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

Automated coding of diagnoses--three methods compared.

P Franz1, A Zaiss, S Schulz

  • 1Freiburg University Hospital, Department of Medical Informatics.

Proceedings. AMIA Symposium
|November 18, 2000
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

Development of fast 2.5 MeV neutron detectors for high-intensity stray magnetic field environments.

The Review of scientific instruments·2024
Same author

[Comparative analysis of three models of reverse shoulder prosthesis based on the new angles of distalization and lateralization].

Acta ortopedica mexicana·2021
Same author

A connection between neurovascular conflicts within the cerebellopontine angle and vestibular neuritis, a case controlled cohort study.

Acta otorhinolaryngologica Italica : organo ufficiale della Societa italiana di otorinolaringologia e chirurgia cervico-facciale·2016
Same author

Calibration of a two-color soft x-ray diagnostic for electron temperature measurement.

The Review of scientific instruments·2016
Same author

A comparison between soft x-ray and magnetic phase data on the Madison symmetric torus.

The Review of scientific instruments·2016
Same author

Synthesis of Bi<sub>2</sub>Te<sub>3</sub> and (Bi<sub>x</sub>Sb<sub>1-x</sub>)<sub>2</sub>Te<sub>3</sub> nanoparticles using the novel IL [C<sub>4</sub>mim]<sub>3</sub>[Bi<sub>3</sub>I<sub>12</sub>].

Dalton transactions (Cambridge, England : 2003)·2016
Same journal

Progressive display of very high resolution images using wavelets.

Proceedings. AMIA Symposium·2002
Same journal

The Chronus II temporal database mediator.

Proceedings. AMIA Symposium·2002
Same journal

Gene expression levels in different stages of progression in oral squamous cell carcinoma.

Proceedings. AMIA Symposium·2002
Same journal

An assessment of the visibility of MeSH-indexed medical web catalogs through search engines.

Proceedings. AMIA Symposium·2002
Same journal

Filtering for medical news items using a machine learning approach.

Proceedings. AMIA Symposium·2002
Same journal

Enriching the structure of the UMLS semantic network.

Proceedings. AMIA Symposium·2002
See all related articles

Automated coding of German diagnoses is crucial for legal compliance. Lexicon-based methods improve accuracy only when incorporating medical knowledge, like SNOMED codes.

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Health Information Management

Background:

  • New German legal requirements necessitate precise encoding of patient diagnoses.
  • There is a growing need for computer-assisted tools for automated medical coding.
  • Accurate coding impacts healthcare data management and compliance.

Purpose of the Study:

  • To evaluate automated coding methods for German-language diagnosis phrases.
  • To compare lexicon-free and lexicon-based approaches for medical term encoding.
  • To assess the impact of incorporating semantic knowledge (SNOMED codes) on coding accuracy.

Main Methods:

  • Compared a lexicon-free n-gram approach with a lexicon-based method using medical morphemes and SNOMED code mapping.

Related Experiment Videos

  • Utilized a vector space model for ranked retrieval of potential diagnoses.
  • Modified the lexicon-based method with a heuristic approach leveraging SNOMED's semantic structure.

    • Main Results:

    • No significant difference between lexicon-free and initial lexicon-based methods (approx. 40% for 3-digit, 30% for 4-digit codes).
    • The modified lexicon-based approach, using SNOMED semantic structure, significantly improved accuracy (approx. 50% for 3-digit, 40% for 4-digit codes).
    • Lexicon-based retrieval requires conceptual knowledge integration for superior performance.

    Conclusions:

    • Lexicon-free methods are comparable to basic lexicon-based approaches for automated diagnosis coding.
    • Integrating conceptual knowledge, such as SNOMED's semantic structure, is key to enhancing lexicon-based coding accuracy.
    • Future automated coding tools should leverage medical ontologies for improved performance.