文献速递流行病学与生物统计医学人工智能与信息学临床试验与 GCP

利用基线协变量信息提升临床试验效率的机器学习方法

Machine learning methods for leveraging baseline covariate information to improve the efficiency of clinical trials.
PubMed 文献 · Stat Med · 2018-11-25

临床试验效率可通过纳入与结局相关的基线协变量信息来提升。该文研究用机器学习方法估计最优增广项,比较基于估计回归函数的间接法与直接最小化治疗效应估计量渐近方差的直接法。理论与模拟表明直接法通常更优,可用任一能最小化加权预测误差平方和的预测算法实现,超级学习器组合具有理想oracle性质,并用卒中试验数据展示。

要点

  • 直接法通过最小化治疗效应估计量渐近方差来估计最优增广项,通常优于间接法。
  • 直接法可借助现有预测算法实现,超级学习器组合具有理想oracle性质且易于实施。
  • 该方法在真实卒中试验数据中进行了展示。

核心结论

  • 直接法通常优于基于估计回归函数的间接法,直接超级学习器具有理想oracle性质且在实际设置中表现良好。

研究设计与样本

  • 方法学研究,比较间接法与直接法估计最优增广项,并结合理论考虑、模拟结果及一项卒中试验的真实数据展示。

主要发现

  • 理论考虑与模拟结果表明直接法通常比间接法更可取。
  • 直接法可通过任一能最小化加权预测误差平方和的现有预测算法实现。
  • 直接超级学习器具有理想oracle性质,易于实施,并在现实设置中表现良好。

临床怎么用

  • 在临床试验中可利用基线协变量信息,通过直接法估计增广项以提升治疗效应估计的效率。

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

Clinical trials are widely considered the gold standard for treatment evaluation, and they can be highly expensive in terms of time and money. The efficiency of clinical trials can be improved by incorporating information from baseline covariates that are related to clinical outcomes. This can be done by modifying an unadjusted treatment effect estimator with an augmentation term that involves a function of covariates. The optimal augmentation is well characterized in theory but must be estimated in practice. In this article, we investigate the use of machine learning methods to estimate the optimal augmentation. We consider and compare an indirect approach based on an estimated regression function and a direct approach that aims directly to minimize the asymptotic variance of the treatment effect estimator. Theoretical considerations and simulation results indicate that the direct approach is generally preferable over the indirect approach. The direct approach can be implemented using any existing prediction algorithm that can minimize a weighted sum of squared prediction errors. Many such prediction algorithms are available, and the super learning principle can be used to combine multiple algorithms into a super learner under the direct approach. The resulting direct super learner has a desirable oracle property, is easy to implement, and performs well in realistic settings. The proposed methodology is illustrated with real data from a stroke trial.

来源:Stat Med,查看原文。版权归原作者所有。

引用

  1. Zhang Z, Ma S. Machine learning methods for leveraging baseline covariate information to improve the efficiency of clinical trials. Stat Med. 2018. PMID: 30474289. doi:10.1002/sim.8054

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。