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

Optical coherence tomography machine learning classifiers for glaucoma detection: a preliminary study.

Zvia Burgansky-Eliash1, Gadi Wollstein, Tianjiao Chu

  • 1UPMC Eye Center, Ophthalmology and Visual Science Research Center, Eye and Ear Institute, Department of Ophthalmology, University of Pittsburgh School of Medicine, PA 15213, USA.

Investigative Ophthalmology & Visual Science
|October 27, 2005
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

Comparing the Use of Measured and Smoothed Data in Forecasting Visual Field Tests Using Deep Learning.

Ophthalmology science·2026
Same author

Modalities of vision restoration in optic neuropathies and retinal disease.

Progress in retinal and eye research·2026
Same author

Predicting Intraocular Pressure From Glaucoma Patients Receiving Medication Treatment Using Explainable Machine Learning.

BioMed research international·2026
Same author

Best practices for moving from correlation to causation in ecological research.

Nature communications·2026
Same author

Predicting Intraocular Pressure From Glaucoma Patients Receiving Medication Treatment Using Explainable Machine Learning.

BioMed research international·2026
Same author

Stimulus-driven cerebrospinal fluid dynamics is impaired in glaucoma patients.

npj aging·2026

Machine-learning classifiers significantly enhance optical coherence tomography (OCT) for glaucoma detection. Support vector machines with eight parameters achieved high accuracy, improving diagnostic capabilities for this eye condition.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Glaucoma is a leading cause of irreversible blindness worldwide.
  • Early detection and monitoring are crucial for managing glaucoma and preventing vision loss.
  • Optical coherence tomography (OCT) provides detailed cross-sectional images of the optic nerve head and retinal nerve fiber layer.

Purpose of the Study:

  • To evaluate the effectiveness of machine-learning classifiers in improving glaucoma detection using OCT data.
  • To compare the performance of different machine-learning algorithms for discriminating between healthy and glaucomatous eyes.
  • To identify the optimal set of OCT parameters for accurate glaucoma diagnosis.

Main Methods:

  • A cross-sectional study included 47 glaucoma patients and 42 healthy subjects.

Related Experiment Videos

  • Machine-learning classifiers were trained using 38 OCT parameters and a reduced set of 8 parameters correlated with visual field mean deviation (MD).
  • Five classifiers (LDA, SVM, RPT, GLM, GAM) were tested, with feature selection employed for GLM and GAM.

    • Main Results:

    • The support vector machine (SVM) using eight parameters achieved the highest area under the ROC curve (AROC = 0.981) for glaucoma detection.
    • This SVM classifier demonstrated high sensitivity (97.9%) at 80% specificity and excellent cross-validated accuracy (0.966).
    • The generalized additive model (GAM) with three parameters effectively differentiated between early and advanced glaucoma (AROC = 0.854).

    Conclusions:

    • Automated machine classifiers show promise for enhancing the diagnostic utility of OCT in glaucoma detection.
    • Machine learning algorithms can effectively analyze complex OCT data to identify glaucomatous abnormalities.
    • These findings suggest that integrating machine learning with OCT could improve clinical decision-making for glaucoma management.