Effects of input data on the performance of a neural network in distinguishing normal and glaucomatous visual fields
Effects of input data on the performance of a neural network in distinguishing normal and glaucomatous visual fields
复制标题
DOI：
10.1167/iovs.05-0175
复制
发表时间：
2005-10-01
影响因子：
4.4
通讯作者：
Heijl, A
中科院分区：
文献类型：
--
作者：
Bengtsson, B;Bizios, D;Heijl, A
目的。使用不同类型的数据输入：数值阈值灵敏度、Statpac总偏差和模式偏差，以及基于总偏差和模式偏差概率图的概率评分（Carl Zeiss Meditec, Inc., Dublin， CA），比较神经网络在周视青光眼诊断中的性能。纳入213名健康受试者、127名青光眼患者、68名青光眼合并白内障患者和41名白内障患者的SITA标准视野测试结果。将五种不同类型的输入数据输入到五个设计相同的人工神经网络中。针对每个网络调整网络阈值。构建受试者工作特征（ROC）曲线，以显示灵敏度和特异性的结合。以Pattern Deviation probability scores形式输入的数据效果最好，ROC曲线下面积为0.988，显著优于阈值敏感性和数值Total Deviation、Total Deviation probability得分（P < 0.001）。第二优结果为数值模式偏差面积为0.980。数据输入类型的选择对青光眼神经网络的诊断性能有重要影响。基于模式偏差的精炼输入数据比原始阈值产生更高的灵敏度和特异性。神经网络可能有很高的潜力，在生产有用的临床工具分类的视野测试。
PURPOSE. To compare the performance of neural networks for perimetric glaucoma diagnosis when using different types of data inputs: numerical threshold sensitivities, Statpac Total Deviation and Pattern Deviation, and probability scores based on Total and Pattern Deviation probability maps (Carl Zeiss Meditec, Inc., Dublin, CA).METHODS. The results of SITA Standard visual field tests in 213 healthy subjects, 127 patients with glaucoma, 68 patients with concomitant glaucoma and cataract, and 41 patients with cataract only were included. The five different types of input data were entered into five identically designed artificial neural networks. Network thresholds were adjusted for each network. Receiver operating characteristic (ROC) curves were constructed to display the combinations of sensitivity and specificity.RESULTS. Input data in the form of Pattern Deviation probability scores gave the best results, with an area of 0.988 under the ROC curve, and were significantly better (P < 0.001) than threshold sensitivities and numerical Total Deviations and Total Deviation probability scores. The second best result was obtained with numerical Pattern Deviations with an area of 0.980.CONCLUSIONS. The choice of type of data input had important effects on the performance of the neural networks in glaucoma diagnosis. Refined input data, based on Pattern Deviations, resulted in higher sensitivity and specificity than did raw threshold values. Neural networks may have high potential in the production of useful clinical tools for the classification of visual field tests.