基于平均生存时间的两种分类方法的比较

The Comparative Analysis of Two Methods of Classification Based on Mean Survival Time

诸如疾病分类系统的预后预测和分类方法,常可用于帮助进行临床管理决策。同一疾病总体常可得到多种分类方法,因此有必要比较这些方法以确定最优分类,或者寻找不逊于最优分类的替代方法。本文基于约束平均寿命引入分离度指标来度量分类方法的预后分类效率,这个指标可用来比较以生存时间为结局的两种分类方法的功效,特别是用于非劣性和等效性检验。我们给出了基于配对数据的两个分离度的估计与检验方法。模拟结果提示,检验方法在适当的样本量条件下能够控制第一类错误。两个实例表明在医学临床中的应用。

Methods of prognostic prediction and classification, such as classification of disease, are commonly used to assist decision-making in clinical management. Multiple classification methods are often available for the same disease population. Comparison of these methods is necessary to identify the optimum classification for patient survival or to determine non-inferior alternatives to the optimum classification. This paper introduces an indicator-degree of separation（ DOS ） based on restricted mean lifetimes to measure the efficiency in prognostic separation by a classification method. This indicator could be used to compare the efficiency of two classification methods with survival time as the endpoint, especially for non-inferiority or equivalence test. The paper proposes estimating and testing procedures of two DOSs based on paired data. The simulation results suggest that the proposed testing procedure have a desired type one error under the circumstance of reasonable study sample sizes. Two clinical examples demonstrated its application in medical research.