.

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

Time trends in the incidence of multiple primary melanomas in Australia.

Cancer epidemiology·2026
Same author

Multi-dimensional omics integrated machine learning framework identifies macrophage-fibroblast-tumor co-infiltration patterns to predict prognosis in gastric cancer.

NPJ digital medicine·2025
Same author

Relationships between multimodal ocular imaging and white matter hyperintensity volume.

Quantitative imaging in medicine and surgery·2025
Same author

Atorvastatin pretreatment, ST-segment resolution and long-term prognosis for ST-segment elevation myocardial infarction with primary percutaneous coronary intervention.

International journal of cardiology. Heart & vasculature·2025
Same author

Synergistic Coupling of Antenna Effect and Schottky Junction in Tb-Doped Covalent Organic Framework for Enhanced Electrochemiluminescence Sening of Isobutyryl Fentanyl.

Analytical chemistry·2025
Same author

Multimodal Deep Learning for ARDS Detection.

medRxiv : the preprint server for health sciences·2025

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Health Statistics

Background:

  • Medical records contain crucial diagnostic and clinical information.
  • International Classification of Diseases (ICD) codes are essential for health statistics, public health investment, and insurance billing.
  • Manual ICD coding is labor-intensive, complex, and prone to errors.

Purpose of the Study:

  • To develop an automated system for predicting ICD codes from medical text.
  • To leverage the hierarchical structure of ICD codes for improved prediction accuracy.
  • To outperform existing state-of-the-art methods in ICD code assignment.

Main Methods:

  • A novel 3-layer attentional convolutional network was designed.
  • The network architecture incorporates the hierarchical structure of ICD codes.

Related Experiment Videos

  • The model predicts ICD codes directly from unstructured medical record text.

    • Main Results:

    • The proposed model achieved a Hit@1 accuracy of 0.6969.
    • The model achieved a Hit@5 accuracy of 0.8903.
    • Performance metrics surpassed those of current state-of-the-art methods.

    Conclusions:

    • The 3-layer attentional convolutional network offers a highly effective automated solution for ICD code prediction.
    • This approach significantly enhances the efficiency and accuracy of medical record coding.
    • The method holds promise for improving health data management and financial processes in healthcare.