Statistical ICA Methods for Analysis and Integration of Multi-dimensional Data

多维数据分析与整合的统计ICA方法

• 批准号: 10475127
• 负责人: Ying Guo
• 金额: $ 51.64万
• 依托单位: EMORY UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-09-25 至 2025-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10475127
• 关键词: Address; Advanced Development; Award; Behavior; Behavior assessment; Biological Markers; Brain; Brain imaging; Clinical; Clinical assessments; Communities; Computational Technique; Data; Data Analyses; Data Set; Development; Diagnosis; Diffusion Magnetic Resonance Imaging; Dimensions; Disease Progression; Feeling suicidal; Fingerprint; Functional Magnetic Resonance Imaging; Funding; Goals; Human; Hybrids; Image; Individual; Investigation; Joints; Lead; Libraries; Link; Longitudinal Studies; Major Depressive Disorder; Measures; Mental Depression; Mental Health; Mental disorders; Methods; Modeling; National Institute of Mental Health; Neural Pathways; Neurosciences Research; Patients; Phenotype; Physiological; Prediction of Response to Therapy; Psychiatry; Pythons; Regimen; Relapse; Research; Sample Size; Selection for Treatments; Statistical Methods; Strategic Planning; Structure; Symptoms; Time; Treatment outcome; United States National Institutes of Health; Validation; analytical tool; base; behavior change; brain behavior; clinical biomarkers; cohort; complex data; computer framework; denoising; depressive symptoms; disorder subtype; effective therapy; endophenotype; feature extraction; graphical user interface; imaging modality; imaging study; improved; independent component analysis; individualized medicine; innovation; insight; learning strategy; magnetic resonance imaging/electroencephalography; method development; multidimensional data; multimodal neuroimaging; multimodality; neural circuit; neural network; neurobiological mechanism; neuroimaging; neuroimaging marker; novel; predict clinical outcome; predictive marker; predictive modeling; predictive tools; relating to nervous system; tool; treatment planning; treatment response; user friendly software

Project Summary/Abstract Recent mental health studies have led to an expanded depth of multimodal brain imaging data, clinical assessments and physiological data. In addition, longitudinal studies have become increasingly important to capture the trajectory of disease progression, treatment response and relapse. This wealth of datasets provides an unprecedented opportunity for crosscutting investigations. However, much-needed statistical methods for exploring discoveries are lacking. In particular, there has been very limited development of advanced statistical methods for several important objectives: decompose observed brain connectivity measures to reveal underlying neural circuits which are key biomarkers for mental disorders, effectively extract low dimensional neural features from imaging to reliably predict clinical outcomes such as treatment response, and analyze longitudinal multidimensional data including neuroimaging, clinical and behavioral assessments to study the dynamic interplay between brain and behavior changes due to treatments. In this competing renewal proposal, we will build upon the theoretical and computational framework established in our previous award to develop rigorous and computationally efficient statistical methods to address the aforementioned objectives. Specifically, we plan to develop 1) a sparse and low rank ICA (SLR- ICA) framework for reliable and parsimonious decomposition of brain connectivity measures to reveal underlying neural circuits associated with specific clinical symptoms in mental disorders; 2) an ICA-Neural Network (ICA-NN) predictive model that effectively extracts relevant low dimensional linear and non-linear neural features to predict clinical outcomes; and (3) longitudinal multidimensional data analysis tools for investigating heterogeneous changes in neural circuits due to different treatments and disease subtypes, and disentangle the relationship between changes in neuroimaging phenotypes and clinical symptoms. The statistical methods will be applied to a major NIH funded longitudinal study of major depressive disorder (MDD) to help discover neural circuits underlying specific depressive symptoms (e.g. suicidal thoughts) and differential treatment response, and ultimately help lead to more effective treatment for individual MDD patients based on his/her own neural circuitry fingerprints and behavior. We plan to replicate the findings using an independent validation cohort from an R01 study of MDD. User-friendly software will be made available to general research communities. Our proposed method developments will directly benefit mental health research by providing innovative statistical tools to effectively extract reliable and highly relevant low dimensional features from neuroimaging to deepen mechanistic understanding and improve treatment of MDD and other mental disorders.

项目概要/摘要 最近的心理健康研究扩大了多模式脑成像数据、临床数据的深度 评估和生理数据。此外，纵向研究对于 捕捉疾病进展、治疗反应和复发的轨迹。如此丰富的数据集 为跨领域调查提供了前所未有的机会。然而，急需的统计数据 缺乏探索发现的方法。特别是，其发展非常有限。 先进的统计方法可实现几个重要目标：分解观察到的大脑连接 揭示潜在神经回路的措施，这是精神障碍的关键生物标志物，有效提取 来自成像的低维神经特征可以可靠地预测临床结果，例如治疗反应， 并分析纵向多维数据，包括神经影像、临床和行为评估，以 研究大脑与治疗引起的行为变化之间的动态相互作用。 在这个竞争性的更新提案中，我们将建立在理论和计算框架的基础上 我们在上一个奖项中设立的目标是开发严格且计算高效的统计方法 实现上述目标。具体来说，我们计划开发 1) 稀疏低阶 ICA (SLR- ICA）框架，用于可靠且简约地分解大脑连接测量以揭示 与精神障碍特定临床症状相关的潜在神经回路； 2) ICA 神经网络 有效提取相关低维线性和非线性的网络（ICA-NN）预测模型 预测临床结果的神经特征； (3)纵向多维数据分析工具 研究由于不同治疗和疾病亚型导致的神经回路的异质变化，以及 理清神经影像表型变化与临床症状之间的关系。这 统计方法将应用于 NIH 资助的重度抑郁症 (MDD) 纵向研究 帮助发现特定抑郁症状（例如自杀念头）背后的神经回路和差异 治疗反应，最终有助于为个体 MDD 患者提供更有效的治疗 他/她自己的神经回路指纹和行为。我们计划使用独立的机构来重复研究结果 MDD R01 研究的验证队列。用户友好的软件将可供一般研究使用 社区。我们提出的方法开发将通过提供直接有利于心理健康研究 创新的统计工具，可有效地从中提取可靠且高度相关的低维特征 神经影像学可加深对机制的理解并改善 MDD 和其他精神疾病的治疗 失调。