Bayesian machine learning for causal inference with incomplete longitudinal covariates and censored survival outcomes

用于不完整纵向协变量和审查生存结果的因果推理的贝叶斯机器学习

基本信息

批准号：
10445648
负责人：
Liangyuan Hu
金额：
$ 72.23万
依托单位：
RBHS-SCHOOL OF PUBLIC HEALTH
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-05-15 至 2023-04-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10445648
关键词：
Address Adult Age Antihypertensive Agents Atherosclerosis Risk in Communities Bayesian Analysis Bayesian Method Bayesian learning Blood Pressure Cardiovascular Diseases Cardiovascular system Cholesterol Clinical Cohort Studies Complex Computer software Data Data Pooling Elderly Frail Elderly Funding Goals Health Policy Institutes Intervention Investigation Knowledge Life Cycle Stages Longitudinal cohort study Machine Learning Methodology Methods Mission Modeling Multi-Ethnic Study of Atherosclerosis National Heart, Lung, and Blood Institute Outcome Paper Pathway interactions Pattern Population Postdoctoral Fellow Prevention strategy Property Public Health Research Research Methodology Research Personnel Risk Estimate Risk Factors Sample Size Selection Bias Software Tools Source Standardization Statistical Methods Strategic vision Structure Techniques Time Time Study To specify Trees Uncertainty United States National Institutes of Health Weight Work cardiovascular disorder prevention cardiovascular disorder risk cardiovascular health cohort data complexity ethnic diversity flexibility follow-up health data improved innovation machine learning framework machine learning method novel population based racial and ethnic software development survival outcome temporal measurement tool treatment effect young adult

项目摘要

Project Summary Population cohort studies funded by the National Institute of Health, including the Atherosclerosis Risk in Com- munities (ARIC) Study and Multi-Ethnic Study of Atherosclerosis (MESA), are widely used in cardiovascular research and have provided fundamental knowledge for cardiovascular disease (CVD) prevention strategies and public health policies. Pooling data across multiple cohorts provides a unique opportunity for in-depth investiga- tions of emerging CVD research questions, such as optimal blood pressure threshold values triggering initiation of antihypertensive treatment for young adults, that heretofore would not have been possible. While forming a fertile ground for innovative research, the methodological issues associated with the pooled cohorts data cannot be as effectively addressed by existing statistical methods. There are three main analytic challenges. First, many discrete or continuous longitudinal variables have missing values with various missing data patterns. Existing methods either are susceptible to misspeciﬁcation biases or do not provide coherent estimates of imputation un- certainty, and cannot handle missing not at random. Second, current causal inference methods either require aligned measurement time points or parametric assumptions about forms of causal pathways, neither of which can be satisﬁed in complex longitudinal health data. Third, violations of the “sequential ignorability” assumption embedded in causal inference methodology can be a potential source of bias. The sensitivity analysis methods for time-varying confounding with censored survival outcomes are underdeveloped. To overcome these chal- lenges and improve statistical and CVD research, we propose a suite of generalizable statistical methods utilizing machine learning. We propose to develop a scalable Bayesian nonparametric (BNP) framework to impute con- tinuous or discrete missing at random longitudinal covariates while providing coherent uncertainty intervals, and address the missing not at random mechanism via sensitivity analysis. We will apply the developed method to address missing data issues for several longitudinal CVD risk factors such as blood pressure, cholesterol levels (Speciﬁc Aim 1); to develop a robust and computationally efﬁcient BNP causal inference method (Speciﬁc Aim 2) and a new continuous-time marginal structural survival model from a Bayesian perspective (Speciﬁc Aim 3) to study and validate the survival effects of time-varying antihypertensive treatments for young adults and the frail elderly; to develop a ﬂexible and interpretable survival sensitivity analysis method to assess the sensitivity of the causal effect estimates to varying degrees of sequential unmeasured confounding (Speciﬁc Aim 4); and to create usable R software packages for all proposed methods and develop tutorial papers and short courses to bridge theoretical and practical knowledge and promote use of our methods (Speciﬁc Aim 5).

项目概要由美国国立卫生研究院资助的人口队列研究，包括冠状动脉粥样硬化风险社区（ARIC）研究和动脉粥样硬化多种族研究（MESA），广泛应用于心血管领域研究并为心血管疾病（CVD）预防策略和提供了基础知识公共卫生政策。汇集多个群体的数据为深入调查提供了独特的机会。新兴心血管疾病研究问题的解决方案，例如触发启动的最佳血压阈值对年轻人进行抗高血压治疗，这在以前是不可能的。作为创新研究的沃土，与汇总队列数据相关的方法论问题不能现有的统计方法可以有效解决三个主要的分析挑战。离散或连续纵向变量具有各种现有缺失数据模式的缺失值。方法要么容易受到错误指定偏差的影响，要么不能提供对插补的连贯估计其次，当前的因果推理方法要么需要确定性，要么不能处理非随机的缺失。对齐的测量时间点或关于因果路径形式的参数假设，两者都不是可以在复杂的纵向健康数据中得到满足第三，违反了“顺序可忽略性”假设。嵌入因果推理方法中的敏感性分析方法可能是潜在的偏差来源。对于时变混杂与审查生存结果的克服这些挑战尚不成熟。长度并改进统计和 CVD 研究，我们提出了一套可推广的统计方法，利用我们建议开发一个可扩展的贝叶斯非参数（BNP）框架来估算con- 随机纵向协变量的连续或离散缺失，同时提供连贯的不确定性区间，以及我们将通过敏感性分析来解决缺失的非随机机制。解决血压、胆固醇水平等多个纵向 CVD 危险因素的数据缺失问题（具体目标 1）；开发一种稳健且计算高效的 BNP 因果推理方法（具体目标 2）以及从贝叶斯角度出发的新的连续时间边际结构生存模型（具体目标 3）研究并验证时变抗高血压治疗对年轻人和体弱者的生存影响开发一种灵活且可解释的生存敏感性分析方法来评估老年人的敏感性对不同程度的连续未测量混杂因素进行因果效应估计（具体目标 4）；适用于所有建议方法的可用 R 软件包，并开发教程论文和短期课程来衔接理论和实践知识并促进我们方法的使用（具体目标 5）。