靶向临床试验全随机设计四种分析策略的比较  

Comparison of four testing strategies for all-randomized design in targeted clinical trials

作　　者：徐昌榕 柏建岭 陈梦锴[1] 陈峰 魏永越 赵杨[1,2] 黄丽红 蔡晶晶[1] 于浩 XU Changrong;BAI Jianling;CHEN Mengkai;CHEN Feng;WEI Yongyue;ZHAO Yang;HUANG Lihong;CAI Jingjing;YU Hao(Department of Biostatistics,School of Public Health,Nanjing Medical University,Nanfing 211166,Jiangsu,China;Key Laboratory of Biomedical Big data of Nanfing Medical University,Nanjing 211166,Jiangsu,China)

机构地区：[1]南京医科大学公共卫生学院,生物统计学系,江苏南京211166 [2]南京医科大学生物医学大数据重点实验室,江苏南京211166

出　　处：《中国临床药理学与治疗学》2018年第7期782-789,共8页Chinese Journal of Clinical Pharmacology and Therapeutics

基　　金：国家自然科学基金(81773554);国家自然科学基金青年基金(81302512);江苏省青蓝工程、江苏省高校优势学科建设工程、江苏高校品牌专业建设工程资助项目(PPZY2015A067)

摘　　要：目的:探讨靶向临床试验全随机设计四种分析策略的统计学性能,为靶向药物研究分析方法的选择提供依据。方法:采用蒙特卡罗方法模拟数据,在不同参数组合下,比较序贯亚组特异性策略、序贯标志物阳性和总人群策略、标志物序贯设计及倒退设计的Ⅰ类错误和检验效能。结果:在阳性亚组分析中,当人群标志物阳性率较高时,四种分析策略的检验效能的差别较小,当人群标志物阳性率较低时,若靶向药物在不同标志物状态人群中疗效差异较大,序贯亚组特异性策略、序贯标志物阳性和总人群策略及标志物序贯设计的检验效能较高,若疗效差异较小,倒退设计和标志物序贯设计的检验效能较高;序贯亚组特异性策略及序贯标志物阳性和总人群策略能控制Ⅰ类错误。在总人群分析中,当阳性率较高时,序贯亚组特异性策略和标志物序贯设计的检验效能较可靠,当阳性率较低,疗效差异较大时,标志物序贯设计的检验效能最高,疗效差异较小时,标志物序贯设计和序贯亚组特异性策略的检验效能较好且差异不大。结论:在靶向治疗药物的全随机临床试验研究中,探寻靶向药物对阳性人群疗效时,宜采用序贯亚组特异性策略及序贯标志物阳性和总人群策略,仅当明确得知靶向药物在不同标志物状态的人群疗效的差异较小且人群标志物阳性率较低时,倒退设计是最优方法;而研究总人群疗效时,首要推荐标志物序贯设计。AIM：To evaluate statistical per-formance of four testing strategies for all-randomized design in targeted clinical trials and to provide basis for the selection of analysis methods in targeted drugs research.METHODS：Simulating the data based on Monte Carlo Method and comparing type Ⅰerror rate and power of sequential subgroup-specific strategy,sequential biomarker-positive and overall population strategy,marker sequential test design and fall-back design under different parameters.RESULTS：When the biomarker-positive prevalence is high,there is little difference in power of the four strategies for the positive subgroup analysis.While in the overall population analysis,sequential subgroup-specific strategy and Ma ST have higher power.When the biomarker-positive prevalence is low,if the efficacy of targeted drugs in different marker-status populations is quite different,in the positive subgroup analysis,sequential subgroup-specific strategy,sequential biomarker-positive and overall population strategy and Ma ST have higher power,and Ma ST has highest power in the overall.If the targeted drugs in the different markers of the state of the crowd less difference,fall-back design and Ma ST have higher power in the positive subgroup analysis and power of sequential subgroup-specific strategy and Ma ST is higher in the overall analysis.Sequential subgroup-specific strategy and sequential biomarker-positive and overall population strategy can control type Ⅰerror in the positive subgroup analysis.CONCLUSION：In the all-randomized clinical trials of targeted drugs,exploring the efficacy of targeted drugs in the positive population,we recommend sequential subgroup-specific strategy and sequential biomarker-positive and overall population strategy,and fall-back design is the optimal approach only if there is a clear difference between the efficacy of the targeted drugs in different marker populations and the low positive rate of the population marker.While Ma ST is the first recommended design in the overall populati

关 键 词：靶向临床试验 全随机设计 分析策略 Ⅰ类错误 检验效能 

分 类 号：R969.4[医药卫生—药理学]