BROWSE

Related Researcher

Author's Photo

Jang, Gil-Jin
Machine Intelligence Lab
Research Interests
  • Acoustic signal processing

ITEM VIEW & DOWNLOAD

Glaucomatous Patterns in Frequency Doubling Technology (FDT) Perimetry Data Identified by Unsupervised Machine Learning Classifiers

Cited 0 times inthomson ciCited 2 times inthomson ci
Title
Glaucomatous Patterns in Frequency Doubling Technology (FDT) Perimetry Data Identified by Unsupervised Machine Learning Classifiers
Author
Bowd, ChristopherWeinreb, Robert N.Balasubramanian, MadhusudhananLee, IntaeJang, Gil-JinYousefi, SiamakZangwill, Linda M.Medeiros, Felipe A.Girkin, Christopher A.Liebmann, Jeffrey M.Goldbaum, Michael H.
Keywords
STANDARD AUTOMATED PERIMETRY; RELEVANCE VECTOR MACHINE; VISUAL-FIELD DEFECTS; INDEPENDENT COMPONENT ANALYSIS; ARTIFICIAL NEURAL-NETWORK; FUNCTIONAL MEASUREMENTS; DIAGNOSTIC-ACCURACY; OPTIC DISC; MIXTURE; EYES
Issue Date
2014-01
Publisher
PUBLIC LIBRARY SCIENCE
Citation
PLOS ONE, v.9, no.1, pp.e85941 -
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 G(1) and G(2) combined, contained primarily abnormal fields (651/786, sensitivity 82.8%). For clusters G(1) and G(2) 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.
URI
Go to Link
DOI
10.1371/journal.pone.0085941
ISSN
1932-6203
Appears in Collections:
ECE_Journal Papers
Files in This Item:
000330617100011.pdf Download

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU