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

Medical dictionaries for patient encoding systems: a methodology

C Lovis1, R Baud, A M Rassinoux

  • 1Department of Internal Medicine, University State Hospital of Geneva, Switzerland. lovis@dim.hcuge.ch

Artificial Intelligence in Medicine
|October 21, 1998
PubMed
Summary

This study introduces a novel natural language processing approach to enhance medical lexical knowledge, aiding physicians in assigning accurate International Classification of Diseases (ICD) codes for diagnoses.

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

The impact of low-mode symmetry on inertial fusion energy output in the burning plasma state.

Nature communications·2024
Same author

Achievement of Target Gain Larger than Unity in an Inertial Fusion Experiment.

Physical review letters·2024
Same author

Cerclage performance analysis - a biomechanical comparison of different techniques and materials.

BMC musculoskeletal disorders·2022
Same author

Lawson Criterion for Ignition Exceeded in an Inertial Fusion Experiment.

Physical review letters·2022
Same author

Publisher Correction: Burning plasma achieved in inertial fusion.

Nature·2022
Same author

Burning plasma achieved in inertial fusion.

Nature·2022

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Natural Language Processing

Background:

  • Medical language is complex, relying heavily on compositional roots and specific morphological/semantic word formation rules.
  • Accurate coding of diagnoses is crucial for medical record-keeping and billing, but challenges exist in medical lexical knowledge coverage.
  • Existing systems may struggle with the nuances of medical terminology, impacting the accuracy of International Classification of Diseases (ICD) code assignment.

Purpose of the Study:

  • To address the limitations in medical lexical knowledge coverage for diagnostic coding.
  • To develop a dynamic natural language processing (NLP) dictionary and analyzer for medical diagnoses and procedures.
  • To improve the accuracy and efficiency of assigning International Classification of Diseases (ICD) codes.

Related Experiment Videos

Main Methods:

  • Developing a methodology for morphological decomposition and semantic analysis of medical terms.
  • Creating a powerful, dynamic dictionary specifically for NLP in medical diagnoses and narrative procedures.
  • Designing an analyzer that leverages the developed dictionary for enhanced medical term processing.

Main Results:

  • The proposed methodology demonstrates efficiency in handling various medical classifications.
  • The system successfully supports multiple languages, including French, German, English, and Dutch.
  • The approach is effective for both ICD-9 and ICD-10 classification systems.

Conclusions:

  • The developed NLP approach effectively enhances medical lexical knowledge, aiding physicians in accurate ICD code assignment.
  • The dynamic dictionary and analyzer offer a robust solution for processing medical diagnoses and procedures.
  • The system's multilingual and multi-classification capabilities highlight its broad applicability in clinical settings.