Bayesian machine learning for complex missing data and causal inference with a focus on cardiovascular and obesity studies

用于复杂缺失数据和因果推理的贝叶斯机器学习，重点关注心血管和肥胖研究

• 批准号: 10563598
• 负责人: Michael J Daniels
• 金额: $ 54.83万
• 依托单位: UNIVERSITY OF FLORIDA
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-03-01 至 2027-02-28
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10563598
• 关键词: Address; Algorithms; Bayesian Method; Bayesian Modeling; Bayesian learning; Behavioral Mechanisms; Behavioral trial; Blood Pressure; Body Weight; Cardiovascular system; Caring; Clinical; Clinical Research; Clinical Trials; Cluster randomized trial; Code; Collaborations; Comparative Study; Complex; Computer software; Data; Data Element; Diabetes Mellitus; Electronic Health Record; Ensure; Ethics; Exhibits; Frequencies; Funding; Future; Hand; Heterogeneity; Individual; Intervention; Kenya; Literature; Malignant Neoplasms; Mediating; Mediation; Mediator; Mental disorders; Methodology; Methods; Modeling; National Heart, Lung, and Blood Institute; Obesity; Observational Study; Outcome; Paper; Pharmaceutical Preparations; Pharmacoepidemiology; Process; Property; Protocols documentation; Public Health; Recording of previous events; Research; Research Personnel; Risk; Sampling; Science; Structure; Time; Uncertainty; Weight; Weight maintenance regimen; Work; bariatric surgery; behavior change; behavioral study; cardiovascular health; cost; data complexity; data modeling; diabetogenic; flexibility; hypertension treatment; improved; interest; large datasets; longitudinal, prospective study; machine learning method; novel; novel strategies; primary outcome; prospective; randomized trial; secondary outcome; tool; usability; virtual

Project Summary This proposal will develop Bayesian machine learning approaches via Bayesian nonparametrics (BNP) to handle nonignorable missingness (in outcomes and covariates) and conduct causal inference for electronic health records (EHRs), to address missingness in multivariate longitudinal data, and for causal mediation problems. Missing data remains a problem in clinical studies and in particular, for studies using EHRs. In clinical studies, more e↵ort is spent to try to minimize the amount of missingness, but it still remains a problem and missingness is a constant issue (and less controllable) in studies based on EHRs. In addition, there has been limited work on the use of auxiliary information in EHRs that can enhance the ability to deal with missing data. Approaches for missingness in multivariate longitudinal data is underdeveloped and relevant across many clinical trials settings from cost e↵ectiveness analysis to incomplete time-varying auxiliary covariates (or confounders) to causal mediation to multiple outcomes of interest. The mechanisms of treatment e↵ectiveness are of particular interest in behavioral trials. Specifically, how do di↵erent processes mediate the e↵ect of an intervention? This can facilitate constructing future interventions. However, determining the causal e↵ect of such 'mediators' on outcomes is di"cult. We will develop new approaches to identify these e↵ects in the complex setting of cluster randomized trials for which little work has been done. For all these settings, a Bayesian approach is ideal as it allows one to appropriately characterize uncertainty about unverifiable assumptions (which are present in all these problems) and allows the flexibility of Bayesian nonparametric models. MCMC algorithms for BNP can sometimes converge slowly and can be untenable for large n. We will extend existing approaches to address both these complications which will be important for all the applications considered and in general, given the increasing size and complexity of data. The methods are motivated by several NHLBI funded studies, whose PI's are co-investigators on this proposal, and will be developed to help answer numerous important clinical questions including the mechanisms of behavior change in weight management and the impact of linkage (and engagement) to care on treatment e↵ectiveness for blood pressure outcomes. The methods will also help us evaluate potentially synergistic e↵ects when drugs with potential diabetogenic e↵ects are used concomitantly and whether the impact on cancer outcomes varies by di↵erent bariatric surgeries. The history of the the collaborations among the entire study team will help produce the best science and facilitate dissemination of our methodological and clinical findings. We will disseminate code for these methods (via the PI's github page and software papers) to ensure the methods will be readily usable by investigators involved in cardiovascular, obesity, diabetes, and cancer studies.

项目概要 该提案将通过贝叶斯非参数（BNP）开发贝叶斯机器学习方法来处理 不可忽略的缺失（结果和协变量）并对电子健康记录进行因果推断 （EHR），解决多变量纵向数据的缺失以及因果中介问题。 数据仍然是临床研究中的一个问题，尤其是使用电子病历的研究。 我们付出了努力来尽量减少缺失的数量，但这仍然是一个问题，缺失是 在基于电子病历的研究中，这是一个持续存在的问题（且不太可控）。此外，这方面的工作也很有限。 在电子病历中使用辅助信息可以增强处理缺失数据的能力。 多变量纵向数据的缺失尚未得到充分发展，并且与许多临床试验环境相关 从成本效益分析到不完全时变辅助协变量（或混杂因素）再到因果中介 治疗有效性的机制对行为学特别感兴趣。 具体来说，不同的过程如何调节干预的效果？ 然而，确定此类“中介”对结果的因果影响是困难的。我们将 开发新方法来识别复杂的整群随机试验中的这些影响 对于所有这些设置，贝叶斯方法是理想的，因为它允许人们适当地进行。 描述无法验证的假设（存在于所有这些问题中）的不确定性，并允许 BNP 的贝叶斯非参数模型的灵活性有时会收敛得很慢并且可能会失败。 对于大的 n 来说是站不住脚的。我们将扩展现有的方法来解决这两个复杂问题。 鉴于数据规模和复杂性不断增加，对于所有考虑的应用程序和一般应用程序都很重要。 这些方法是由 NHLBI 资助的几项研究推动的，这些研究的 PI 是该提案的共同研究员， 并将被开发以帮助回答许多重要的临床问题，包括行为机制 体重管理的变化以及护理联系（和参与）对治疗效果的影响 这些方法还将帮助我们评估药物的潜在协同效应。 同时使用具有潜在糖尿病作用的药物，以及对癌症结果的影响是否因不同因素而异 不同的减肥手术。 整个研究团队之间的合作历史将有助于产生最好的科学和成果 促进我们的方法学和临床研究结果的传播，我们将传播这些方法的代码。 （通过 PI 的 github 页面和软件论文）确保研究人员可以轻松使用这些方法 参与心血管、肥胖、糖尿病和癌症研究。