Tools for standardizing clinical research metadata using HL7 FHIR

项目摘要 建议的项目是对U01融资机会公告(FOA)的回应，大数据将 知识(BD2K)在以下主题领域开发生物医学大数据软件工具和方法 正在应用元数据。这里的总体目标是设计、开发和评估一个集成的平台 利用基于标准的表示和可伸缩的临床研究元数据标准化 语义网技术。最终目标是推进临床研究数据的发现和分析 临床和翻译中心及研究人员的能力。临床和转化性研究 越来越多地涉及对大型数据集(例如，患者记录和基因组图谱)的操作，以及 复杂方法的应用。为了从如此庞大的数据集中得出临床相关的结论，临床 而翻译研究社区面临着与可扩展性相关的重大数据集成挑战， 互动性、表现标准、可持续性和稳健性。如果不能应对这些挑战， 对下游数据在更广泛的科学领域内的重复使用、共享和分析产生重大负面影响 社区。详细的临床模型(DCM)一直被视为保留可计算性的基础 这意味着在不同的临床系统之间交换数据。在新兴国家中 国际上关于DCM建模标准化的倡议是临床信息学建模 计划(CIMI)和HL7快速医疗互操作性资源(FHIR)。FHIR是一种新兴的HL7 标准；它利用现有的逻辑和理论模型来提供一致、易于实施和 在医疗保健应用程序之间交换数据的严格机制。然而，目前的工具箱 使HL7 FHIR能够作为全球数据模型来标准化临床研究元数据是非常有限的。是这样的 元数据包括与临床研究数据集和各种基础数据相关联的数据词典 现有集成数据仓库(IDR)中的模型，如集成生物学和 床边(I2b2)。拟议的项目利用新兴的语义网技术来提供 可扩展的基于标准的框架，可实现高效的大数据集成和语义 分享。拟议的项目建立在我们开发的语义元数据软件和基础设施上 以前的项目，包括NIH U24 BioCADDIE(生物医学和保健数据发现索引 生态系统)试点项目(PI：酱)，调查使用以下技术索引临床研究数据集的可行性 HL7 FHIR和一个NCI U01附录(PI：酱)，它创建了一个带有FHIR的开源IDR(例如i2b2)- 为癌症研究提供基于癌症数据的服务。拟议项目的目标是巩固， 开发和评估用于标准化临床研究元数据和数据模型的方法和工具 HL7冷杉。我们的具体目标是：1)整合我们用于索引临床研究元数据的BioCADDIE工具 使用HL7 FHIR；2)创建集成i2b2临床数据仓库和HL7 FHIR的方法和工具；3) 部署一个综合门户网站，以统一基于社区的元数据和传播工具。这个 拟议的项目将产生一套用于临床研究元数据标准化的方法和工具，使用 HL7 FHIR，并最终有效促进临床研究数据和应用程序的二次使用 推进临床和翻译数据发现和分析。

Project Summary The proposed project is in response to the U01 Funding Opportunity Announcement (FOA) for the Big Data to Knowledge (BD2K) Development of Software Tools and Methods for Biomedical Big Data in the topic area of applying metadata. The overall goal here is to design, develop and evaluate an integrated platform for clinical research metadata standardization leveraging both standards-based representation and scalable Semantic Web technologies. The ultimate goal is to advance clinical research data discovery and analytic capabilities for clinical and translational centers and investigators. Clinical and translational research studies increasingly involve the manipulation of large datasets (e.g., patient records and genomic profiles) and the application of complex methods. To derive clinically relevant conclusions from such large datasets, the clinical and translational research community faces significant data integration challenges related to scalability, interactivity, representation standards, sustainability, and robustness. Failure to deal with these challenges will have a significant negative impact on downstream data reuse, sharing and analysis in the broader scientific communities. Detailed Clinical Models (DCMs) have been regarded as the basis for retaining computable meaning when data are exchanged between heterogeneous clinical systems. Amongst the emerging national and international initiatives on the standardization of DCM modeling are the Clinical Informatics Modeling Initiative (CIMI) and the HL7 Fast Healthcare Interoperability Resources (FHIR). FHIR is an emerging HL7 standard; it leverages existing logical and theoretical models to provide a consistent, easy to implement, and rigorous mechanism for exchanging data between healthcare applications. However, currently the toolbox that enables HL7 FHIR as a global data model to standardize clinical research metadata is very limited. Such metadata include data dictionaries associated with clinical research datasets and a variety of underlying data models in the existing integrated data repositories (IDRs) such as the Informatics for Integrating Biology and the Bedside (i2b2). The proposed project leverages emerging Semantic Web technologies to provide a scalable standards-based framework that enables effective and efficient big data integration and semantic sharing. The proposed project builds on semantic metadata software and infrastructure developed in our previous projects, including an NIH U24 bioCADDIE (biomedical and healthCAre Data Discovery Index Ecosystem) pilot project (PI: Jiang) that investigates the feasibility of indexing clinical research datasets using HL7 FHIR, and an NCI U01 supplement (PI: Jiang) that creates an open-source IDR (e.g., i2b2) with FHIR- based cancer data services for cancer research. The objective of the proposed project is to consolidate, develop, and evaluate methods and tools for standardizing clinical research metadata and data models using HL7 FHIR. Our specific aims are: 1) Consolidate our bioCADDIE tools for indexing clinical research metadata using HL7 FHIR; 2) Create methods and tools for integrating i2b2 clinical data repository with HL7 FHIR; 3) Deploy an integrated web-portal for community-based metadata harmonization and tool dissemination. The proposed project will produce a suite of methods and tools for clinical research metadata standardization using HL7 FHIR and effectively facilitate secondary use of clinical research data and applications, ultimately advancing clinical and translational data discovery and analytics.