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: 10687870
• 负责人: Ying Guo
• 金额: $ 51.7万
• 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/10687870
• 关键词: Address; Advanced Development; Award; Behavior; Behavior assessment; Biological Markers; Brain; Brain imaging; Clinical; Clinical assessments; Communities; Complex; 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; behavior change; clinical biomarkers; cohort; 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; longitudinal analysis; magnetic resonance imaging/electroencephalography; method development; multidimensional data; multimodal neuroimaging; multimodality; neural; neural circuit; neural network; neurobiological mechanism; neuroimaging; neuroimaging marker; novel; predict clinical outcome; predictive modeling; predictive tools; 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.

项目摘要/摘要 最近的心理健康研究导致多模式脑成像数据的深度扩大 评估和生理数据。此外，纵向研究对 捕获疾病进展，治疗反应和复发的轨迹。这些数据集 提供了一个前所未有的交叉调查机会。但是，急需的统计 缺乏探索发现的方法。特别是，有限的发展非常有限 几个重要目标的高级统计方法：分解观察到的大脑连接性 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，有效地提取 低维神经特征从成像到可靠地预测临床结果，例如治疗反应， 并分析纵向多维数据，包括神经影像学，临床和行为评估 研究由于治疗而引起的大脑和行为变化之间的动态相互作用。 在这个竞争性的续约建议中，我们将建立在理论和计算框架的基础上 在我们以前的奖励中建立，以开发严格和计算上有效的统计方法 解决上述目标。具体而言，我们计划开发1）稀疏和低等级ICA（SLR- ICA）可靠和简约的大脑连通性措施分解框架以揭示 与精神障碍的特定临床症状相关的基本神经回路； 2）ICA神经 网络（ICA-NN）预测模型有效提取相关的低维线性和非线性 神经特征可预测临床结果； （3）用于纵向多维数据分析工具 研究因不同的治疗和疾病亚型而引起的神经回路的异质变化，以及 解开神经影像型的变化与临床症状之间的关系。这 统计方法将应用于主要NIH资助的主要抑郁症纵向研究（MDD） 帮助发现特定抑郁症状（例如自杀思想）和差异的神经回路 治疗反应，并最终帮助基于MDD患者提供更有效的治疗 他/她自己的神经电路指纹和行为。我们计划使用独立 MDD的R01研究验证队列。用户友好的软件将用于一般研究 社区。我们提出的方法发展将通过提供直接使心理健康研究受益 创新的统计工具可有效提取可靠且高度相关的低维特征 神经影像学以加深机械理解并改善对MDD和其他心理的治疗 疾病。

项目成果

A BAYESIAN HIERARCHICAL SPATIAL POINT PROCESS MODEL FOR MULTI-TYPE NEUROIMAGING META-ANALYSIS.

• DOI: 10.1214/14-aoas757
• 发表时间: 2014-09
• 期刊: The annals of applied statistics
• 作者: Kang J;Nichols TE;Wager TD;Johnson TD
• 通讯作者: Johnson TD

A parsimonious statistical method to detect groupwise differentially expressed functional connectivity networks.

• DOI: 10.1002/hbm.23007
• 发表时间: 2015-12
• 期刊: Human brain mapping
• 影响因子: 4.8
• 作者: Chen S;Kang J;Xing Y;Wang G
• 通讯作者: Wang G

SCALAR ON NETWORK REGRESSION VIA BOOSTING.

• DOI: 10.1214/22-aoas1612
• 发表时间: 2022-12
• 期刊: The annals of applied statistics

Relationship Between Basic Properties of BOLD Fluctuations and Calculated Metrics of Complexity in the Human Connectome Project.

• DOI: 10.3389/fnins.2020.550923
• 发表时间: 2020
• 期刊: Frontiers in neuroscience
• 影响因子: 4.3
• 作者: Keilholz S;Maltbie E;Zhang X;Yousefi B;Pan WJ;Xu N;Nezafati M;LaGrow TJ;Guo Y
• 通讯作者: Guo Y

Adaptive Sequence-Based Stimulus Selection in an ERP-Based Brain-Computer Interface by Thompson Sampling in a Multi-Armed Bandit Problem.

• DOI: 10.1109/bibm52615.2021.9669724
• 发表时间: 2021-12
• 期刊: Proceedings. IEEE International Conference on Bioinformatics and Biomedicine
• 作者: Ma, Tianwen;Huggins, Jane E;Kang, Jian
• 通讯作者: Kang, Jian