Artificial Intelligence Strategies for Alzheimer's Disease Research

阿尔茨海默病（AD）是一种常见的疾病，其部分原因是蛋白质错误折叠， 聚合来对AD的研究是国家的优先事项，每年有550万美国人受到影响。 花费超过2500亿美元，而且没有可用的治疗方法。这是尽管大量投资， 在实验和基于人群的研究中收集各种临床和生物学数据。 人工智能（AI）和机器学习有可能揭示临床和医学领域的模式。 使用标准方法尚未发现的多源大规模阿尔茨海默氏症数据。 我们在这里提出了一个全面的生物医学计算和健康信息学研究项目 开发和应用尖端的人工智能算法和生物医学软件，用于分析大型 规模AD数据。这个拟议的信息学计划的核心是PennAI方法， 用于通过AI算法自动化机器学习的软件，该算法可以从先前的 分析。这种方法消除了选择正确机器学习算法的猜测 和参数设置，从而使这种计算技术对每个人都是可访问的。 具体来说，我们将开发三种新的信息学方法来定制PennAI，以分析 AD数据。首先，我们将开发一个多模态交互（M2I）特征选择算法， 识别预测AD的遗传相互作用（AIM 1）。第二，我们会发展一个 知识驱动的多组学集成（KMI）算法，用于组合AI的组学特征 AD分析（AIM 2）。第三，我们将开发多维脑成像组学（MBIO） 多源大规模数据联合分析预测AD的集成框架。 最后，我们将把这三种生物医学信息学方法整合到我们的开源PennAI中。 软件包，并将其应用到两个大的人口为基础的研究AD。我们期待彭奈 将揭示AD的新生物标志物，为更好的治疗和临床决策打开大门 支持.

Alzheimer's disease (AD) is a common disease that is partly due to protein misfolding and aggregation. Research on AD is a national priority with 5.5 million Americans affected at an annual cost of more than $250 billion and no available cure. This is despite heavy investments in the collection of diverse clinical and biological data in experimental and population-based studies. Artificial intelligence (AI) and machine learning have the potential to reveal patterns in clinical and multi-source large-scale Alzheimer’s data that have not been found using standard approaches. We propose here a comprehensive biomedical computing and health informatics research project to develop and apply cutting-edge AI algorithms and biomedical software for the analysis of large- scale AD data. At the heart of this proposed informatics program is the PennAI method and software for automating machine learning through an AI algorithm that can learn from prior analyses. This approach takes the guesswork out of picking the right machine learning algorithms and parameter settings thus making this computing technology accessible to everyone. Specifically, we will develop three novel informatics methods to tailor PennAI to the analysis of AD data. First, we will develop a Multi-Modal Interaction (M2I) feature selection algorithm for identifying genetic interactions that are predictive of AD (AIM 1). Second, we will develop a Knowledge-driven Multi-omics Integration (KMI) algorithm for combining omics features for AI analysis of AD (AIM 2). Third, we will develop a Multidimensional Brain Imaging Omics (MBIO) integration framework for the joint analysis of multi-source large-scale data for predicting AD. Finally, we will integrate all three biomedical informatics methods into our open-source PennAI software package and apply it to two large population-based studies of AD. We expect PennAI will reveal new biomarkers for AD that will open the door for better treatments and clinical decision support.