Advanced machine learning algorithms that integrate genomewide, longitudinal MRI and demographic data to predict future cognitive decline toward dementia

先进的机器学习算法，集成全基因组、纵向 MRI 和人口统计数据，以预测未来痴呆症的认知能力下降

• 批准号: 10188360
• 负责人: Mert Rory Sabuncu
• 金额: $ 41万
• 依托单位: CORNELL UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-07-01 至 2021-07-02
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10188360
• 关键词: Activities of Daily Living; Adverse effects; Age; Algorithmic Software; Algorithms; Alzheimer' s Disease; Alzheimer' s disease model; Alzheimer' s disease pathology; Amyloid; Amyloid beta-Protein; Anatomy; Bayesian learning; Benchmarking; Biological Markers; Blood; Brain; Clinical; Clinical Data; Complex; Computer Analysis; Computer Models; Computer software; Data; Dementia; Education; Elderly; Emerging Technologies; Foundations; Funding; Future; Genetic; Genomics; Genotype; Harvest; Hippocampus (Brain); Image; Impaired cognition; Impairment; Individual; Laboratories; Life; MRI Scans; Machine Learning; Magnetic Resonance Imaging; Maintenance; Methods; Mining; Modality; Modeling; Outcome; Pattern; Pharmaceutical Preparations; Phase; Prevention approach; Research; Risk; Risk Factors; Saliva; Scanning; Secondary Prevention; Site; Structure; Study Subject; Symptoms; Testing; Therapeutic; Time; Training; United States National Institutes of Health; Validation; aging brain; base; big biomedical data; case control; clinical predictors; clinical risk; cognitive ability; cognitive testing; data mining; flexibility; functional disability; genetic testing; genome-wide; genomic data; genomic locus; high dimensionality; imaging biomarker; imaging genetics; improved; innovation; large scale data; machine learning algorithm; machine learning method; mild cognitive impairment; multidimensional data; multimodal data; multimodality; neuroimaging; novel; pre-clinical; predictive modeling; prognostic; prognostic model; risk minimization; serial imaging; sex; software development; sound; tool; whole genome

ABSTRACT The “preclinical” phase of Alzheimer’s disease (AD) is characterized by abnormal levels of brain amyloid accumulation in the absence of major symptoms, can last decades, and potentially holds the key to successful therapeutic strategies. Today there is an urgent need for quantitative biomarkers and genetic tests that can predict clinical progression at the individual level. This project will develop cutting edge machine learning algorithms that will mine high dimensional, multi-modal, and longitudinal data to derive models that yield individual-level clinical predictions in the context of dementia. The developed prognostic models will specifically utilize ubiquitous and affordable data types: structural brain MRI scans, saliva or blood-derived genome-wide sequence data, and demographic variables (age, education, and sex). Prior research has demonstrated that all these variables are strongly associated with clinical decline to dementia, however to date we have no model that can harvest all the predictive information embedded in these high dimensional data. Machine learning (ML) algorithms are increasingly used to compute clinical predictions from high- dimensional biomedical data such as clinical scans. Yet, most prior ML methods were developed for applications where the ``prediction’’ task was about concurrent condition (e.g., discriminate cases and controls); and established risk factors (e.g., age), multiple modalities (e.g., genotype and images) and longitudinal data were not fully exploited. This application’s core innovation will be to develop rigorous, flexible, and practical ML methods that can fully exploit multi-modal, longitudinal, and high- dimensional biomedical data to compute prognostic clinical predictions. The proposed project will build on the PI’s strong background in computational modeling and analysis of large-scale biomedical data. We will employ an innovative Bayesian ML framework that offers the flexibility to handle and exploit real-life longitudinal and multi-modal data. We hypothesize that the developed models will be more useful than alternative benchmarks for identifying preclinical individuals who are at heightened risk of imminent clinical decline. We will use a statistically rigorous approach for discovery, cross-validation, and benchmarking the developed tools. This project will yield freely distributed, documented, and validated software and models for predicting future clinical progression based on whole-genome, longitudinal structural MRI and demographic data. We believe the algorithms and software we develop will yield invaluable tools for stratifying preclinical AD subjects in drug trials, optimizing future therapies, and minimizing the risk of adverse effects.

抽象的 阿尔茨海默病 (AD) 的“临床前”阶段的特点是脑部异常水平 在没有主要症状的情况下，淀粉样蛋白的积累可以持续数十年，并有可能保持 成功治疗策略的关键。如今迫切需要定量生物标志物 以及可以预测个体水平临床进展的基因测试。该项目将开发 尖端的机器学习算法将挖掘高维、多模态和 纵向数据来导出模型，在以下情况下产生个体水平的临床预测 失智。开发的预测模型将专门利用无处不在且负担得起的数据 类型：结构性脑部 MRI 扫描、唾液或血液来源的全基因组序列数据，以及 人口变量（年龄、教育程度和性别）。先前的研究表明，所有这些 变量与痴呆症的临床衰退密切相关，但迄今为止我们还没有模型 可以收获这些高维数据中嵌入的所有预测信息。 机器学习 (ML) 算法越来越多地用于计算来自高水平的临床预测。 三维生物医学数据，例如临床扫描。然而，大多数先前的机器学习方法都是为 “预测”任务与并发条件有关的应用程序（例如，区分案例和 控制）；和既定的风险因素（例如年龄）、多种模式（例如基因型和图像）和 纵向数据没有得到充分利用。该应用程序的核心创新将是开发 严谨、灵活、实用的机器学习方法，可以充分利用多模态、纵向和高阶特征 多维生物医学数据来计算预后临床预测。 拟议的项目将建立在 PI 在计算建模和分析方面的强大背景之上 大规模生物医学数据。我们将采用创新的贝叶斯机器学习框架，该框架提供 灵活地处理和利用现实生活中的纵向和多模式数据。我们假设 开发的模型将比用于识别临床前的替代基准更有用 临床即将衰退的风险较高的个人。我们将使用严格的统计方法 发现、交叉验证和对已开发工具进行基准测试的方法。该项目将 产生免费分发、记录和验证的软件和模型，用于预测未来的临床 基于全基因组、纵向结构 MRI 和人口统计数据的进展。我们相信 我们开发的算法和软件将为临床前 AD 分层提供宝贵的工具 药物试验中的受试者，优化未来的治疗方法，并最大限度地减少不良反应的风险。