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

Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry.

Michael H Goldbaum1, Pamela A Sample, Kwokleung Chan

  • 1Ophthalmic Informatics Laboratory, Department of Ophthalmology, University of California at San Diego, La Jolla, California, USA. mgoldbaum@ucsd.edu

Investigative Ophthalmology & Visual Science
|January 5, 2002
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

Image-Quality-Aware Multimodal Artificial Intelligence for Automated Structured OCT Report Generation in Glaucoma Evaluation.

Ophthalmology science·2026
Same author

Ocular Hypertension Treatment Study: Effect of Time After Incident Glaucoma on OCT Optic Nerve Head and Macula Measurements.

American journal of ophthalmology·2026
Same author

Glaucomatous Remodeling of the Lamina Cribrosa: Association With Visual Field Progression.

Investigative ophthalmology & visual science·2026
Same author

A Comparative Analysis of Visual Field Test Results Using Tablet-Based and Table-Mounted Devices in a Telemedicine Program Set in Underserved Areas.

Translational vision science & technology·2026
Same author

Macula Spatial Patterns and Their Association With Central Visual Field Progression in Glaucoma Using Artificial Intelligence.

Journal of glaucoma·2026
Same author

Characterization of Temporal Delay and Modeling of Intraocular Pressure and Visual Field Progression in the African Descent and Glaucoma Evaluation Study.

Ophthalmology. Glaucoma·2026

The Mixture of Gaussians (MoG) machine learning classifier best interprets standard automated perimetry (SAP) visual field data, outperforming traditional STATPAC 2 indices and human experts in glaucoma diagnosis.

Area of Science:

  • Ophthalmology
  • Machine Learning
  • Medical Diagnostics

Background:

  • Standard automated perimetry (SAP) is crucial for diagnosing glaucoma.
  • Interpreting SAP data can be complex, necessitating advanced analytical tools.
  • Current interpretation methods, like STATPAC 2, have limitations.

Purpose of the Study:

  • To identify the optimal machine learning classifier for SAP data interpretation.
  • To compare the performance of machine learning classifiers against established glaucoma diagnostic indices and human experts.

Main Methods:

  • Four machine learning classifiers (MLP, SVM, MoG, MGG) were trained and validated using SAP data from normal and glaucomatous eyes.
  • Performance was evaluated using the area under the ROC curve.

Related Experiment Videos

  • Classifiers were compared with STATPAC 2 global indices and human expert assessments.

    • Main Results:

    • The Mixture of Gaussians (MoG) classifier demonstrated the highest area under the ROC curve among machine learning models.
    • MoG significantly outperformed STATPAC 2's Pattern SD (PSD) and corrected PSD (CPSD) indices.
    • Human experts did not achieve superior accuracy compared to machine classifiers or STATPAC 2 indices.

    Conclusions:

    • The MoG classifier, utilizing full visual field data and age, provides superior interpretation of SAP compared to STATPAC 2.
    • Machine learning classifiers show potential to enhance existing glaucoma diagnostic tools.