Deeply Tailored Adaptive Interventions to Reduce College Student Drinking: a Real-World Application of Q-Learning for SMART Studies.
Deeply Tailored Adaptive Interventions to Reduce College Student Drinking: a Real-World Application of Q-Learning for SMART Studies.
复制标题
DOI：
10.1007/s11121-022-01371-7
复制
发表时间：
2022-08
影响因子：
3.5
通讯作者：
Patrick, Megan E
中科院分区：
文献类型：
--
作者：
Lyden, Grace R;Vock, David M;Sur, Aparajita;Morrell, Nicole;Lee, Christine M;Patrick, Megan E
M-bridge是一项序贯多任务随机试验（SMART），旨在开发一种资源高效的适应性预防干预措施（API），以减少大学一年级学生的酗酒。M-桥的主要结果表明，平均而言，随机分配到API与仅评估对照组的学生之间的酗酒没有差异，但API的某些元素对高危亚组有益。本文扩展了M桥的主要结果，通过探索性分析，使用Q学习，一种新的算法，从计算机科学文献。具体来说，我们试图进一步定制M-bridge API的两个方面，以个人和测试深度定制是否提供了一个比仅评估控制的好处。Q学习是一种估计分配最佳治疗的决策规则的方法（即，根据学生的特点，尽量减少暴饮暴食。对于M-bridge API的第一个方面（何时提供），我们从一组20个候选变量中确定了最佳定制特性。对于第二个（如何桥接），我们使用了试验中已知的效果修改器。我们的分析结果是两个规则，优化1）普遍干预的时间为每个学生的基础上，他们的饮酒动机和2）桥接策略，以指示干预（即，在那些谁继续喝大量中期）基于中期狂欢饮酒频率。我们估计，如果向所有一年级学生提供这种新的特制API，平均每2.5个月将减少1次酗酒（95% CI：减少1.45至0.28次，p<0.01）。我们的分析表明，现实世界中实施Q学习的实质性目的，如果在未来的试验中可复制，我们的结果对旨在减少学生酗酒的大学校园有实际意义。
M-bridge was a sequential multiple assignment randomized trial (SMART) that aimed to develop a resource-efficient adaptive preventive intervention (API) to reduce binge drinking in first-year college students. The main results of M-bridge suggested no difference, on average, in binge drinking between students randomized to APIs versus assessment-only control, but certain elements of the API were beneficial for at-risk subgroups. This paper extends the main results of M-bridge through an exploratory analysis using Q-learning, a novel algorithm from the computer science literature. Specifically, we sought to further tailor the two aspects of the M-bridge APIs to an individual and test whether deep tailoring offers a benefit over assessment-only control. Q-learning is a method to estimate decision rules that assign optimal treatment (i.e., to minimize binge drinking) based on student characteristics. For the first aspect of the M-bridge API (when to offer), we identified the optimal tailoring characteristic post-hoc from a set of 20 candidate variables. For the second (how to bridge), we used a known effect modifier from the trial. The results of our analysis are two rules that optimize 1) the timing of universal intervention for each student based on their motives for drinking and 2) the bridging strategy to indicated interventions (i.e., among those who continue to drink heavily mid-semester) based on mid-semester binge drinking frequency. We estimate that this newly tailored API, if offered to all first-year students, would reduce binge drinking by 1 occasion per 2.5 months (95% CI: decrease of 1.45 to 0.28 occasions, p<0.01) on average. Our analyses demonstrate a real-world implementation of Q-learning for a substantive purpose, and, if replicable in future trials, our results have practical implications for college campuses aiming to reduce student binge drinking.