mCART 可减少随机试验中亚组治疗的错误发现
该研究提出一种新方法 mCART,在识别异质性治疗效应(HTE)亚组时使协变量保持平衡。模拟试验显示,在无 HTE 情形下 mCART 未识别任何亚组,而逻辑回归、随机森林和梯度随机森林均产生假阳性;在有 HTE 情形下 mCART 能捕获真实亚组且协变量绝对标准化差异均小于 0.2。
要点
- 协变量不平衡可能导致亚组分析出现假阳性
- 无 HTE 时 mCART 未发现亚组,其他方法均出现假阳性
- mCART 识别的亚组协变量绝对标准化差异均小于 0.2
核心结论
- 协变量不平衡可能使亚组分析产生假阳性,mCART 有助于在随机试验数据的二次分析中防止 HTE 亚组的错误发现。
研究设计与样本
- 方法学研究,提出匹配加分类回归树(mCART)方法,并与逻辑回归(LR,基于 AIC 的后向协变量选择)、随机森林(RF)和梯度随机森林在模拟数据中比较。
- 模拟包括 N=200 的 II 期肿瘤试验(无 HTE 或两个 HTE 亚组)和 N=6000 的 III 期心血管病试验(无 HTE、四个 HTE 亚组,或无平均治疗效应但有四个 HTE 亚组),结局为二分类且真实 HTE 亚组已知。
主要发现
- 模拟 1A 和 2A(无 HTE)中,mCART 未识别任何 HTE 亚组,LR 分别发现 2 和 448 个,RF 发现 5 和 2 个,梯度 RF 发现 5 和 24 个,均为假阳性。
- 模拟 1B 中 mCART 未能识别两个真实 HTE 亚组,LR 发现 4 个、RF 发现 6 个、梯度 RF 发现 10 个,其中一半或更多为假阳性。
- 模拟 2B 和 2C 中 mCART 捕获四个真实 HTE 亚组,其他方法仅发现假阳性。
关键数值与推荐
- mCART 识别的所有 HTE 亚组治疗组与对照组协变量平衡可接受,绝对标准化差异小于 0.2。
- LR、RF 和梯度 RF 的绝对标准化差异通常超过 0.2,提示其识别的亚组存在协变量不平衡,假阳性可能源于混杂。
临床怎么用
- 在随机试验数据的亚组二次分析中,可考虑使用 mCART 以减少因协变量不平衡导致的 HTE 假阳性发现。
局限性
- mCART 在模拟 1B 中未能识别两个真实 HTE 亚组。
- 证据来自模拟研究,尚需进一步验证。
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
BACKGROUND: Heterogeneous treatment effects (HTEs), or systematic differences in treatment effectiveness among participants with different observable features, may be important when applying trial results to clinical practice. Current methods suffer from a potential for false detection of HTEs due to imbalances in covariates between candidate subgroups. METHODS: We introduce a new method, matching plus classification and regression trees (mCART), that yields balance in covariates in identified HTE subgroups. We compared mCART to a classical method (logistic regression [LR] with backwards covariate selection using the Akaike information criterion ) and two machine-learning approaches increasingly applied to HTE detection (random forest [RF] and gradient RF) in simulations with a binary outcome with known HTE subgroups. We considered an N = 200 phase II oncology trial where there were either no HTEs (1A) or two HTE subgroups (1B) and an N = 6000 phase III cardiovascular disease trial where there were either no HTEs (2A) or four HTE subgroups (2B). Additionally, we considered an N = 6000 phase III cardiovascular disease trial where there was no average treatment effect but there were four HTE subgroups (2C). RESULTS: In simulations 1A and 2A (no HTEs), mCART did not identify any HTE subgroups, whereas LR found 2 and 448, RF 5 and 2, and gradient RF 5 and 24, respectively (all false positives). In simulation 1B, mCART failed to identify the two true HTE subgroups whereas LR found 4, RF 6, and gradient RF 10 (half or more of which were false positives). In simulations 2B and 2C, mCART captured the four true HTE subgroups, whereas the other methods found only false positives. All HTE subgroups identified by mCART had acceptable treated vs. control covariate balance with absolute standardized differences less than 0.2, whereas the absolute standardized differences for the other methods typically exceeded 0.2. The imbalance in covariates in identified subgroups for LR, RF, and gradient RF indicates the false HTE detection may have been due to confounding. CONCLUSIONS: Covariate imbalances may be producing false positives in subgroup analyses. mCART could be a useful tool to help prevent the false discovery of HTE subgroups in secondary analyses of randomized trial data.
引用
- Rigdon J, Baiocchi M, Basu S, et al. Preventing false discovery of heterogeneous treatment effect subgroups in randomized trials. Trials. 2018. PMID: 30012181. doi:10.1186/s13063-018-2774-5
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。