The cut off point for PG and OPN was determined using receiver operator characteristics curves ( ROC ). 应用受试者工作特征曲线(ROC)确定PG联合OPN筛查胃癌的检验效率。
Receiver operator characteristics curve tests demonstrate that the performance of neural network ensembles is better than that of single neural networks. 受试者特征曲线测试表明,神经网络集成性能优于单个神经网络。