Statistical and Machine Learning Methods to Improve Dynamic Treatment Regimens Estimation Using Real World Data

使用真实世界数据改进动态治疗方案估计的统计和机器学习方法

• 批准号: 10654927
• 负责人: Yuanjia Wang
• 金额: --
• 依托单位: UNIV OF NORTH CAROLINA CHAPEL HILL
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-04-01 至 2023-08-27
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10654927
• 关键词: Academic Medical Centers; Acceleration; Achievement; Address; Adherence; Adverse event; Affect; Algorithms; American; Atherosclerosis; Benefits and Risks; Center for Translational Science Activities; Chronic Kidney Failure; Clinical Trials; Complement; Computer software; Data; Data Set; Databases; Decision Making; Diabetes Mellitus; Dimensions; Disadvantaged; Disease; Effectiveness; Electronic Health Record; Ensure; Epidemic; Equilibrium; Exclusion; Feedback; Funding; Goals; Guidelines; Health Status; Hypoglycemia; Individual; Inequality; Joints; Lead; Learning; Length; Maintenance; Managed Care; Medical; Medical center; Methods; Modeling; Non-Insulin-Dependent Diabetes Mellitus; Obesity; Observational Study; Ohio; Outcome; Patient Care; Patient Preferences; Patients; Pattern; Performance; Population; Population Distributions; Population Heterogeneity; Procedures; Process; Public Health; Quality Control; Randomized, Controlled Trials; Recommendation; Risk; Safety; Sample Size; Sampling; Selection Bias; Statistical Methods; Surveys; Time; Treatment Protocols; Uncertainty; Universities; Update; algorithm development; cardiovascular disorder risk; clinical decision-making; clinical practice; cohort; comorbidity; cost efficient; data modeling; disease registry; efficacy outcomes; feature selection; improved; individual patient; individualized medicine; insight; knowledge base; learning algorithm; learning strategy; machine learning algorithm; machine learning method; method development; novel; optimal treatments; patient oriented; patient population; personalized care; personalized decision; precision medicine; preference; prospective; semiparametric; side effect; simulation; social health determinants; software development; statistical and machine learning; statistical learning; theories; tool; translational clinical trial; treatment choice; treatment effect; treatment guidelines; treatment pattern; treatment strategy

Project Summary/Abstract Type 2 diabetes (T2D) is a global epidemic affecting approximately 462 million individuals world-wide. Cur- rent medical treatment guidelines rely largely on data from randomized controlled trials (RCTs) that study average effects, which is far from adequate for making individualized decisions for real world patients. This limitation is even worse for discovering dynamic treatment regimens (DTRs) in a heterogeneous population where treatment decisions are made over one or more stages of disease course. This limitation can be partially addressed by sup- plementing RCT data with real world data (RWD), such as disease registries, prospective observational studies, surveys and electronic health records, to improve medical decision making. Despite of the promise of combining RWD and RCT, there are several significant challenges in method and algorithm development. These include lack of generalizability or practical utility for the findings from RCTs when applied to real world patients; bias due to unobserved confounders; and concern about long-term side effects/risks. This proposal aims to address each of these challenges. Specifically, in Aim 1, we address the generalizability issue by proposing a novel framework that uses evidence from RWD to improve learning DTRs in the trials. The framework uses RWD to select infor- mative tailoring features, balance population distributions and improve statistical efficiency through doubly robust estimation. In Aim 2, to improve the practical utility of DTRs, we propose a robust method to first infer individual treatment choice/preference from RWD, then incorporate this estimated preference into learning DTRs using the trial data. The resulting DTRs are not only statistically valid but also compatible with patient/clinician preference in real world populations. In Aim 3, to lessen the bias due to hidden confounders in RWD, we propose joint semiparametric models to combine the trial data with RWD; the models we propose allow different magnitudes of treatment effect sizes and control for possible bias due to hidden confounders in RWD. In Aim 4, to address the concern about long-term risks, we consider a general procedure for estimating DTRs that maximizes efficacy outcomes while ensuring that long-term side effects associated with the recommended DTRs remain below a certain threshold. We then propose a novel simultaneous learning algorithm to estimate the optimal DTRs across all stages. For all four aims, we will provide rigorous assumptions and theoretical justifications using tools from concentration inequalities, statistical learning theory, empirical processes and semiparametric inference. We will conduct extensive simulation studies to study the performance of the proposed approaches in a variety of set- tings, and compare their performance with off-the-shelf methods. We will apply the proposed methods to estimate DTRs for T2D using clinical trial data and RWD taken from electronic health records in Columbia University and Ohio State University medical centers as well as Allof Us precision medicine study. Our methods and findings will be publicized through software development; the software will receive frequent updates based on user feedback.

项目概要/摘要 2 型糖尿病 (T2D) 是一种全球流行病，影响全球约 4.62 亿人。 租金医疗指南很大程度上依赖于随机对照试验（RCT）的数据，这些试验的研究平均 影响，这远远不足以为现实世界的患者做出个性化决策。 更糟糕的是在异质人群中发现动态治疗方案（DTR），其中治疗 这一限制可以通过支持来部分解决。 将 RCT 数据与真实世界数据 (RWD) 相结合，例如疾病登记、前瞻性观察研究、 调查和电子健康记录，以改善医疗决策，尽管有结合的希望。 RWD 和 RCT，在方法和算法开发方面存在几个重大挑战。 由于存在偏见，随机对照试验的结果在应用于现实世界的患者时缺乏普遍性或实用性； 未观察到的混杂因素；以及对长期副作用/风险的担忧。 具体来说，在目标 1 中，我们通过提出一个新颖的框架来解决普遍性问题。 使用 RWD 的证据来改进试验中的学习 DTR。该框架使用 RWD 来选择信息。 主动剪裁功能，通过双稳健平衡人口分布并提高统计效率 在目标 2 中，为了提高 DTR 的实用性，我们提出了一种稳健的方法来首先推断个体。 来自 RWD 的治疗选择/偏好，然后使用以下方法将估计的偏好纳入学习 DTR 中： 试验数据产生的 DTR 不仅具有临床有效性，而且符合患者/临床医生的偏好。 在目标 3 中，为了减少 RWD 中隐藏的混杂因素造成的偏差，我们共同提出。 将试验数据与 RWD 结合起来的半参数模型；我们提出的模型允许不同的量级 治疗效果大小和控制由于 RWD 中隐藏的混杂因素可能产生的偏差，以解决目标 4。 出于对长期风险的担忧，我们考虑采用一种估算 DTR 的通用程序，以最大限度地提高功效 结果，同时确保与推荐的 DTR 相关的长期副作用保持在低于 然后，我们提出了一种新颖的同时学习算法来估计最佳 DTR。 对于所有四个目标，我们将使用以下工具提供严格的假设和理论依据。 集中不等式、统计学习理论、经验过程和半参数推理。 进行广泛的模拟研究，以研究所提出的方法在各种设置中的性能 廷，并将其性能与现成的方法进行比较，我们将应用所提出的方法进行估计。 使用从哥伦比亚大学电子健康记录中获取的临床试验数据和 RWD 进行 T2D 的 DTR 俄亥俄州立大学医学中心以及我们所有人的精准医学研究将我们的方法和研究结果。 通过软件开发进行公开；软件将根据用户反馈进行频繁更新。