Data Integration Core

摘要 阻塞性睡眠呼吸暂停(OSA)是一种常见的慢性疾病，全球有超过10亿人受到影响。 未诊断和未治疗的阻塞性睡眠呼吸暂停综合症也与巨大的经济负担有关，占 估计每年的成本为1496亿美元。考虑到巨大的疾病负担和相关的经济成本 对于未经诊断和治疗的阻塞性睡眠呼吸暂停综合征，需要一个强有力的临床研究框架来解决预防问题， 阻塞性睡眠呼吸暂停综合征的诊断和治疗。阻塞性睡眠呼吸暂停的P4医学方法 计划项目旨在进行科学研究，预测谁会患上这种疾病，预防阻塞性睡眠呼吸暂停综合症和 它的不良后果，并个性化的诊断、治疗和临床护理。为了研究OSA 通过本计划中的项目，来自各种数据源的多样和复杂的数据，包括 电子健康记录(EHR)、每日持续气道正压(CPAP)使用和遵守情况 必须研究信息、遗传学和分子生物标记物。有效回答科学问题 在每个项目的提出下，我们构建了一个数据集成核心(Core C)来收集、集成和分析 从这些不同的数据源获得的信息。我们的团队将由导演约翰·霍姆斯博士领导， 资深医学信息学家和流行病学家，拥有超过35年的数据库设计和 实施、开发临床研究信息系统，并与 生物统计学家和临床研究人员。Core C将由临床医生Danielle Mowery博士共同领导 在数据科学、机器学习和临床研究信息学方面有专长的信息学家，以及迭戈博士 Mazzotti是一名睡眠医学研究员，曾接受过生物医学信息学方面的专门培训。核心C领导层 和支持人员带来了在临床研究、睡眠医学、数据科学、信息学、 数字健康、基因组科学、流行病学和生物统计学。总的来说，Core C将提供数据收集 和管理资源，以及开发和采用最先进的数据方法 集成和分析以支持所有项目。我们还将实施与临床所有阶段相关的策略 研究数据管理，包括临床数据库挖掘、异类数据源的集成以及 根据可查找、可访问、可互操作和可重用(公平)原则表示数据，使所有 工具和方法是开源的，可供广大生物医学研究社区使用。

ABSTRACT Obstructive sleep apnea (OSA) is a common chronic disorder affecting over 1 billion people worldwide. Undiagnosed and untreated OSA is also associated with a substantial economic burden, accounting for an estimated annual cost of $149.6 billion. Given the significant disease burden and economic costs associated with undiagnosed and untreated OSA, a robust clinical research framework is needed to address the prevention, diagnosis, and treatment of OSA. The P4 Medicine approach to Obstructive Sleep Apnea that drives this overall Program Project aims to conduct scientific studies that predict who will develop the disorder, prevent OSA and its adverse consequences, and personalize diagnoses, therapies, and clinical care. In order to study OSA through the Project in this Program, diverse and complex data from a variety of data sources, including the electronic health record (EHR), daily continuous positive airway pressure (CPAP) usage and adherence information, genetics, and molecular biomarkers must be studied. To effectively answer the scientific questions posed by each Project, we have constructed a Data Integration Core (Core C) to collect, integrate, and analyze information derived from these varied data sources. Our team will be led by Director Dr. John Holmes, an established medical informatician and epidemiologist with over 35 years of experience in database design and implementation, development of information systems for clinical research, and analytic collaborations with biostatisticians and clinical researchers. Core C will be co-led by co-Directors Dr. Danielle Mowery, a clinical informatician with expertise in data science, machine learning, and clinical research informatics, and Dr. Diego Mazzotti, a sleep medicine researcher with specific training in biomedical informatics. The Core C leadership and support staff bring decades of experience in clinical research, sleep medicine, data science, informatics, digital health, genome science, epidemiology, and biostatistics. Collectively, Core C will provide data collection and management resources, as well as development and incorporation of cutting-edge approaches to data integration and analysis to support all Projects. We will also implement strategies related to all stages of clinical research data management, including clinical database mining, integration of heterogeneous data sources, and data representation according to Findable, Accessible, Interoperable and Reusable (FAIR) principles, making all tools and approaches open-source and available to the biomedical research community at large.