Novel imaging genetic biomarkers for sporadic frontotemporal dementia through machine learning

通过机器学习发现散发性额颞叶痴呆的新型成像遗传生物标志物

基本信息

批准号：
10364707
负责人：
Iris J Broce-Diaz
金额：
$ 12.04万
依托单位：
UNIVERSITY OF CALIFORNIA, SAN DIEGO
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-03-15 至 2026-02-28
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10364707
关键词：
Age Age of Onset Aging Alzheimer&apos s Disease Alzheimer&apos s disease related dementia Alzheimer&apos s disease risk Atrophic Behavioral Biological Biological Markers Biometry Brain California Cardiovascular Diseases Cardiovascular system Classification Clinical Clinical Research Clinical Trials Clinical Trials Design Cognitive aging Complex Computer Models Data Data Set Dementia Development Diagnosis Diagnostic Differential Diagnosis Discriminant Analysis Disease Early Diagnosis Environment Epidemiologist Epidemiology Fostering Frontotemporal Dementia Frontotemporal Lobar Degenerations Genes Genetic Genetic Markers Genetic Models Genetic Research Genetic Risk Genotype Goals Image Immune Immunologics Incidence Individual Inherited International Iris Knowledge Language Machine Learning Magnetic Resonance Imaging Maps Mediating Memory Mentored Research Scientist Development Award Mentors Mentorship Methodology Methods Mission Modeling Multimodal Imaging Nerve Degeneration Neurodegenerative Disorders Neurologist Outcome Pathway interactions Patients Pattern Performance Phenotype Postdoctoral Fellow Prognosis Research Research Methodology Research Project Grants Risk Role San Francisco Scientist Social Behavior Stratification Subgroup Tauopathies Techniques Temporal Lobe Therapeutic Therapeutic Clinical Trial Time Training Translating United States National Institutes of Health Universities Validation Work accurate diagnosis base biomarker development career clinical heterogeneity clinical subtypes cohort dementia risk diagnostic tool experience frontal lobe genetic variant hazard high risk imaging genetics improved innovation model development multimodal data multimodality neuroimaging novel patient oriented patient subsets personalized medicine personalized strategies pleiotropism polygenic risk score population based predictive marker predictive modeling professor prognostic tool programs recruit risk prediction skills statistics symptomatology targeted treatment tau Proteins tool

项目摘要

Project Summary This is an application for a K01 award for Dr. Iris Broce-Diaz, a neuroimaging genetics postdoctoral fellow at the University of California, San Diego and University of California, San Francisco. Dr. Broce-Diaz is establishing herself as a young imaging geneticist conducting clinical research on neurodegenerative disease. This K01 will provide Dr. Broce-Diaz with the support necessary to accomplish the following goals: (1) gain proficiency in machine learning and computational modeling techniques, (2) gain proficiency in clinical and genetic research methodology for cognitive aging and complex spectrum of neurodegenerative diseases, including clinical characterization of frontotemporal dementia (FTD) and other Alzheimer’s Disease-Related Dementias, differential diagnosis, risk prediction, and biomarker development, and (3) develop an independent research career. To achieve these goals, Dr. Broce-Diaz has assembled an expert mentoring team, including her primary mentors: Dr Anders Dale (renowned computational neuroimaging genetics scientist) and co-primary mentor Bruce Miller (internationally recognized behavioral neurologist and leader in FTD), co-mentors: Drs. Jennifer Yokoyama (expert in FTD genetics) and Chun Chieh Fan (expert in epidemiology/biostatistics), and two collaborators: Drs. Adam Boxer (leader in clinical trials for FTD-spectrum disorders) and Wesley Thompson (expert in advanced statistics). The goal of the proposed project is to develop novel imaging genetics biomarkers for predicting individuals at risk of developing sporadic (non-familial) FTD and improving classification accuracy of sporadic FTD. Dr. Broce- Diaz will achieve this goal through the following specific aims: (1a) utilize a polygenic hazard approach to develop and validate a novel genetic biomarker for predicting age-specific risk of sporadic FTD; (1b) leverage pleiotropic information to increase accuracy of the genetic risk scores and derive biologically-based genetic risk scores; (2) use machine learning approaches to reliably and accurately classify FTD clinical subtypes and obtain personalized atrophy scores from these brain maps; and (3) improve FTD classification by integrating atrophy scores with genetic risk scores. This proposed study uses highly innovative methodological approaches for informing FTD prognosis, diagnosis, and, ultimately, clinical trial design. If validated, these biomarkers will make significant contributions by assisting clinicians in identifying patients at elevated risk for sporadic FTD and assisting in diagnosing sporadic FTD in its earliest stages—reducing diagnostic delays, accelerating the discovery of novel treatments, and improving recruitment accuracy in clinical trials. This K01 research project will provide Dr. Broce-Diaz with the protected research time and opportunity to train with leaders in the field she needs to master the skills required to establish an independent, patient-oriented, imaging genetics and biomarker development clinical research program that will inform diagnosis, prognosis, and guide treatments of FTD and other neurodegenerative diseases.

项目概要这是 Iris Broce-Diaz 博士的 K01 奖申请，她是该大学的神经影像遗传学博士后研究员。加州大学圣地亚哥分校和加州大学旧金山分校正在建立。她自己作为一名年轻的影像遗传学家，正在进行神经退行性疾病的临床研究。为 Broce-Diaz 博士提供实现以下目标所需的支持：(1) 熟练掌握机器学习和计算建模技术，(2) 熟练掌握临床和遗传研究认知衰老和复杂的神经退行性疾病谱的方法论，包括临床额颞叶痴呆（FTD）和其他阿尔茨海默病相关痴呆的特征，鉴别诊断、风险预测和生物标志物开发，以及 (3) 开展独立研究为了实现这些目标，布罗斯-迪亚兹博士组建了一个专家指导团队，其中包括她的主要导师。导师：Anders Dale 博士（著名计算神经影像遗传学科学家）兼联合导师 Bruce Miller（国际公认的行为神经学家和 FTD 领域的领导者），共同导师：Jennifer 博士。 Yokoyama（FTD 遗传学专家）和 Chun Chieh Fan（流行病学/生物统计学专家），以及两位合作者：Adam Boxer 博士（FTD 谱系疾病临床试验的领导者）和 Wesley Thompson （高级统计专家）。该项目的目标是开发新的成像遗传学生物标志物来预测个体发生散发性（非家族性）FTD 的风险并提高散发性 FTD 的分类准确性。 Diaz 将通过以下具体目标实现这一目标：(1a) 利用多基因危害方法来开发并验证一种新的遗传生物标志物，用于预测散发性 FTD 的年龄特异性风险 (1b) 发挥多效性； (2) 用于提高遗传风险评分的准确性并得出基于生物学的遗传风险评分的信息；使用机器学习方法可靠、准确地对 FTD 临床亚型进行分类并获得来自这些脑图的个性化萎缩评分；(3) 通过整合萎缩来改进 FTD 分类；这项拟议的研究使用了高度创新的方法学方法。这些生物标记物将有助于 FTD 预后、诊断以及最终的临床试验设计。协助忠诚者识别散发性 FTD 风险较高的患者，做出了重大贡献在最早阶段协助诊断散发性 FTD——减少诊断延迟，加速治疗发现新疗法，并提高临床试验中的招募准确性。将为 Broce-Diaz 博士提供受保护的研究时间和与她所在领域的领导者一起培训的机会需要掌握建立独立的、以患者为导向的影像遗传学和生物标志物所需的技能制定临床研究计划，为 FTD 的诊断、预后提供信息并指导治疗其他神经退行性疾病。