Yamashita Toyoko S, Nuamah Isaac F, Dorsey Philip A, Hosseini-Nezhad Seyed M, Bielefeld Roger A, Kerekes Edward F, Singer Lynn T
Departments of Pediatrics and Epidemiology & Biostatistics, Case Westem Reserve University School of Medicine, Cleveland, Ohio 44106 U.S.A.
Biostatistics Unit, University of Pennsylvania Cancer Center, Philadelphia, Pennsylvania 19104 U.S.A.
Comput Med Public Health Biotechnol (1994). 1995;5(3):1469-1487.
Neural networks offer a powerful new approach to information processing through their ability to generalize from a specific training data set. The success of this approach has raised interesting new possibilities of incorporating statistical methodology in order to enhance their predictive ability. This paper reports on two complementary methods of prediction. one using neural networks and the other using traditional statistical methods. The two methods are compared on the basis of their prediction applied to standardized developmental infant outcome measures using preselected infant and maternal variables measured at birth. Three neural network algorithms were employed. In our study, no one network outperformed the other two consistently. The neural networks provided significantly better results than the regression model in terms of variation and prediction of extreme outcomes. Finally we demonstrated that selection of relevant input variables through statistical means can produce a reduced network structure with no loss in predictive ability.
神经网络通过其从特定训练数据集进行泛化的能力，为信息处理提供了一种强大的新方法。这种方法的成功引发了将统计方法纳入其中以增强其预测能力的有趣新可能性。本文报告了两种互补的预测方法。一种使用神经网络，另一种使用传统统计方法。基于应用于使用出生时测量的预选婴儿和母亲变量的标准化发育婴儿结局测量的预测，对这两种方法进行了比较。使用了三种神经网络算法。在我们的研究中，没有一个网络始终优于其他两个网络。在极端结局的变化和预测方面，神经网络提供的结果明显优于回归模型。最后，我们证明通过统计手段选择相关输入变量可以产生结构简化的网络，而不会损失预测能力。
