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

这项小企业创新研究（SBIR）第一阶段项目的更广泛影响/商业潜力旨在改善健康结果，同时管理成本。所提出的技术能够在区块链保护的分布式生态系统中集成和检索来自许多地方和格式的数据。医疗保健是一个价值29亿美元的细分市场，之所以成为目标，是因为需求巨大，而美国医疗保健市场高度分散。在保持数据完整性、安全性和隐私性的同时，加快医疗保健数据的互操作和共享速度，是潜在改善医疗保健结果的关键。这个小企业创新研究（SBIR）第一阶段项目正在推进在分布式数据平台上搜索和检索区块链保护的异构数据的基础技术。具有不同格式和数据模型的多个数据源将在区块链中转换为更细粒度的数据块。除了将区块链数据规范化为更细粒度的数据块，以便在不同的应用程序中共享和重用（即简化数据集成和互操作性）之外，研究还将使用自然语言处理（NLP）来协助自动生成元数据标签，以方便跨区块链的搜索。为了提高在搜索中返回的数据的准确性，将创建一个人类专家策划的医疗保健词典和同义词库，并与NLP协助一起使用。这种组合方法可以提高非it、医疗保健、用户在一个安全的点对点数据平台上检索数据的准确性，在这个平台上，数据所有者保留对其数据的完全所有权和控制权。拟议的研究还将通过性能测试验证新的区块链搜索功能是否能够满足医疗保健企业所需的响应能力和规模，这是商业化的关键需求。特别是，该项目将在地理上分散的网络上建立速度和延迟的基准。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识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 I project aims to improve health outcomes while managing costs. The proposed technology enables the integration and retrieval of data from many places and formats across a distributed ecosystem secured by blockchain. Healthcare, a $2.9 B market segment, is targeted because the need is great and the US healthcare market is highly fragmented. Making healthcare data faster to interoperate and share while maintaining data integrity, security and privacy is key to potentially improving healthcare outcomes. This Small Business Innovation Research (SBIR) Phase I project is advancing foundational technology for searching and retrieving heterogeneous data secured in blockchain across a distributed data platform. Multiple data sources with different formats and data models will be transformed into more granular data blocks in blockchain. In addition to normalizing blockchain data into more granular data blocks for sharing and re-use in different applications (i.e., simplifying data integration and interoperability), research will use natural language processing (NLP) to assist in automatically generating metadata tags to facilitate searching across blockchains. To improve the accuracy of data returned in the search, a human expert-curated healthcare dictionary and thesaurus will be created and used in concert with NLP assistance. This combined approach should improve the accuracy of data retrieval by non-IT, healthcare, users across a secure, peer-to-peer data platform where data owners retain full ownership and control of their data. The proposed research will also validate through performance testing new blockchain search capabilies will meet the responsiveness and scale required by healthcare enterprises, a key need for commercialization. In particular, the project will establish benchmarks for speed and latency across a geographically dispersed network.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.