Comparison of machine learning and traditional classifiers in glaucoma diagnosis
Comparison of machine learning and traditional classifiers in glaucoma diagnosis
复制标题
DOI：
10.1109/tbme.2002.802012
复制
发表时间：
2002-09-01
影响因子：
4.6
通讯作者：
Sejnowski, ATJ
中科院分区：
文献类型：
--
作者：
Chan, KL;Lee, TW;Sejnowski, ATJ
青光眼是一种进行性视神经病变，其特征性结构变化反映在视野中。视野敏感度测试通常用于临床环境中以评估青光眼。标准自动视野检查（SAP）是一种常见的计算机化视野检查，其输出可用于机器学习。我们比较了许多机器学习算法的性能与STATPAC指标平均偏差，模式标准偏差和校正模式标准偏差。所研究的机器学习算法包括多层感知器（MLP）、支持向量机（SVM）、线性判别分析（LDA）和二次判别分析（QDA）、Parzen窗、混合高斯（MOG）和混合广义高斯（MGG）。MLP和SVM是直接在决策边界上工作的分类器，属于判别范式。生成式分类器首先对数据概率密度进行建模，然后通过贝叶斯规则执行分类，通常可以更深入地了解数据空间的结构。我们应用MOG、MGG、LDA、QDA和Parzen窗对SAP青光眼进行了分类。通过受试者工作特征曲线下的面积和所选特异性（真阴性率）下的灵敏度（真阳性率）比较各种分类器的性能。机器学习类型的分类器显示出比STATPAC的最佳指标更好的性能。前向选择和后向消除方法进一步提高了分类率，并有可能通过减少视野位置测量的数量来减少测试时间。
Glaucoma is a progressive optic neuropathy with characteristic structural changes in the optic nerve head reflected in the visual field. The visual-field sensitivity test is commonly used in a clinical setting to evaluate glaucoma. Standard automated perimetry (SAP) is a common computerized visual-field test whose output is amenable to machine learning. We compared the performance of a number of machine learning algorithms with STATPAC indexes mean deviation, pattern standard deviation, and corrected pattern standard deviation. The machine learning algorithms studied, included multilayer perceptron (MLP), support vector machine (SVM), and linear (LDA) and quadratic discriminant analysis (QDA), Parzen window, mixture of Gaussian (MOG), and mixture of generalized Gaussian (MGG). MLP and SVM are classifiers that work directly on the decision boundary and fall under the discriminative paradigm. Generative classifiers, which first model the data probability density and then perform classification via Bayes' rule, usually give deeper insight into the structure of the data space. We have applied MOG, MGG, LDA, QDA, and Parzen window to the classification of glaucoma from SAP. Performance of the various classifiers was compared by the areas under their receiver operating characteristic curves and by sensitivities (true-positive rates) at chosen specificities (true-negative rates). The machine-learning-type classifiers showed improved performance over the best indexes from STATPAC. Forward-selection and backward-elimination methodology further improved the classification rate and also has the potential to reduce testing time by diminishing the number of visual-field location measurements.