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

Diagnosis of glaucoma by indirect classifiers.

A Peters1, B Lausen, G Michelson

  • 1Department of Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander-University Erlangen-Nuremberg, Erlangen, Germany.

Methods of Information in Medicine
|April 16, 2003
PubMed
Summary

Indirect classification, combining medical knowledge with statistical methods, improves glaucoma diagnosis accuracy. This approach reduces misclassification errors compared to direct classification techniques.

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

Levels of messenger-RNA coding for DNA topoisomerase-ii isoforms do not correlate with in-vitro drug-sensitivity.

Oncology reports·2011
Same author

Occurrence and concentration of dissolved silver in rivers in England and Wales.

Bulletin of environmental contamination and toxicology·2011
Same author

No evidence for general condition-dependence of structural plumage colour in blue tits: an experiment.

Journal of evolutionary biology·2011
Same author

Assessing the impact of East Coast Fever immunisation by the infection and treatment method in Tanzanian pastoralist systems.

Preventive veterinary medicine·2010
Same author

Prediction models for incident type 2 diabetes mellitus
in the older population: KORA S4/F4 cohort study.

Diabetic medicine : a journal of the British Diabetic Association·2010
Same author

Bose-Einstein condensation in microgravity.

Science (New York, N.Y.)·2010

Area of Science:

  • Ophthalmology
  • Medical Informatics
  • Machine Learning

Background:

  • Glaucoma diagnosis relies on accurate classification of patient data.
  • Traditional classification methods may not fully leverage existing medical knowledge.
  • Improving classification accuracy is crucial for effective glaucoma management.

Purpose of the Study:

  • To demonstrate the effectiveness of indirect classification for glaucoma diagnosis.
  • To compare indirect classification with direct classification methods.
  • To assess the impact of incorporating a priori medical knowledge on classification accuracy.

Main Methods:

  • Indirect classification framework integrating medical knowledge and statistical models.
  • Application of classification trees and bootstrap aggregation for error reduction.

Related Experiment Videos

  • Comparison with direct methods: linear discriminant analysis, classification trees, and bootstrap aggregated classification trees.
  • 10-fold cross-validation for estimating misclassification rates.

    • Main Results:

    • Indirect classification techniques significantly reduced misclassification error in glaucoma diagnosis.
    • The proposed framework outperformed direct classification methods.
    • Bootstrap aggregation further enhanced the reduction of misclassification errors.

    Conclusions:

    • Integrating a priori medical knowledge into statistical classification improves diagnostic accuracy.
    • Indirect classification provides a viable framework for combining domain expertise with data-driven methods.
    • This approach holds promise for enhancing diagnostic performance in complex medical conditions like glaucoma.