探索随机试验中疗效最佳区间的一种方法
该研究以一项纳入2521例心力衰竭患者的里程碑式随机试验为例,展示如何通过分层或匹配分析识别治疗效应可能被放大的疾病严重程度中间区间。总体风险比为0.75(95%CI 0.63-0.89),但疾病严重程度中间五分位组的风险比为0.48(95%CI 0.29-0.79),提示该区间可能存在更明显的生存获益。
要点
- 常规随机试验总体分析可能掩盖中间疾病严重程度区间的更大治疗效应。
- 分层分析显示中间五分位组风险比0.48,优于总体风险比0.75。
- 疾病最严重患者风险比0.89(95%CI 0.69-1.15),获益解释有限。
核心结论
- 通过分层或匹配方法分析随机试验,有助于识别治疗效应可能被放大的潜在最佳区间。
研究设计与样本
- 回顾性分析一项里程碑式随机试验,纳入2521例心力衰竭患者,比较植入式除颤器与对照组的死亡率。
主要发现
- 除颤器组死亡比例为22%(182/829),对照组为29%(484/1692)。
- 总体比例风险分析显示风险比为0.75(95%CI 0.63-0.89)。
- 分层分析显示疾病严重程度中间五分位组风险比为0.48(95%CI 0.29-0.79)。
- 疾病最严重患者风险比为0.89(95%CI 0.69-1.15)。
- 粗分析与分层分析之间的差异可通过图形展示,并可通过匹配比较复现。
临床怎么用
- 在分析随机试验时,可考虑采用分层或匹配方法探索治疗效应的异质性,识别潜在最佳获益区间。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: The objective of the study was to demonstrate how a conventional randomized trial can be analyzed through a stratified or a matched approach to identify a potential sweet spot where observed differences might be accentuated in the mid range of disease severity. DESIGN AND SETTING: We review a landmark randomized trial of heart failure patients that tested whether implantable defibrillators reduce mortality (n = 2,521). RESULTS: Overall, 22% (182/829) of the patients in the defibrillator group died compared with 29% (484/1,692) of patients in the control group. Proportional hazards analysis yielded a modest 25% survival benefit (hazard ratio = 0.75, 95% confidence interval: 0.63 to 0.89). Stratified analysis of the trial yielded a larger 52% survival benefit for those in the middle quintile of disease severity (hazard ratio = 0.48, 95% confidence interval: 0.29 to 0.79). In contrast, little of the survival benefit was explained by patients with the greatest disease severity (hazard ratio = 0.89, 95% confidence interval: 0.69 to 1.15). The discrepancy between crude and stratified analyses could be visualized by graphical displays and replicated with matched comparisons. CONCLUSION: Our approach for analyzing a randomized trial could help identify a potential sweet spot of an accentuated treatment effect.
引用
- Redelmeier DA, Tibshirani RJ. An approach to explore for a sweet spot in randomized trials. J Clin Epidemiol. 2019. PMID: 31874202. doi:10.1016/j.jclinepi.2019.12.012
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。