在具有事件发生时间终点的临床试验（例如子宫内膜癌试验）中，相当大比例的患者被治愈（或长期存活）的情况并不少见。在设计临床试验时，应采用混合治愈模型，充分考虑治愈分数。此前，混合治愈模型样本量计算是基于组间潜伏期分布的比例风险假设，并使用对数秩检验来推导样本量公式。在实际研究中，两组的延迟分布往往不满足比例风险假设。本文推导了以受限平均生存时间为主要终点的混合治疗模型的样本量计算公式，并进行了模拟和实例研究。限制性平均生存时间检验不受比例风险假设的影响，得到的治疗效果差异可以量化为生存时间增加或减少的年数（或月数），非常方便临床医患沟通。模拟结果表明，无论是否满足比例风险假设，混合物治愈模型的限制平均生存时间检验估计的样本量都是准确的，并且在大多数情况下小于对数秩检验估计的样本量。违反比例风险假设的情景。

It is not uncommon for a substantial proportion of patients to be cured (or survive long-term) in clinical trials with time-to-event endpoints, such as the endometrial cancer trial. When designing a clinical trial, a mixture cure model should be used to fully consider the cure fraction. Previously, mixture cure model sample size calculations were based on the proportional hazards assumption of latency distribution between groups, and the log-rank test was used for deriving sample size formulas. In real studies, the latency distributions of the two groups often do not satisfy the proportional hazards assumptions. This article has derived a sample size calculation formula for a mixture cure model with restricted mean survival time as the primary endpoint, and did simulation and example studies. The restricted mean survival time test is not subject to proportional hazards assumptions, and the difference in treatment effect obtained can be quantified as the number of years (or months) increased or decreased in survival time, making it very convenient for clinical patient-physician communication. The simulation results showed that the sample sizes estimated by the restricted mean survival time test for the mixture cure model were accurate regardless of whether the proportional hazards assumptions were satisfied and were smaller than the sample sizes estimated by the log-rank test in most cases for the scenarios in which the proportional hazards assumptions were violated.