用于支持药械注册的现实世界研究统计学思考

Statistical considerations for real world studies supporting new drug registrations

目的探讨现实世界研究(RWS)获得现实世界证据(RWE)的统计学问题。方法对现实世界数据(RWD),RWS的因果推断方法及RWE的评价方式进行总结,分析现存问题。结果获得可靠的RWE用于支持药械监管是RWS的重要目标,适当的RWD通用标准是进行数据质量评价的前提,规范化的数据治理和完善的数据质量评价体系是规范开展RWS的基础,因果推断方法的规范化实施是获得可靠RWE的质量保障,临床上可解释的、有创新性价值的结论是RWE的首要前提,在具体实践中需要客观的RWE判定标准,RWS结果的可验证性是不可忽视的RWE的重要特征。结论单一的临床研究往往无法满足因果关系的判定标准,需要多个研究从不同角度加以验证,RWS与随机对照试验(RCT)互为验证的因果推断研发模式值得推广。

Objective To review statistics-related problems in the process of obtaining real world evidence(RWE)from real world research(RWS).Methods In regard to real world data(RWD),causal inference methods for RWS and approaches to RWE evaluation were reviewed while the existing problems were analyzed and discussed.Results Obtaining reliable RWE that could be used to support regulatory decisions about medical products was an important goal of RWS.An appropriate standard for RWD data was a prerequisite for quality evaluation of the data.A standardized process of data governance and a perfect system for data quality evaluation underlay high-quality RWS.Standardized implementation of causal inference analytical methods could ensure the quality of RWE.Clinically explicable and innovative conclusions were critical to RWE.Objective criteria for evaluation of RWE were also needed in practice.The verifiability of results of RWS was the most important feature of RWE.Conclusion A single clinical trial is often unable to meet the criteria for determining causality.Instead,multiple studies are required to verify causality from different perspectives.Therefore,the combination of randomized controlled trials(RCT)and RWS is a good approach during drug development.