Clinical positron emission tomography (PET) research is costly and entails exposing participants to radioactivity. Researchers should therefore aim to include just the number of subjects needed to fulfill the purpose of the study, no more, no less. In this tutorial we show how to apply sequential Bayes Factor testing in order to stop the recruitment of subjects in a clinical PET study as soon as enough data have been collected to make a conclusion. We evaluate this framework in two common PET study designs: a cross-sectional (e.g., patient-control comparison) and a paired-sample design (e.g., pre-intervention-post scan comparison). By using simulations, we show that it is possible to stop a clinical PET study early, both when there is an effect and when there is no effect, while keeping the number of erroneous conclusions at acceptable levels. Based on the results we recommend settings for a sequential design that are appropriate for commonly seen sample sizes in clinical PET-studies. Finally, we apply sequential Bayes Factor testing to a real PET data set and show that it is possible to obtain support in favor of an effect while simultaneously reducing the sample size with 30%. Using this procedure allows researchers to reduce expense and radioactivity exposure for a range of effect sizes relevant for PET research.

中文翻译：

---

早期停止临床 PET 研究：如何减少费用和暴露

临床正电子发射断层扫描 (PET) 研究成本高昂，并且需要让参与者接触放射性。因此，研究人员的目标应该是仅包括完成研究目的所需的受试者数量，不多也不少。在本教程中，我们将展示如何应用顺序贝叶斯因子测试，以便在收集到足够的数据以得出结论后立即停止在临床 PET 研究中招募受试者。我们在两种常见的 PET 研究设计中评估该框架：横断面（例如，患者对照比较）和配对样本设计（例如，干预前 - 扫描后比较）。通过使用模拟，我们表明可以在有效果和没有效果时及早停止临床 PET 研究，同时将错误结论的数量保持在可接受的水平。基于这些结果，我们推荐适合临床 PET 研究中常见样本量的顺序设计设置。最后，我们将顺序贝叶斯因子测试应用于真实的 PET 数据集，并表明有可能获得有利于效果的支持，同时将样本量减少 30%。使用此程序可以让研究人员减少与 PET 研究相关的一系列效应大小的费用和放射性暴露。