Université Paris Cité and Université Sorbonne Paris Nord, Inserm, INRAE, Center for Research in Epidemiology and StatisticS (CRESS), Paris, France.
Cochrane France, Paris, France.
BMC Med Res Methodol. 2024 Mar 25;24(1):74. doi: 10.1186/s12874-024-02202-9.
One key aspect of personalized medicine is to identify individuals who benefit from an intervention. Some approaches have been developed to estimate individualized treatment effects (ITE) with a single randomized control trial (RCT) or observational data, but they are often underpowered for the ITE estimation. Using individual participant data meta-analyses (IPD-MA) might solve this problem. Few studies have investigated how to develop risk prediction models with IPD-MA, and it remains unclear how to combine those methods with approaches used for ITE estimation. In this article, we compared different approaches using both simulated and real data with binary and time-to-event outcomes to estimate the individualized treatment effects from an IPD-MA in a one-stage approach.
We compared five one-stage models: naive model (NA), random intercept (RI), stratified intercept (SI), rank-1 (R1), and fully stratified (FS), built with two different strategies, the S-learner and the T-learner constructed with a Monte Carlo simulation study in which we explored different scenarios with a binary or a time-to-event outcome. To evaluate the performance of the models, we used the c-statistic for benefit, the calibration of predictions, and the mean squared error. The different models were also used on the INDANA IPD-MA, comparing an anti-hypertensive treatment to no treatment or placebo ( , 836 events).
Simulation results showed that using the S-learner led to better ITE estimation performances for both binary and time-to-event outcomes. None of the risk models stand out and had significantly better results. For the INDANA dataset with a binary outcome, the naive and the random intercept models had the best performances.
For the choice of the strategy, using interactions with treatment (the S-learner) is preferable. For the choice of the method, no approach is better than the other.
个性化医学的一个关键方面是确定从干预中受益的个体。已经开发了一些方法来使用单个随机对照试验（RCT）或观察数据估计个体化治疗效果（ITE），但它们通常在 ITE 估计方面的功效不足。使用个体参与者数据荟萃分析（IPD-MA）可能会解决此问题。很少有研究调查如何使用 IPD-MA 开发风险预测模型，并且仍然不清楚如何将这些方法与用于 ITE 估计的方法相结合。在本文中，我们使用模拟和真实数据（具有二分类和生存结局）比较了不同的方法，以在单阶段方法中从 IPD-MA 估计个体化治疗效果。
我们比较了五种单阶段模型：朴素模型（NA）、随机截距（RI）、分层截距（SI）、秩一（R1）和完全分层（FS），使用两种不同的策略构建，即 S-learner 和 T-learner，通过蒙特卡罗模拟研究构建，在该研究中，我们探索了具有二分类或生存结局的不同情况。为了评估模型的性能，我们使用获益的 C 统计量、预测的校准和均方误差。还在 INDANA IPD-MA 上使用了不同的模型，比较了抗高血压治疗与不治疗或安慰剂（n=836 事件）的疗效。
模拟结果表明，对于二分类和生存结局，使用交互项与治疗（S-learner）进行估计可以获得更好的 ITE 估计性能。没有任何风险模型脱颖而出，并且没有明显更好的结果。对于具有二分类结局的 INDANA 数据集，朴素和随机截距模型具有最佳性能。
对于策略的选择，使用与治疗的交互（S-learner）更为可取。对于方法的选择，没有一种方法比其他方法更好。
