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

Statistical selector of the best multiple ICD-coding method.

Eiji Aramaki1, Takeshi Imai, Masayuki Kajino

  • 1The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan. aramaki@hcc.h.u-tokyo.ac.jp

Studies in Health Technology and Informatics
|October 4, 2007
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

Benchmarking Zero-Shot Generative Pre-Trained Transformer-Based Multimodal Large Language Models for Pressure Injury Staging.

Advances in wound care·2026
Same author

Emotion Classification in Japanese Cancer Survivor Interview Narratives Using Sentiment Polarity and Plutchik Emotion Frameworks: Model Development and Evaluation Study.

JMIR formative research·2026
Same author

HeXEHRS: Design and Implementation of a FHIR-Based Cloud EHR and Client for Depopulated Regions with AI and Digital-Twin Integration.

Studies in health technology and informatics·2026
Same author

A Multiassessment and Multiprofessional Agents Approach for Medical Chatbot Risk Estimation: Development and Evaluation Study.

JMIR medical informatics·2026
Same author

Evaluating Encoder and Decoder Models for Extended Clinical Concept Recognition in Japanese Clinical Texts: Comparative Study With Weighted Soft Matching.

Journal of medical Internet research·2026
Same author

Subset binding enables detection of multimodal patient subgroup patterns and drug target discovery in idiopathic pulmonary fibrosis.

Briefings in bioinformatics·2026
Same journal

A GenAI Pipeline for Violinist Kinematic Data Management.

Studies in health technology and informatics·2026
Same journal

AMAL-For-Qatar: A Comprehensive AI Ecosystem for Fetal Ultrasound Analysis - Project Overview and Achievements.

Studies in health technology and informatics·2026
Same journal

Longitudinal Treatment-Aware Multimodal AI for Dermatology: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Predicting Postpartum Depression Using Imbalance-Aware Machine Learning.

Studies in health technology and informatics·2026
Same journal

Validation of Deep-Learning Models for Autosegmentation of Brain Metastases.

Studies in health technology and informatics·2026
Same journal

Delay-Dependent Gating in Modular RNNs.

Studies in health technology and informatics·2026
See all related articles

This study introduces a hybrid approach for International Classification of Diseases 10th version (ICD-10) coding. A novel system selector improves accuracy by intelligently combining outputs from multiple ICD-10 coding systems.

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Health Information Systems

Background:

  • The International Classification of Diseases 10th version (ICD-10) is a critical standard for disease classification.
  • Automated ICD-10 coding systems are increasingly important in healthcare, leading to diverse proposed solutions.
  • Existing systems face challenges in achieving optimal accuracy and reliability for disease classification.

Purpose of the Study:

  • To propose a novel hybrid architecture for enhancing automated ICD-10 coding.
  • To develop a system selector that intelligently integrates outputs from multiple coding systems.
  • To improve the overall performance and accuracy of ICD-10 disease classification.

Main Methods:

  • A hybrid architecture combining multiple ICD-10 coding systems was developed.

Related Experiment Videos

  • Three distinct coding systems generate potential ICD-10 codes with confidence scores.
  • A C4.5 decision tree-based system selector was employed to choose the optimal code, utilizing input statistics and system confidence scores.

    • Main Results:

    • The proposed hybrid architecture significantly improved overall ICD-10 coding performance.
    • The C4.5-based system selector demonstrated a notable performance boost of +3.4 points.
    • The experimental results validated the effectiveness of the intelligent system selection approach.

    Conclusions:

    • The hybrid ICD-10 coding system with a C4.5 selector offers a superior approach to automated disease classification.
    • Intelligent selection and integration of multiple coding systems enhance accuracy and reliability.
    • This method represents a significant advancement in the field of medical informatics and health information systems.