I-Corps: A data capture and management technology to transform data access, structure, and security

I-Corps项目的更广泛影响/商业潜力是调查描述健康和保健数据的技术应用。进行临床试验的研究人员可以使用这项技术来获取真实世界的患者数据，并简化大规模的后期试验，加速新药和治疗方式的开发。生命科学家可以利用这项技术来加速基础科学的发现，并促进这些发现从实验室到临床的转化。人力资源人员可以更好地跟踪、管理和处理员工健康规划中产生的数据，以减少病假、提高生产力和提高员工满意度。卫生项目协调员有可能促进公共卫生干预和开展研究。护理管理人员和临床医生可以为慢性病人群部署和管理远程管理服务，防止不必要的住院治疗，改善健康结果，并降低护理管理成本。这个I-Corps项目探索了数据捕获和管理技术的贸易空间，以改变数据访问、结构和安全性。该技术由几个核心组件组成，包括：(1)通用包装程序应用程序接口（API），该接口可与现有和未来的硬件、软件和其他数据源进行扩展；(2)数据规范化算法和实体关系模型，将数据结构化并与数据源关联；(3)安全和隐私控制，以保护数据源隐私和最终用户的合规性；(4)机器学习和预测分析，使用不同模式的数据，将数据转化为可操作的见解，用于各种商业用途。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 I-Corps project investigates applications of technologies describing health and wellness data. Researchers conducting clinical trials can use this technology to capture real-world patient data and streamline large-scale late phase trials, accelerating the development of new pharmaceuticals and treatment modalities. Life scientists could use this technology to accelerate basic science discovery and facilitate translation of these findings from the bench to bedside. Human resources personnel could better track, manage, and act on data generated in employee wellness programming toward fewer sick days, more productivity, and higher employee satisfaction. Health program coordinators could potentially facilitate public health interventions and perform research. Care managers and clinicians could deploy and manage remote management services to chronic disease populations, preventing unnecessary hospitalizations, improving health outcomes, and lowering the cost of care management. This I-Corps project explores the trade space of a data capture and management technology to transform data access, structure, and security. This technology consists of several core components, including (1) A universal wrapper application program interface (API) that scales with existing and future hardware, software, and other data sources; (2) A data normalization algorithm and entity relationship model to structure data and affiliate it with the data source; (3) Security and privacy controls to protect data source privacy and end-user regulatory compliance; (4) Machine learning and predictive analytics using data in different modalities to translate data into actionable insights for a variety of commercial uses.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.