arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.00258cs.AIstat.AP
收藏

一种基于情境-bandit的临床试验知情决策方法

A Contextual-bandit-based Approach for Informed Decision-making in Clinical Trials

University of Illinois(伊利诺伊大学);Mayo Clinic(梅奥诊所)

Yogatheesan Varatharajah, Brent Berry, Sanmi Koyejo, Ravishankar Iyer

摘要:

涉及多种治疗的临床试验利用治疗分配的随机化,以便能够以无偏倚的方式评价治疗疗效。这种评估是在事后研究中进行的,通常使用监督学习方法,依赖于以随机方式收集的大量数据。这种方法往往被证明是次优的,因为一些参与者可能会因为在试验期间没有得到最适当的治疗而受苦甚至死亡。强化学习方法通过在试验过程中动态学习治疗效果并相应地调整治疗分配来改善这种情况。最近的努力使用\textit{multi-arm bandits},一种学习方法,集中在最大限度地提高临床结果的人口,假设是同质的。然而,这些方法未能解释参与者之间的差异性,这种差异性由于最近的临床试验研究而变得越来越明显。我们提出了一个基于上下文的强盗在线治疗优化算法,在选择治疗新的参与者在研究中,不仅考虑到最大化的临床结果,但也病人的特点。我们使用来自国际中风试验的真实临床试验数据集评估了我们的算法。我们的回顾性分析的结果表明,所提出的方法比随机分配治疗(当前的金标准)或基于多臂强盗的方法表现得更好,在被分配最合适的治疗的参与者的百分比方面提供了实质性的收益。与随机分配相比,上下文强盗和多臂强盗方法分别提供了72.63%和64.34%的增益。

英文摘要:

Clinical trials involving multiple treatments utilize randomization of the treatment assignments to enable the evaluation of treatment efficacies in an unbiased manner. Such evaluation is performed in post hoc studies that usually use supervised-learning methods that rely on large amounts of data collected in a randomized fashion. That approach often proves to be suboptimal in that some participants may suffer and even die as a result of having not received the most appropriate treatments during the trial. Reinforcement-learning methods improve the situation by making it possible to learn the treatment efficacies dynamically during the course of the trial, and to adapt treatment assignments accordingly. Recent efforts using \textit{multi-arm bandits}, a type of reinforcement-learning methods, have focused on maximizing clinical outcomes for a population that was assumed to be homogeneous. However, those approaches have failed to account for the variability among participants that is becoming increasingly evident as a result of recent clinical-trial-based studies. We present a contextual-bandit-based online treatment optimization algorithm that, in choosing treatments for new participants in the study, takes into account not only the maximization of the clinical outcomes but also the patient characteristics. We evaluated our algorithm using a real clinical trial dataset from the International Stroke Trial. The results of our retrospective analysis indicate that the proposed approach performs significantly better than either a random assignment of treatments (the current gold standard) or a multi-arm-bandit-based approach, providing substantial gains in the percentage of participants who are assigned the most suitable treatments. The contextual-bandit and multi-arm bandit approaches provide 72.63% and 64.34% gains, respectively, compared to a random assignment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑