Tourassi G D, Floyd C E
Department of Radiology, Duke University Medical Center, Durham, North Carolina, USA.
Med Decis Making. 1997 Apr-Jun;17(2):186-92. doi: 10.1177/0272989X9701700209.
To study the effect of data sampling on the predictive assessment of artificial neural networks (ANNs) for medical diagnostic tasks.
Three statistical techniques were used to evaluate the diagnostic performances of ANNs: 1) cross validation, 2) round robin, and 3) bootstrap. These techniques are different sampling plans designed to reduce the small-sample estimation bias and variance contributions. The study was based on two networks, one developed for the diagnosis of pulmonary embolism (1,064 cases) and the other developed for the diagnosis of breast cancer (206 cases).
The three sampling techniques produced different performance estimates for both networks. The estimates varied substantially depending on the training sample size and the training-stopping criterion.
The predictive assessment of ANNs in medical diagnosis can vary substantially based on the complexity of the problem, the data sampling technique, and the number of cases available.
研究数据采样对人工神经网络（ANNs）在医学诊断任务预测评估中的影响。
使用三种统计技术来评估人工神经网络的诊断性能：1）交叉验证，2）循环法，以及3）自助法。这些技术是不同的采样计划，旨在减少小样本估计偏差和方差贡献。该研究基于两个网络，一个是为诊断肺栓塞而开发的（1064例），另一个是为诊断乳腺癌而开发的（206例）。
这三种采样技术对两个网络产生了不同的性能估计。估计值根据训练样本大小和训练停止标准有很大差异。
人工神经网络在医学诊断中的预测评估可能会因问题的复杂性、数据采样技术和可用病例数量而有很大差异。
