Big Data Neuroimaging to Predict Motor Behavior After Stroke

大数据神经影像预测中风后的运动行为

• 批准号: 9888377
• 负责人: Sook-Lei Liew
• 金额: $ 13.32万
• 依托单位: UNIVERSITY OF SOUTHERN CALIFORNIA
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-04-01 至 2020-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9888377
• 关键词: Activities of Daily Living; Acute; Address; Adult; Affect; Age; Area; Behavior; Behavioral; Big Data; Big Data Methods; Biological Markers; Brain; Brain imaging; Caring; Characteristics; Classification; Clinical; Clinical Research; Collaborations; Corticospinal Tracts; Data; Data Set; Diffuse; Disease; Effectiveness of Interventions; Ensure; Future; Gait; Gender; Genetic study; Genomics; Goals; Grant; Heterogeneity; Image; Impairment; Individual; Infrastructure; Injury; International; K-Series Research Career Programs; Knowledge; Language; Lead; Left; Lesion; Location; Magnetic Resonance Imaging; Measures; Medicine; Mentors; Mentorship; Methodology; Methods; Modeling; Motor; Motor Cortex; Nature; Outcome; Participant; Patients; Performance; Persons; Physical Medicine; Population; Population Heterogeneity; Precision Medicine Initiative; Property; Recovery; Recovery of Function; Rehabilitation therapy; Reproducibility; Reproducibility of Results; Research; Research Personnel; Resources; Sensitivity and Specificity; Sensory; Site; Statistical Models; Stroke; Structure; Task Performances; Techniques; Testing; Thick; Time; Training; United States National Institutes of Health; Wolves; arm; arm movement; computerized tools; disability; functional disability; functional improvement; heterogenous data; imaging biomarker; improved; large datasets; machine learning algorithm; motor behavior; motor impairment; motor recovery; muscle strength; neurobiological mechanism; neuroimaging; neurological rehabilitation; novel; personalized medicine; post stroke; predictive marker; predictive modeling; predictive test; prevent; rehabilitation research; relating to nervous system; research and development; response; skills; statistical and machine learning; stroke outcome; stroke patient; stroke recovery; stroke rehabilitation; stroke survivor; stroke therapy; supervised learning; tool; treatment response; unsupervised learning; working group

PROJECT SUMMARY Stroke is a leading cause of serious long-term adult disability around the world. Despite intensive therapy, an estimated 2/3 of stroke survivors do not fully recover and are left unable to care for themselves independently. Growing research suggests that rehabilitation is not “one-size-fits-all”; variability among stroke survivors in terms of lesion location, age, gender, time since stroke and more may all affect a person's likelihood of recovery and response to different types of treatments. Personalized rehabilitation medicine to maximize each individual's recovery potential is thus desperately needed. However, in order to develop accurate, robust, and specific predictive models that can determine an individual's recovery potential and response to different treatments, large, heterogeneous datasets are needed. The current best predictors of stroke outcomes are neuroimaging (MRI) and behavioral biomarkers that look at brain structure/function and motor performance at baseline. Generating a large enough dataset of MRI and behavioral data is extremely difficult and expensive for any one site to do on its own. This proposal addresses this problem by generating a large, diverse dataset using a novel meta-analytic approach that harmonizes post-stroke data collected worldwide. In partnership with an international consortium comprised of over 500 researchers who produce the largest-known neuroimaging and genetic studies of over 18 different diseases (ENIGMA Center for Worldwide Medicine, Imaging, and Genomics), I propose to apply ENIGMA's powerful approach to answer critical questions in stroke recovery. Under this K01 career development award, I will develop skills in big data neuroimaging analytics, clinical research, and consortium building through my ENIGMA Stroke Recovery working group in order to ask questions about stroke recovery using a large dataset approach (goal n>3,000). This project has four specific aims: Aim 1 will leverage ENIGMA's existing methodology to develop the infrastructure, optimal methods, and analysis techniques for harmonizing a large dataset of post-stroke MRI and behavioral data. Aim 2 will use this large dataset to identify neural and behavioral biomarkers predicting recovery of motor impairment (e.g., actual arm movement ability) and recovery of function (e.g., ability to perform tasks, such as picking up objects with the affected arm). Aim 3 will use supervised machine learning to generate and fine-tune highly accurate predictive models of the relationship between these biomarkers and recovery of impairment versus function. Lastly, Aim 4 will use unsupervised machine learning techniques to examine shared properties of outliers from the predictive model and determine additional neurobiological mechanisms that may prevent individuals from recovering. This approach has the potential to revolutionize the way that rehabilitation research is validated, to ensure robust, reliable, and reproducible results. The methods developed here could be extended to other domains of recovery (language, gait), to study other predictors of recovery (functional brain activity, genomics), and to other clinical populations to improve rehabilitation overall.

项目摘要 中风是世界各地成人严重长期残疾的主要原因。尽管进行了强化治疗， 据估计，2/3的中风幸存者没有完全康复，无法照顾自己。 独立地。越来越多的研究表明，康复不是"一刀切";中风之间的差异 就病变部位、年龄、性别、中风后的时间等而言，幸存者的死亡率都可能影响一个人的 恢复的可能性和对不同类型治疗的反应。个性化康复医学， 因此，迫切需要最大限度地发挥每个人的康复潜力。然而，为了发展 准确，强大，具体的预测模型，可以确定一个人的恢复潜力， 响应于不同的处理，需要大的异构数据集。目前最好的预测因子 卒中结局是神经影像学（MRI）和行为生物标志物，这些生物标志物观察大脑结构/功能， 基线时的运动表现。生成足够大的MRI和行为数据的数据集是极其困难的。 这对任何一个网站来说都是困难和昂贵的。该提案通过生成一个 使用一种新的荟萃分析方法，协调收集的中风后数据， 国际吧与一个由500多名研究人员组成的国际财团合作， 对超过18种不同疾病的最大已知神经影像学和遗传学研究（ENIGMA全球研究中心 医学，成像和基因组学），我建议应用ENIGMA的强大方法来回答关键的 中风康复的问题在这个K01职业发展奖下，我将发展大数据技能 通过我的ENIGMA中风康复，神经影像分析，临床研究和联盟建设 工作组，以便使用大型数据集方法询问有关中风恢复的问题（目标n> 3，000）。 该项目有四个具体目标：目标1将利用ENIGMA现有的方法来开发 协调卒中后MRI大型数据集的基础设施、最佳方法和分析技术 和行为数据。Aim 2将使用这个大型数据集来识别神经和行为生物标志物， 运动损伤的恢复（例如，实际手臂运动能力）和功能恢复（例如，能力 执行任务，例如用受影响的手臂拾取物体）。Aim 3将使用监督机器学习 生成和微调这些生物标志物之间关系的高度准确的预测模型， 损伤与功能的恢复。最后，Aim 4将使用无监督机器学习技术， 检查预测模型中离群值的共享属性，并确定其他神经生物学特性 可能会阻碍个人康复的机制。这种方法有可能彻底改变 验证康复研究的方式，以确保稳健，可靠和可重复的结果。的方法 这里开发的可以扩展到其他领域的恢复（语言，步态），研究其他预测因素， 康复（功能性大脑活动，基因组学），并用于其他临床人群，以改善整体康复。

项目成果

The Effects of Sensory Manipulations on Motor Behavior: From Basic Science to Clinical Rehabilitation.

感觉操纵对运动行为的影响：从基础科学到临床康复。

• DOI: 10.1080/00222895.2016.1241740
• 发表时间: 2017
• 期刊: Journal of motor behavior
• 影响因子: 1.4
• 作者: Sugiyama,Taisei;Liew,Sook-Lei
• 通讯作者: Liew,Sook-Lei

Development of a Low-Cost, Modular Muscle-Computer Interface for At-Home Telerehabilitation for Chronic Stroke.

• DOI: 10.3390/s21051806
• 发表时间: 2021-03-05
• 期刊: Sensors (Basel, Switzerland)
• 作者: Marin-Pardo O;Phanord C;Donnelly MR;Laine CM;Liew SL
• 通讯作者: Liew SL

Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning.

• DOI: 10.3390/s21061952
• 发表时间: 2021-03-10
• 期刊: Sensors (Basel, Switzerland)
• 作者: Paing MP;Tungjitkusolmun S;Bui TH;Visitsattapongse S;Pintavirooj C
• 通讯作者: Pintavirooj C

Editorial: Collaborative Efforts for Understanding the Human Brain.

社论：理解人脑的协作努力。

• DOI: 10.3389/fninf.2019.00038
• 发表时间: 2019
• 期刊: Frontiers in neuroinformatics
• 影响因子: 3.5
• 作者: Liew,Sook-Lei;Schmaal,Lianne;Jahanshad,Neda
• 通讯作者: Jahanshad,Neda

A Preliminary Comparison of Motor Learning Across Different Non-invasive Brain Stimulation Paradigms Shows No Consistent Modulations.

• DOI: 10.3389/fnins.2018.00253
• 发表时间: 2018
• 期刊: Frontiers in neuroscience
• 影响因子: 4.3
• 作者: Lopez-Alonso V;Liew SL;Fernández Del Olmo M;Cheeran B;Sandrini M;Abe M;Cohen LG
• 通讯作者: Cohen LG