中药治疗2型糖尿病随机对照试验效应指标把握度的调查研究  

An Investigation of the Statistical Power of the Effect Size in Randomized Controlled Trials for the Treatment of Patients with Type 2 Diabetes Mellitus Using Chinese Medicine

作　　者：马立新[1] 刘建平[1] 

机构地区：[1]北京中医药大学循证医学中心,北京100029

出　　处：《中国中西医结合杂志》2012年第1期119-123,共5页Chinese Journal of Integrated Traditional and Western Medicine

基　　金：国家重点基础研究发展计划(973计划)课题资助(No.2006CB504602);科技部国际合作项目(No.2009DFA31460)

摘　　要：目的调查国内中药治疗2型糖尿病的随机对照试验(randomized controlled trials,RCTs)的效应值大小是否基于足够的样本含量以及充分的把握度。方法系统检索中国知网、中国生物医学文献数据库、维普、万方数据库,筛选、纳入干预时间≥3个月的中药治疗2型糖尿病RCTs。两人独立提取样本量等研究信息。根据样本量计算公式推算效应值大小的把握度。结果共纳入207项中药治疗2型糖尿病RCTs研究。在111项优效性试验中,报告糖化血红蛋(glycosylated hemoglobin HbA1c,HbA1c)及空腹血糖(fasting plasma glucose,FPG)而且样本总数>150的RCTs研究,分别占9%及12%,HbA1c把握度>80%的试验仅占10%,FPG把握度>80%的试验仅占23%。96项非劣效试验中,报告HbA1c及FPG而且样本总数>150的RCTs研究分别为31%及36%;HbA1c把握度>80%的试验占36%;FPG把握度达到80%的试验仅占27%。结论中药治疗2型糖尿病RCTs的样本量大多数未达到统计学要求的80%把握度,故其结果和结论的信度有限。建议今后的临床试验应明确研究目的并建立假说,据此选择合理的设计类型和结局效应指标,估算恰当的试验样本量。Objective To investigate whether the power of the effect size was based on adequate sample size in randomized controlled trials （RCTs） for the treatment of patients with type 2 diabetes mellitus （T2DM） using Chinese medicine. Methods China Knowledge Resource Integrated Database （CNKI）, VIP Database for Chinese Technical Periodicals （VIP）, Chinese Biomedical Database （CBM）, and Wangfang Data were system- atically recruited using terms like ＂Xiaoke＂ or diabetes, Chinese herbal medicine, patent medicine, traditional Chinese medicine, randomized, controlled, blinded, and placebo-controlled. Limitation was set on the interven- tion course I〉3 months in order to identify the information of outcome assessement and the sample size. Data col- lection forms were made according to the checking lists found in the CONSORT statement. Independent double data extractions were performed on all included trials. The statistical power of the effects size for each RCT study was assessed using sample size calculation equations. Results （1） A total of 207 RCTs were included, including 111 superiority trials and 96 non-inferiority trials. （2） Among the 111 superiority trials, fasting plasma glucose （FPG） and glycosylated hemoglobin HbAlc （HbAlc） outcome measure were reported in 9% and 12% of the RCTs respectively with the sample size 〉 150 in each trial. For the outcome of HbAlc, only 10% of the RCTs had more than 80% power. For FPG, 23% of the RCTs had more than 80% power. （3） In the 96 non-inferiority trials, the outcomes FPG and HbAlc were reported as 31% and 36% respectively. These RCTs had a samples size 〉 150. For HbAlc only 36% of the RCTs had more than 80% power. For FPG, only 27% of the studies had more than 80% power. Conclusions The sample size for statistical analysis was distressingly low and most RCTs did not achieve 80% power. In order to obtain a sufficient statistic power, it is recommended that clinical trials should establish clear research objective and hypothesis fir

关 键 词：2型糖尿病 随机对照试验 样本含量 效应指标 把握度 

分 类 号：R259[医药卫生—中西医结合]