Department of Industrial & Management Engineering, POSTECH, Pohang, South Korea.
Kyung Hee University Hospital at Gangdong, College of Medicine, Kyung Hee University, Seoul, South Korea.
Artif Intell Med. 2019 Mar;94:110-116. doi: 10.1016/j.artmed.2019.02.006. Epub 2019 Feb 25.
Visual field testing via standard automated perimetry (SAP) is a commonly used glaucoma diagnosis method. Applying machine learning techniques to the visual field test results, a valid clinical diagnosis of glaucoma solely based on the SAP data is provided. In order to reflect structural-functional patterns of glaucoma on the automated diagnostic models, we propose composite variables derived from anatomically grouped visual field clusters to improve the prediction performance. A set of machine learning-based diagnostic models are designed that implement different input data manipulation, dimensionality reduction, and classification methods.
Visual field testing data of 375 healthy and 257 glaucomatous eyes were used to build the diagnostic models. Three kinds of composite variables derived from the Garway-Heath map and the glaucoma hemifield test (GHT) sector map were included in the input variables in addition to the 52 SAP visual filed locations. Dimensionality reduction was conducted to select important variables so as to alleviate high-dimensionality problems. To validate the proposed methods, we applied four classifiers-linear discriminant analysis, naïve Bayes classifier, support vector machines, and artificial neural networks-and four dimensionality reduction methods-Pearson correlation coefficient-based variable selection, Markov blanket variable selection, the minimum redundancy maximum relevance algorithm, and principal component analysis- and compared their classification performances.
For all tested combinations, the classification performance improved when the proposed composite variables and dimensionality reduction techniques were implemented. The combination of total deviation values, the GHT sector map, support vector machines, and Markov blanket variable selection obtains the best performance: an area under the receiver operating characteristic curve (AUC) of 0.912.
A glaucoma diagnosis model giving an AUC of 0.912 was constructed by applying machine learning techniques to SAP data. The results show that dimensionality reduction not only reduces dimensions of the input space but also enhances the classification performance. The variable selection results show that the proposed composite variables from visual field clustering play a key role in the diagnosis model.
通过标准自动视野计（SAP）进行视野测试是一种常用的青光眼诊断方法。通过将机器学习技术应用于视野测试结果，可以仅基于 SAP 数据提供有效的临床青光眼诊断。为了在自动诊断模型中反映青光眼的结构-功能模式，我们提出了从解剖分组的视野聚类中派生的组合变量，以提高预测性能。设计了一组基于机器学习的诊断模型，这些模型实现了不同的输入数据操作、降维和分类方法。
使用 375 只健康眼和 257 只青光眼眼的视野测试数据来构建诊断模型。除了 52 个 SAP 视野位置外，输入变量中还包括从加威-希思图和青光眼半视野测试（GHT）扇区图派生的三种组合变量。进行降维以选择重要变量，以缓解高维问题。为了验证所提出的方法，我们应用了四种分类器——线性判别分析、朴素贝叶斯分类器、支持向量机和人工神经网络，以及四种降维方法——基于皮尔逊相关系数的变量选择、马尔可夫毯变量选择、最小冗余最大相关性算法和主成分分析，并比较了它们的分类性能。
对于所有测试组合，当实施所提出的组合变量和降维技术时，分类性能得到了提高。总偏差值、GHT 扇区图、支持向量机和马尔可夫毯变量选择的组合获得了最佳性能：接收器工作特征曲线（AUC）下的面积为 0.912。
通过将机器学习技术应用于 SAP 数据，构建了一个 AUC 为 0.912 的青光眼诊断模型。结果表明，降维不仅降低了输入空间的维度，而且提高了分类性能。变量选择结果表明，从视野聚类中提出的组合变量在诊断模型中起着关键作用。
