Developing a Robust and Efficient Strategy for Censored Covariates to Improve Clinical Trial Design for Neurodegenerative Diseases

为删失协变量制定稳健有效的策略，以改进神经退行性疾病的临床试验设计

• 批准号: 10634043
• 负责人: Tanya Pamela Garcia
• 金额: $ 48.56万
• 依托单位: UNIV OF NORTH CAROLINA CHAPEL HILL
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-06-01 至 2028-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10634043
• 关键词: Area; Behavioral; Clinical Trials; Clinical Trials Design; Cognitive; Data; Data Set; Disease; Disease Progression; Drops; Enrollment; Funding; Genetic; Huntington Disease; Intervention; Investigational Therapies; Joints; Lead; Measurement; Measures; Methods; Modeling; Modification; Motor; Neurodegenerative Disorders; Patients; Research Personnel; Science; Scientist; Source Code; Statistical Models; Symptoms; Testing; Time; United States National Institutes of Health; Visit; Work; clinical diagnosis; cohort; design; improved; longitudinal dataset; model building; neuroimaging; open source; prevent; semiparametric; theories

Project Summary: Developing disease-modifying therapies for neurodegenerative diseases has been challenging, in part because accurate statistical models to identify the optimal time for intervention do not exist. Models of how symptoms worsen over time (i.e., the symptom trajectory) before and after a clinical diagnosis can help identify that optimal time. These models can help pinpoint when a therapy could prevent a clinical diagnosis, or slow the disease after a clinical diagnosis. Yet modeling the symptom trajectory is not easy even for Huntington disease, a disease for which researchers can track symptoms in patients guaranteed to develop it. Like other neurodegenerative diseases, Huntington disease progresses slowly over decades, so studies that track symptoms often end before clinical diagnosis. This makes time to clinical diagnosis right-censored (i.e., a patient's motor abnormalities will merit a clinical diagnosis sometime after the last study visit, but exactly when is unknown), leaving researchers with the challenge of trying to model the symptom trajectory before and after clinical diagnosis without full information about when clinical diagnosis occurs. The challenge creates a unique statistical problem of modeling the symptom trajectory as a function of a right-censored covariate, time to clinical diagnosis. Tackling this problem by modeling the distribution for time to clinical diagnosis has long been thought to be the best strategy. For years, we and others worked to develop reliable distribution models, but we found that if the model is even slightly wrong, we get biased estimates of how the symptom trajectory changes as a function of time to clinical diagnosis. This bias causes problems for clinical trials because they are incorrectly powered to determine if a therapy modifies the disease course with statistical significance. We began seeking a strategy that estimates the symptom trajectory as a function of time to clinical diagnosis without needing to accurately model the distribution for time to clinical diagnosis. Our team developed such a strategy for a related problem: estimating a regression model that has a covariate measured with error. Like a right-censored covariate, when a covariate is measured with error, the covariate's true value and distribution are unknown. Rather than finding the correct distribution, our nontraditional strategy accurately estimates the regression model even when the distribution for the covariate is mismodeled. Our overarching objective is to develop a similarly robust strategy when we have a right-censored covariate, which requires tackling challenges in three new areas: noninformative censoring (Aim 1), informative censoring (Aim 2), and handling longitudinal measures of the symptom trajectory (Aim 3). Upon completion, our work will produce robust estimates of the Huntington disease symptom trajectory as a function of time to clinical diagnosis. The work is timely, given recent therapies that show potential for modifying the course of Huntington disease. Correctly powered clinical trials will enable researchers to test these therapies and determine if they modify the disease course. Our strategy could help design these clinical trials and push forward the science of Huntington disease and other neurodegenerative diseases.

项目摘要：开发神经退行性疾病的疾病修饰疗法一直具有挑战性，部分原因是 因为不存在确定最佳干预时间的准确统计模型。症状的模式 随时间恶化（即，症状轨迹）可以帮助识别最佳时间。 这些模型可以帮助确定治疗何时可以预防临床诊断，或在临床诊断后减缓疾病。 诊断. 然而，即使是对亨廷顿病的症状轨迹建模也并不容易， 可以跟踪患者的症状，保证发展它。像其他神经退行性疾病，亨廷顿病， 在过去的几十年里，这种疾病的进展缓慢，因此跟踪症状的研究往往在临床诊断之前就结束了。这使得时间 临床诊断右删失（即，患者的运动异常将值得临床诊断后的某个时候， 最后一次研究访问，但具体时间未知），给研究人员带来了试图模拟症状的挑战 在临床诊断之前和之后的轨迹，而没有关于临床诊断何时发生的完整信息。的挑战 创建了一个独特的统计问题，将症状轨迹建模为右删失协变量时间的函数， 临床诊断。 通过对临床诊断时间的分布进行建模来解决这个问题一直被认为是 最好的策略。多年来，我们和其他人一直致力于开发可靠的分销模式，但我们发现， 即使模型有一点点错误，我们也会得到关于症状轨迹如何随时间变化的有偏估计。 临床诊断。这种偏差给临床试验带来了问题，因为它们不正确地决定了 如果一种治疗方法能改善病程，且具有统计学意义。我们开始寻求一种策略， 作为临床诊断时间的函数的症状轨迹，而不需要精确地对 临床诊断时间。我们的团队为一个相关的问题开发了这样一个策略：估计一个回归模型 有一个测量误差的协变量就像右删失协变量一样，当协变量被误差测量时， 协变量的真实值和分布未知。而不是找到正确的分布，我们的非传统 即使协变量的分布被错误建模，该策略也能准确估计回归模型。 我们的总体目标是当我们有一个右删失协变量时， 需要解决三个新领域的挑战：非信息性审查（目标1），信息性审查（目标2）， 处理症状轨迹的纵向测量（目标3）。完成后，我们的工作将产生强大的 作为临床诊断时间的函数的亨廷顿病症状轨迹的估计。工作是及时的， 鉴于最近的治疗显示出改变亨廷顿病病程的潜力。正确把握度的临床 试验将使研究人员能够测试这些疗法，并确定它们是否能改变疾病进程。我们的策略可以 帮助设计这些临床试验，推动亨廷顿病和其他神经退行性疾病的科学发展。