Technical University of Munich, School of Medicine, Institute of Medical Informatics, Statistics and Epidemiology, Ismaninger Str. 22, 81675 Munich, Germany.
Comput Math Methods Med. 2019 Jun 13;2019:7037230. doi: 10.1155/2019/7037230. eCollection 2019.
Identification of relevant biomarkers that are associated with a treatment effect is one requirement for adequate treatment stratification and consequently to improve health care by administering the best available treatment to an individual patient. Various statistical approaches were proposed that allow assessing the interaction between a continuous covariate and treatment. Nevertheless, categorization of a continuous covariate, e.g., by splitting the data at the observed median value, appears to be very prevalent in practice. In this article, we present a simulation study considering data as observed in a randomized clinical trial with a time-to-event outcome performed to compare properties of such approaches, namely, Cox regression with linear interaction, Multivariable Fractional Polynomials for Interaction (MFPI), Local Partial-Likelihood Bootstrap (LPLB), and the Subpopulation Treatment Effect Pattern Plot (STEPP) method, and of strategies based on categorization of continuous covariates (splitting the covariate at the median, splitting at quartiles, and using an "optimal" split by maximizing a corresponding test statistic). In different scenarios with no interactions, linear interactions or nonlinear interactions, type I error probability and the power for detection of a true covariate-treatment interaction were estimated. The Cox regression approach was more efficient than the other methods for scenarios with monotonous interactions, especially when the number of observed events was small to moderate. When patterns of the biomarker-treatment interaction effect were more complex, MFPI and LPLB performed well compared to the other approaches. Categorization of data generally led to a loss of power, but for very complex patterns, splitting the data into multiple categories might help to explore the nature of the interaction effect. Consequently, we recommend application of statistical methods developed for assessment of interactions between continuous biomarkers and treatment instead of arbitrary or data-driven categorization of continuous covariates.
确定与治疗效果相关的相关生物标志物是进行充分治疗分层的要求之一，从而通过向个体患者提供最佳可用治疗来改善医疗保健。已经提出了各种统计方法来评估连续协变量与治疗之间的相互作用。然而，连续协变量的分类，例如通过将数据在观察到的中位数处分割，在实践中似乎非常普遍。在本文中，我们进行了一项模拟研究，考虑了一项以时间为事件的结局进行的随机临床试验中的数据，以比较这些方法的特性，即具有线性交互作用的 Cox 回归，用于交互作用的多变量分数多项式（MFPI），局部部分似然引导（LPLB）和亚组治疗效果模式图（STEPP）方法，以及基于连续协变量分类的策略（将协变量在中位数处分割，在四分位数处分割，以及通过最大化相应的检验统计量来使用“最佳”分割）。在没有相互作用，线性相互作用或非线性相互作用的不同情况下，估计了零假设错误概率和检测真实协变量-治疗相互作用的功效。对于具有单调相互作用的情况，Cox 回归方法比其他方法更有效，尤其是当观察到的事件数量较少到中等时。当生物标志物-治疗相互作用效果的模式更复杂时，MFPI 和 LPLB 与其他方法相比表现良好。数据的分类通常会导致功效损失，但是对于非常复杂的模式，将数据分成多个类别可能有助于探索相互作用效果的性质。因此，我们建议应用为评估连续生物标志物和治疗之间的相互作用而开发的统计方法，而不是任意或基于数据的连续协变量分类。
Zotero 插件
