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.

项目摘要/摘要 2型糖尿病（T2D）是一种全球流行病，影响了全球约4.62亿个人。 cur 租金医疗指南主要依赖于研究平均研究的随机对照试验（RCT）的数据 效果，这远远不足以为现实世界患者做出个性化决策。这个限制是 在异质种群中发现动态治疗方案（DTR）的情况更糟 决定在一个或多个疾病过程中做出决定。此限制可以由SUP-部分解决 使用现实世界数据（RWD）（例如疾病登记，前瞻性观察研究）来使RCT数据配置 调查和电子健康记录，以改善医疗决策。尽管有合并的承诺 RWD和RCT，方法和算法开发中存在一些重要的挑战。这些包括 当应用于现实世界患者时，RCT的发现缺乏通用性或实用性；偏见应得 未观察到的混杂因素；并担心长期副作用/风险。该建议旨在解决每个建议 这些挑战。在AIM 1中，我们通过提出一个新颖的框架来解决普遍性问题 这使用RWD的证据来改善试验中的学习DTR。该框架使用RWD选择Infor- 通过双倍稳定 估计。在AIM 2中，为了改善DTR的实际实用性，我们提出了一种强大的方法来推断个人 RWD的治疗选择/偏好，然后将此估计的偏好纳入学习DTR中 试用数据。所得的DTR不仅在统计上有效，而且与患者/临床医生的偏好兼容 在现实世界中。在AIM 3中，为了减少由于RWD中隐藏的混杂因素而引起的偏见，我们提出了关节 半参数模型将试验数据与RWD相结合；我们提出的模型允许不同的磁性 由于RWD中隐藏的混杂因素，治疗效果大小和控制可能偏置。在AIM 4中解决 对长期风险的关注，我们考虑了一种估算DTR的一般程序，以最大程度地提高效率 结果同时确保与建议的DTR相关的长期副作用保持在 某些阈值。然后，我们提出了一种新颖的同时学习算法，以估计跨越的最佳DTR 所有阶段。对于所有四个目标，我们将使用来自 集中不平等，统计学习理论，经验过程和半参数推断。我们将 进行广泛的仿真研究，以研究各种集合中提出的方法的性能 用现成的方法将其性能进行比较。我们将应用提出的方法估算 使用临床试验数据和RWD从哥伦比亚大学和 俄亥俄州立大学医学中心以及我们的精密医学研究。我们的方法和发现将 通过软件开发宣传；该软件将根据用户反馈经常接收更新。