Building on Yu and Kumbier's PCS framework and for randomized experiments, we introduce a novel methodology for Stable Discovery of Interpretable Subgroups via Calibration (StaDISC), with large heterogeneous treatment effects. StaDISC was developed during our re-analysis of the 1999-2000 VIGOR study, an 8076 patient randomized controlled trial (RCT), that compared the risk of adverse events from a then newly approved drug, Rofecoxib (Vioxx), to that from an older drug Naproxen. Vioxx was found to, on average and in comparison to Naproxen, reduce the risk of gastrointestinal (GI) events but increase the risk of thrombotic cardiovascular (CVT) events. Applying StaDISC, we fit 18 popular conditional average treatment effect (CATE) estimators for both outcomes and use calibration to demonstrate their poor global performance. However, they are locally well-calibrated and stable, enabling the identification of patient groups with larger than (estimated) average treatment effects. In fact, StaDISC discovers three clinically interpretable subgroups each for the GI outcome (totaling 29.4% of the study size) and the CVT outcome (totaling 11.0%). Complementary analyses of the found subgroups using the 2001-2004 APPROVe study, a separate independently conducted RCT with 2587 patients, provides further supporting evidence for the promise of StaDISC.

中文翻译：

---

通过因果研究中的校准稳定发现可解释的亚组

在 Yu 和 Kumbier 的 PCS 框架和随机实验的基础上，我们引入了一种通过校准（StaDISC）稳定发现可解释子组的新方法，具有较大的异质治疗效果。StaDISC 是在我们对 1999-2000 年 VIGOR 研究（一项 8076 名患者随机对照试验 (RCT)）的重新分析期间开发的，该试验将当时新批准的药物罗非昔布（Vioxx）的不良事件风险与较老的药物的不良事件风险进行了比较。药物萘普生。平均而言，与萘普生相比，万络可降低胃肠 (GI) 事件的风险，但会增加血栓性心血管 (CVT) 事件的风险。应用 StaDISC，我们为这两个结果拟合了 18 个流行的条件平均治疗效果 (CATE) 估计器，并使用校准来证明它们的整体性能不佳。然而，它们在本地经过良好校准且稳定，能够识别出治疗效果大于（估计）平均效果的患者组。事实上，StaDISC 发现了三个临床可解释的亚组，每个亚组分别用于 GI 结果（总计占研究规模的 29.4%）和 CVT 结果（总计 11.0%）。使用 2001-2004 APPROVe 研究对发现的亚组进行补充分析，这是一项单独独立进行的随机对照试验，涉及 2587 名患者，为 StaDISC 的前景提供了进一步的支持证据。