Related Experiment Video
Updated: Jul 6, 2026

Assessing Early Stage Open-Angle Glaucoma in Patients by Isolated-Check Visual Evoked Potential
Published on: May 25, 2020
Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and
Christopher Bowd1, Jiucang Hao, Ivan M Tavares
1Hamilton Glaucoma Center, Department of Ophthalmology, University of California, San Diego, La Jolla, CA 92037-0946, USA. cbowd@eyecenter.ucsd.edu
Combining optical coherence tomography (OCT) and standard automated perimetry (SAP) measurements with machine learning classifiers (MLCs) slightly improved glaucoma detection accuracy. This approach enhances diagnostic performance for identifying glaucomatous eyes compared to using each method alone.
Area of Science:
- Ophthalmology
- Medical Imaging
- Machine Learning
Background:
- Glaucoma diagnosis relies on structural and functional measurements.
- Optical coherence tomography (OCT) provides structural data, while standard automated perimetry (SAP) offers functional data.
- Machine learning classifiers (MLCs) can analyze complex datasets for diagnostic purposes.
Purpose of the Study:
- To evaluate if combining OCT and SAP measurements improves diagnostic accuracy for glaucoma detection using MLCs.
- To compare the diagnostic performance of MLCs using combined OCT and SAP data versus individual data sources.
Main Methods:
- Sixty-nine healthy eyes and 156 glaucomatous eyes were analyzed.
- OCT (RNFL thickness) and SAP (pattern deviation values) data were collected.
- Relevance vector machine (RVM) and subspace mixture of Gaussians (SSMoG) MLCs were trained and tested using tenfold cross-validation.
Main Results:
- The area under the receiver operating characteristic curve (AUROC) for combined OCT and SAP data ranged from 0.845 (RVM) to 0.869 (SSMoG).
- Combining OCT and SAP data marginally improved diagnostic performance compared to using either OCT or SAP alone.
- Both RVM and SSMoG showed statistically similar classification performance.
Conclusions:
- Bayesian MLCs (RVM and SSMoG) trained on combined OCT and SAP data can effectively distinguish between healthy and early glaucomatous eyes.
- Integrating OCT and SAP measurements offers a marginal enhancement in diagnostic performance for glaucoma detection.
Related Concept Videos
Structural Classification of Joints
A fibrous joint is where the adjacent bones are united by fibrous connective...
Glaucoma: Overview
Functional Classification of Joints
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An immobile...
Open Angle Glaucoma: Treatment
Drugs such as carbonic anhydrase inhibitors, α2- and...
Angle Closure Glaucoma: Treatment