Yang Z J, Lyu J J, Hou Y W, Chen Z
Department of Biostatistics, School of Public Health, Southern Medical University, Guangzhou 510515, China.
Department of Statistics, School of Economics, Jinan University, Guangzhou 510632, China.
Zhonghua Liu Xing Bing Xue Za Zhi. 2019 Feb 10;40(2):247-250. doi: 10.3760/cma.j.issn.0254-6450.2019.02.023.
In clinical follow-up studies, hazard ratio () is routinely used to quantify the differences between-groups, however, it is being estimated by the Cox procedure. , the ratio of two hazard functions has abstract meaning only and is in lack of the context to give an intuitive explanation of the survival of patients and the assumption of proportional hazards () must be satisfied. Under this context, the restricted mean survival time () can be used as a relatively effective measure or index of statistics. This paper introduces the -based statistical analysis methods, including estimation of and its difference, hypothesis testing and regression analysis. The application of in data analysis is also introduced. All the evidence demonstrates that can be used as an effective analytical tool with straightforward interpretation. is also more effective than in comparing differences between groups, when non- is observed. Therefore, is suggested to be stated along with in the process of disease efficacy evaluation and prognosis analysis. Cooperation and complement of the two, a precise reflection on the characteristics of data can be expected.
在临床随访研究中，风险比（HR）通常用于量化组间差异，然而，它是通过Cox方法进行估计的。HR，即两个风险函数的比值，只有抽象的意义，缺乏对患者生存情况进行直观解释的背景，并且必须满足比例风险假设（PH）。在此背景下，受限平均生存时间（RMST）可作为一种相对有效的统计量度或指标。本文介绍了基于RMST的统计分析方法，包括RMST及其差异的估计、假设检验和回归分析。还介绍了RMST在数据分析中的应用。所有证据表明，RMST可作为一种具有直接解释的有效分析工具。在观察到非PH时，RMST在比较组间差异方面也比HR更有效。因此，建议在疾病疗效评估和预后分析过程中同时陈述RMST和HR。两者相互协作与补充，有望精确反映数据特征。
