I-Corps: Assessment Platform for Operationalizing High Reliability Organizational Hallmarks in Healthcare

I-Corps项目更广泛的影响/商业潜力是开发具有嵌入式机器学习算法的软件，旨在为提供者和患者创造更安全的医疗保健环境。潜在市场包括所有类型和规模的医疗机构，包括国家医疗保健系统、大型地区医院、社区卫生中心、农村医院和流动诊所。拟议的技术的目标是通过支持行政和临床合作伙伴关系，促进质量和患者安全的文化，因为他们正在向医疗保健领域实现高可靠性组织标志的目标过渡。文化上的这种变化可能会减少可避免的医疗差错的发生率，因此，可能会使一般人群更负担得起医疗保健。I-Corps项目的基础是软件开发，旨在增加临床医生对未遂事故和安全事故的报告，以及管理员利用这些报告，根据高可靠性组织（HRO）理论，在医疗保健领域做出明智的系统级改进。由于解决最终用户报告的常见生理和心理障碍的协议和软件不足而导致的安全事件缺乏自愿报告，这在医疗保健领域是个问题。此外，对于那些收集到的报告，没有公认的标准来科学地根据人力资源主管的管理特征对其进行评分；这使得它们的推论效用被边缘化。该技术通过采用人为因素原则设计的前端web和应用程序界面，以及后端机器学习和自然语言处理算法，对安全事件报告的语料库进行实时分类，解决了这两个问题。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 is the development of software with embedded machine learning algorithms that seeks to create a safer healthcare environment for both providers and patients. The potential market includes all types and sizes of healthcare institutions, including national healthcare systems, large regional hospitals, community health centers, rural hospitals, and ambulatory clinics. The goal of the proposed technology is to promote a culture of quality and patient safety by supporting administrative and clinical partnerships as they transition toward a goal of operationalizing High Reliability Organizational Hallmarks in healthcare. This change in culture may reduce the incidence of avoidable medical errors, and as a result, may make healthcare more affordable for the general population.This I-Corps project is based on the development of software that seeks to both increase the reporting of near-miss and safety incidents by clinicians and the utilization of these reports by administrators to make informed system-level improvements in healthcare based on High Reliability Organizational (HRO) theory. The lack of voluntary reporting of safety incidents arising from the inadequacy of protocols and software addressing the common physical and psychological barriers to reporting by the end user is problematic in healthcare. In addition, for those reports that are collected, there are no accepted rubrics for scientifically scoring them against the managerial hallmarks of an HRO; This marginalizes their inferential utility. The proposed technology addresses both of these issues through the implementation of a front-end web and application interface that is designed using human factors principles, and a back-end machine learning and natural language processing algorithm that classifies the corpus of safety incident reports in real-time.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.