Online citations, reference lists, and bibliographies.
Please confirm you are human
(Sign Up for free to never see this)
← Back to Search

Detection Of Longitudinal Visual Field Progression In Glaucoma Using Machine Learning.

S. Yousefi, Taichi Kiwaki, Y. Zheng, H. Sugiura, R. Asaoka, H. Murata, H. Lemij, Kenji Yamanishi
Published 2018 · Medicine

Save to my Library
Download PDF
Analyze on Scholarcy
Share
PURPOSE Global indices of standard automated perimerty are insensitive to localized losses, while point-wise indices are sensitive but highly variable. Region-wise indices sit in between. This study introduces a machine learning-based index for glaucoma progression detection that outperforms global, region-wise, and point-wise indices. DESIGN Development and comparison of a prognostic index. METHOD Visual fields from 2085 eyes of 1214 subjects were used to identify glaucoma progression patterns using machine learning. Visual fields from 133 eyes of 71 glaucoma patients were collected 10 times over 10 weeks to provide a no-change, test-retest dataset. The parameters of all methods were identified using visual field sequences in the test-retest dataset to meet fixed 95% specificity. An independent dataset of 270 eyes of 136 glaucoma patients and survival analysis were used to compare methods. RESULTS The time to detect progression in 25% of the eyes in the longitudinal dataset using global mean deviation (MD) was 5.2 (95% confidence interval, 4.1-6.5) years; 4.5 (4.0-5.5) years using region-wise, 3.9 (3.5-4.6) years using point-wise, and 3.5 (3.1-4.0) years using machine learning analysis. The time until 25% of eyes showed subsequently confirmed progression after 2 additional visits were included were 6.6 (5.6-7.4) years, 5.7 (4.8-6.7) years, 5.6 (4.7-6.5) years, and 5.1 (4.5-6.0) years for global, region-wise, point-wise, and machine learning analyses, respectively. CONCLUSIONS Machine learning analysis detects progressing eyes earlier than other methods consistently, with or without confirmation visits. In particular, machine learning detects more slowly progressing eyes than other methods.
This paper references
10.1097/00061198-199508000-00005
Ability of the Heidelberg Retina Tomograph to Detect Early Glaucomatous Visual Field Loss
F. Mikelberg (1995)
10.3109/08820530009037869
Current Practice with Standard Automated Perimetry
C. Bosworth (2000)
10.1080/0065955x.1992.11981920
Automated Static Perimetry
D. Anderson (1992)
10.1016/S0161-6420(00)00284-0
Mapping the visual field to the optic disc in normal tension glaucoma eyes.
D. Garway-Heath (2000)
10.1167/iovs.17-21562
Detection of Functional Change Using Cluster Trend Analysis in Glaucoma
S. Gardiner (2017)
10.1016/J.AJO.2007.09.038
A visual field index for calculation of glaucoma rate of progression.
B. Bengtsson (2008)
10.1167/IOVS.05-0135
Threshold and variability properties of matrix frequency-doubling technology and standard automated perimetry in glaucoma.
P. Artes (2005)
10.1001/ARCHOPHT.1992.01080180084033
Glaucoma Hemifield Test. Automated visual field evaluation.
P. Åsman (1992)
Variability in patients with glaucomatous visual field damage is reduced using size V stimuli.
M. Wall (1997)
10.1109/TBME.2014.2314714
Learning From Data: Recognizing Glaucomatous Defect Patterns and Detecting Progression From Visual Field Measurements
S. Yousefi (2014)
10.1016/j.ajo.2017.01.013
Detecting Change Using Standard Global Perimetric Indices in Glaucoma.
S. Gardiner (2017)
10.1103/PHYSREVA.36.340
Singular-value decomposition and embedding dimension.
Mees (1987)
10.1117/12.2043145
Recognizing patterns of visual field loss using unsupervised machine learning
S. Yousefi (2014)
10.1007/978-0-387-76700-0_23
Detecting Functional Changes in the Patient’s Vision: Visual Field Analysis
C. A. Johnson (2010)
10.1016/j.ophtha.2017.01.027
Frequency of Testing to Detect Visual Field Progression Derived Using a Longitudinal Cohort of Glaucoma Patients.
Zhichao Wu (2017)
Examination of different pointwise linear regression methods for determining visual field progression.
S. Gardiner (2002)
10.1097/IJG.0b013e318179f7ca
Detectability of Glaucomatous Changes Using SAP, FDT, Flicker Perimetry, and OCT
Hiroki Nomoto (2009)
10.1371/journal.pone.0085941
Glaucomatous Patterns in Frequency Doubling Technology (FDT) Perimetry Data Identified by Unsupervised Machine Learning Classifiers
C. Bowd (2014)
10.1136/bjo.81.6.452
High spatial resolution automated perimetry in glaucoma
M. Westcott (1997)
10.1016/J.AJO.2004.08.006
Visual field changes after cataract extraction: the AGIS experience.
B. Koucheki (2004)
10.1109/TBME.2013.2295605
Glaucoma Progression Detection Using Structural Retinal Nerve Fiber Layer Measurements and Functional Visual Field Points
S. Yousefi (2014)
10.1093/BIOMET/69.3.553
A class of rank test procedures for censored survival data
D. Harrington (1982)
10.1136/bjo.80.1.40
Analysis of visual field progression in glaucoma.
F. Fitzke (1996)
10.1136/bjo.86.5.560
Frequency of testing for detecting visual field progression
S. Gardiner (2002)
10.3310/HSDR02270
Frequency of visual field testing when monitoring patients newly diagnosed with glaucoma: mixed methods and modelling
D. Crabb (2014)
10.1167/tvst.5.3.2
Unsupervised Gaussian Mixture-Model With Expectation Maximization for Detecting Glaucomatous Progression in Standard Automated Perimetry Visual Fields
S. Yousefi (2016)
10.1016/S0002-9394(02)01577-5
Structure and function evaluation (SAFE): I. criteria for glaucomatous visual field loss using standard automated perimetry (SAP) and short wavelength automated perimetry (SWAP).
C. Johnson (2002)



This paper is referenced by
10.1136/bjophthalmol-2019-315016
Glaucoma management in the era of artificial intelligence
Sripad Krishna Devalla (2019)
10.1109/ISBI45749.2020.9098614
Macular GCIPL Thickness Map Prediction via Time-Aware Convolutional LSTM
Zhiqi Chen (2020)
10.4103/kjo.kjo_54_19
Role of artificial intelligence and machine learning in ophthalmology
J. Akkara (2019)
10.1167/tvst.9.2.42
A Review of Deep Learning for Screening, Diagnosis, and Detection of Glaucoma Progression
A. C. Thompson (2020)
10.1167/tvst.7.5.3
Application of Pattern Recognition Analysis to Optimize Hemifield Asymmetry Patterns for Early Detection of Glaucoma
Jack Phu (2018)
10.1097/ICU.0000000000000552
Artificial intelligence in glaucoma
C. Zheng (2019)
10.1038/s41598-019-44852-6
Visual Field Prediction using Recurrent Neural Network
Keunheung Park (2019)
10.1038/s41598-019-54653-6
Estimating Rates of Progression and Predicting Future Visual Fields in Glaucoma Using a Deep Variational Autoencoder
S. Berchuck (2019)
10.1109/IVCNZ.2018.8634733
Glaucoma Monitoring Using Manifold Learning and Unsupervised Clustering
S. Yousefi (2018)
10.1167/iovs.18-25568
An Artificial Intelligence Approach to Detect Visual Field Progression in Glaucoma Based on Spatial Pattern Analysis
Mengyu Wang (2019)
10.1038/s41598-020-64869-6
The usefulness of the Deep Learning method of variational autoencoder to reduce measurement noise in glaucomatous visual fields
R. Asaoka (2020)
10.1016/j.preteyeres.2020.100907
Fundus-controlled perimetry (microperimetry): Application as outcome measure in clinical trials
M. Pfau (2020)
10.1007/s10384-019-00659-6
Evaluation of deep convolutional neural networks for glaucoma detection
S. Phan (2019)
10.1016/j.ophtha.2020.03.008
Monitoring Glaucomatous Functional Loss Using an Artificial Intelligence-Enabled Dashboard.
S. Yousefi (2020)
10.1080/08820538.2019.1620801
Machine Learning in the Detection of the Glaucomatous Disc and Visual Field
D. Smits (2019)
10.21037/ATM.2020.02.162
An artificial intelligence model for the simulation of visual effects in patients with visual field defects.
Z. Zhou (2020)
10.1167/tvst.9.2.55
Artificial Intelligence Algorithms to Diagnose Glaucoma and Detect Glaucoma Progression: Translation to Clinical Practice
A. S. Mursch-Edlmayr (2020)
10.1016/j.ophtha.2019.12.004
Artificial Intelligence Classification of Central Visual Field Patterns in Glaucoma.
Mengyu Wang (2019)
10.1016/j.compmedimag.2020.101818
Artificial intelligence (AI) impacting diagnosis of glaucoma and understanding the regulatory aspects of AI-based software as medical device.
B. Prabhakar (2020)
10.1136/bjophthalmol-2019-314136
Validating the efficacy of the binomial pointwise linear regression method to detect glaucoma progression with multicentral database
Shotaro Asano (2019)
10.1007/s40123-019-00207-y
Optical Coherence Tomography-Based Deep-Learning Models for Classifying Normal and Age-Related Macular Degeneration and Exudative and Non-Exudative Age-Related Macular Degeneration Changes
Naohiro Motozawa (2019)
Scalable Modeling of Spatiotemporal Data using the Variational Autoencoder: an Application in Glaucoma.
S. Berchuck (2019)
10.1016/J.OGLA.2019.01.003
Comparing 10-2 and 24-2 Visual Fields for Detecting Progressive Central Visual Loss in Glaucoma Eyes with Early Central Abnormalities.
Zhichao Wu (2019)
10.1038/s41598-020-75816-w
Optical coherence tomography-based deep-learning model for detecting central serous chorioretinopathy
Jeewoo Yoon (2020)
10.1007/s40135-019-00209-w
The Role of Artificial Intelligence in the Diagnosis and Management of Glaucoma
Rahul Kapoor (2019)
10.1136/bjophthalmol-2018-313173
Artificial intelligence and deep learning in ophthalmology
D. Ting (2019)
10.1016/j.ajo.2018.11.004
Early Detection of Glaucomatous Visual Field Progression Using Pointwise Linear Regression With Binomial Test in the Central 10 Degrees.
Shotaro Asano (2019)
10.1038/s41746-020-00329-9
Development and clinical deployment of a smartphone-based visual field deep learning system for glaucoma detection
F. Li (2020)
10.1101/652487
Estimating Rates of Progression and Predicting Future Visual Fields in Glaucoma Using a Deep Variational Autoencoder
S. Berchuck (2019)
10.1016/j.preteyeres.2020.100900
Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective
Ji-Peng Olivia Li (2020)
Semantic Scholar Logo Some data provided by SemanticScholar