Show simple item record

dc.contributor.authorSaeedi, Osamah
dc.contributor.authorBoland, Michael V
dc.contributor.authorD'Acunto, Loris
dc.contributor.authorSwamy, Ramya
dc.contributor.authorHegde, Vikram
dc.contributor.authorGupta, Surabhi
dc.contributor.authorVenjara, Amin
dc.contributor.authorTsai, Joby
dc.contributor.authorMyers, Jonathan S
dc.contributor.authorWellik, Sarah R
dc.contributor.authorDeMoraes, Gustavo
dc.contributor.authorPasquale, Louis R
dc.contributor.authorShen, Lucy Q
dc.contributor.authorLi, Yangjiani
dc.contributor.authorElze, Tobias
dc.date.accessioned2021-06-24T18:26:02Z
dc.date.available2021-06-24T18:26:02Z
dc.date.issued2021-06-22
dc.identifier.urihttp://hdl.handle.net/10713/16081
dc.description.abstractPURPOSE: To develop and test machine learning classifiers (MLCs) for determining visual field progression. METHODS: In total, 90,713 visual fields from 13,156 eyes were included. Six different progression algorithms (linear regression of mean deviation, linear regression of the visual field index, Advanced Glaucoma Intervention Study algorithm, Collaborative Initial Glaucoma Treatment Study algorithm, pointwise linear regression [PLR], and permutation of PLR) were applied to classify each eye as progressing or stable. Six MLCs were applied (logistic regression, random forest, extreme gradient boosting, support vector classifier, convolutional neural network, fully connected neural network) using a training and testing set. For MLC input, visual fields for a given eye were divided into the first and second half and each location averaged over time within each half. Each algorithm was tested for accuracy, sensitivity, positive predictive value, and class bias with a subset of visual fields labeled by a panel of three experts from 161 eyes. RESULTS: MLCs had similar performance metrics as some of the conventional algorithms and ranged from 87% to 91% accurate with sensitivity ranging from 0.83 to 0.88 and specificity from 0.92 to 0.96. All conventional algorithms showed significant class bias, meaning each individual algorithm was more likely to grade uncertain cases as either progressing or stable (P ≤ 0.01). Conversely, all MLCs were balanced, meaning they were equally likely to grade uncertain cases as either progressing or stable (P ≥ 0.08). CONCLUSIONS: MLCs showed a moderate to high level of accuracy, sensitivity, and specificity and were more balanced than conventional algorithms. TRANSLATIONAL RELEVANCE: MLCs may help to determine visual field progression.en_US
dc.description.urihttps://doi.org/10.1167/tvst.10.7.27en_US
dc.language.isoenen_US
dc.publisherAssociation for Research in Vision and Ophthalmology, Inc.en_US
dc.relation.ispartofTranslational Vision Science & Technologyen_US
dc.subjectmachine learning classifiersen_US
dc.subject.meshDisease Progressionen_US
dc.subject.meshGlaucomaen_US
dc.subject.meshMachine Learning Algorithmsen_US
dc.subject.meshVisual Field Tests--methodsen_US
dc.titleDevelopment and Comparison of Machine Learning Algorithms to Determine Visual Field Progressionen_US
dc.typeArticleen_US
dc.identifier.doi10.1167/tvst.10.7.27
dc.identifier.pmid34157101
dc.source.volume10
dc.source.issue7
dc.source.beginpage27
dc.source.endpage
dc.source.countryUnited States


This item appears in the following Collection(s)

Show simple item record