Format

Send to

Choose Destination
PLoS One. 2014 Jan 30;9(1):e85941. doi: 10.1371/journal.pone.0085941. eCollection 2014.

Glaucomatous patterns in Frequency Doubling Technology (FDT) perimetry data identified by unsupervised machine learning classifiers.

Author information

1
Hamilton Glaucoma Center, Department of Ophthalmology, University of California, San Diego, La Jolla, California, United States of America.
2
Hamilton Glaucoma Center, Department of Ophthalmology, University of California, San Diego, La Jolla, California, United States of America ; School of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology, Ulsan, South Korea.
3
Department of Ophthalmology, University of Alabama at Birmingham, Birmingham, Alabama, United States of America.
4
Department of Ophthalmology, New York University School of Medicine, New York, New York, United States of America ; New York Eye and Ear Infirmary, New York, New York, United States of America.

Abstract

PURPOSE:

The variational Bayesian independent component analysis-mixture model (VIM), an unsupervised machine-learning classifier, was used to automatically separate Matrix Frequency Doubling Technology (FDT) perimetry data into clusters of healthy and glaucomatous eyes, and to identify axes representing statistically independent patterns of defect in the glaucoma clusters.

METHODS:

FDT measurements were obtained from 1,190 eyes with normal FDT results and 786 eyes with abnormal FDT results from the UCSD-based Diagnostic Innovations in Glaucoma Study (DIGS) and African Descent and Glaucoma Evaluation Study (ADAGES). For all eyes, VIM input was 52 threshold test points from the 24-2 test pattern, plus age.

RESULTS:

FDT mean deviation was -1.00 dB (S.D. = 2.80 dB) and -5.57 dB (S.D. = 5.09 dB) in FDT-normal eyes and FDT-abnormal eyes, respectively (p<0.001). VIM identified meaningful clusters of FDT data and positioned a set of statistically independent axes through the mean of each cluster. The optimal VIM model separated the FDT fields into 3 clusters. Cluster N contained primarily normal fields (1109/1190, specificity 93.1%) and clusters G1 and G2 combined, contained primarily abnormal fields (651/786, sensitivity 82.8%). For clusters G1 and G2 the optimal number of axes were 2 and 5, respectively. Patterns automatically generated along axes within the glaucoma clusters were similar to those known to be indicative of glaucoma. Fields located farther from the normal mean on each glaucoma axis showed increasing field defect severity.

CONCLUSIONS:

VIM successfully separated FDT fields from healthy and glaucoma eyes without a priori information about class membership, and identified familiar glaucomatous patterns of loss.

PMID:
24497932
PMCID:
PMC3907565
DOI:
10.1371/journal.pone.0085941
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Public Library of Science Icon for PubMed Central
Loading ...
Support Center