SBIR Phase II: A Platform for Health Care Data Integration Using Blockchain and Artificial Intelligence

该小型企业创新研究（SBIR）II期项目的更广泛影响/商业潜力是提供改善患者结局和体验所需的个人医疗保健数据。由于医疗保健数据受到保护，因此需要一种安全的方式在正确的时间与正确的人共享正确的数据。目前，试图统一来自许多系统的数据，并以许多格式和大小是非常困难和昂贵的，因此缺乏这种努力。推进区块链和人工智能技术用于分布式数据管理，实现彻底的数据互操作性，使患者受益，并解决了3.93万亿美元医疗保健市场的优先需求。该团队开发了一个平台的技术，该平台可以保护来自不可变区块链中任何地方的任何类型的数据，同时各个数据所有者保留所有权和控制权，以安全地共享-需要遵循其数据治理标准的数据。数据被转换和规范化到更细粒度的区块链中，并且可以组合用于个体或聚合人群健康建模。自然语言处理与精心策划的词库相结合，为加密的区块链自动创建元数据标签，促进数据搜索，发现和高级分析。由于医疗保健数据复杂多样，该项目通过优先用例演示了数据如何实现互操作。 这些用例包括：1）共享患者临床数据，以便在同意的情况下参与临床研究; 2）创建跨越许多服务或治疗的更完整的患者医疗保健记录; 3）弥合临床数据和索赔之间的操作差距;以及4）研究组织之间在严重疾病治疗方面的合作。其他技术包括从区块链中实例化“按需数据集市”，用于分析，机器学习，以及通过智能合约，捕获标准和类似同意自动共享数据。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is to provide the personal healthcare data needed to improve the patient’s outcome and experience]. Because healthcare data is protected, a secure way of sharing the right data, with the right people, at the right time is needed. Currently, attempts to harmonize data from many systems, and in many formats and sizes is very difficult and expensive and so such efforts are lacking. Advancing blockchain and artificial intelligence technologies for distributed data management and enabling radical data interoperability benefits patients and addresses a priority need in a $3.93 trillion healthcare market.This team develops the technology for a platform that secures data of any type from anywhere in immutable blockchains while respective data owners retain ownership and control to securely share just-needed data following their data governance criteria. Data is transformed and normalized into more granular blockchains and that can be combined for individual or aggregated population health modeling. Natural language processing is combined with a curated thesaurus to automatically create metadata tags for encrypted blockchains, facilitating data searches, discovery, and advanced analytics. Because healthcare data is complex and diverse, this project demonstrates, through priority use cases, how data needs to become interoperable. Such use cases include 1) sharing patient clinical data for participation in clinical research with consent; 2) creating a more complete patient healthcare record that spans many services or treatments; 3) bridging an operational gap between clinical data and claims; and 4) collaborating among research organizations in severe disease treatment. Additional technologies include instantiating a "datamart on demand" from blockchains for analytics, machine learning, and automating sharing of data, via smart contracts, capturing criteria, and like consent.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.