Comparison of Machine-Learning Classification Models for Glaucoma Management. (19th June 2018)

• Record Type: Journal Article
• Authors: An, Guangzhou; Omodaka, Kazuko; Tsuda, Satoru; Shiga, Yukihiro; Takada, Naoko; Kikawa, Tsutomu; Nakazawa, Toru; Yokota, Hideo; Akiba, Masahiro
• Other Names: Hussain Altaf Academic Editor.
• Is Part Of: Journal of healthcare engineering. Volume 2018(2018)
• Publication Date: 2018-06-19
• Subjects: Hospital buildings -- Environmental engineering -- Periodicals; Medical technology -- Periodicals; Medical informatics -- Periodicals; 610.28
• DOI: 10.1155/2018/6874765
• Languages: English
• ISSNs: 2040-2295

Abstract

Abstract : This study develops an objective machine-learning classification model for classifying glaucomatous optic discs and reveals the classificatory criteria to assist in clinical glaucoma management. In this study, 163 glaucoma eyes were labelled with four optic disc types by three glaucoma specialists and then randomly separated into training and test data. All the images of these eyes were captured using optical coherence tomography and laser speckle flowgraphy to quantify the ocular structure and blood-flow-related parameters. A total of 91 parameters were extracted from each eye along with the patients' background information. Machine-learning classifiers, including the neural network (NN), naïve Bayes (NB), support vector machine (SVM), and gradient boosted decision trees (GBDT), were trained to build the classification models, and a hybrid feature selection method that combines minimum redundancy maximum relevance and genetic-algorithm-based feature selection was applied to find the most valid and relevant features for NN, NB, and SVM. A comparison of the performance of the three machine-learning classification models showed that the NN had the best classification performance with a validated accuracy of 87.8% using only nine ocular parameters. These selected quantified parameters enabled the trained NN to classify glaucomatous optic discs with relatively high performance without requiring color fundus images.