Issues for statisticians in conducting analyses and translating results for quality of life end points in clinical trials.
Issues for statisticians in conducting analyses and translating results for quality of life end points in clinical trials.
复制标题
DOI：
10.1081/bip-120028507
复制
发表时间：
2004-02-01
影响因子：
1.1
通讯作者：
Dueck, A
中科院分区：
文献类型：
--
作者：
Sloan, J A;Dueck, A
药物临床试验中的生活质量（QOL）终点正处于十字路口。一方面，近年来已经学到了很多关于如何有效地测量患者QOL的知识。另一方面，研究人员和监管机构仍然在努力准确地评估QOL终点的结果和其他患者报告的结果。统计学家经常不得不在希望评估患者QOL的研究者和希望获得合理科学依据和分析计划的监管机构之间架起差距。不幸的是，很少有专门为统计受众撰写的文章来帮助翻译。本文的目的就是试图弥合这一差距。我们将描述成功地将心理测量和统计挑战转化为调查人员和监管机构可以理解的结果的语言和方法。最重要的进展之一是制定了评估临床意义的通用指南，即基于经验规则效应量（ERES）方法的“半标准差”方法。我们用具体的例子来填充这篇论文，说明在统计分析方面，生活质量数据与肿瘤反应或其他临床终点数据相比，不需要有任何不同的处理。
Quality of life (QOL) end points in pharmaceutical clinical trials are at a crossroads. On the one hand, much has been learned in recent years of how to efficiently and effectively measure patient QOL. On the other hand, investigators and regulatory agencies still struggle with exactly how to assess the results of QOL end points and other patient-reported outcomes. Statisticians are often left in the position of having to bridge the gap between investigators who want to assess patient QOL and regulatory bodies who want a sound scientific rationale and analysis plan for doing so. Unfortunately, little has been written specifically for the statistical audience to assist in this translation. The purpose of this paper is to attempt to bridge this gap. We will describe the language and methods that have been successful in translating the psychometric and statistical challenges into understandable findings for investigators and regulatory agencies. One of the most important advances is the development of a general guideline for assessing clinical significance, namely the "half standard deviation" method based on the empirical rule effect size (ERES) approach. We populate the paper with concrete examples of how QOL data need not be treated any different, in terms of statistical analysis, than tumor response or other clinical end points.