SBIR Phase I: Tackling Healthcare’s Paradoxes: Quality Patient Care, Provider Workflow, and Data Security

该小型企业创新研究（SBIR）第一阶段项目的更广泛影响/商业潜力是为医生提供一种新工具，以自动准备保险文件并促进索赔，这可能有助于降低提供者成本并提高患者获得护理的机会和质量。医生可以花费高达50%的时间执行非临床任务，这些任务也与医生倦怠有关，这是一种已知会导致医疗错误，护理质量降低，成本升高和患者总体预后较差的心理状况。拟议的创新是一种专有算法，利用数据自动完成保险表格文档。这项新技术旨在通过简化医疗表格文档的准备，提供更简单的提供者体验，从而解决工作流程瓶颈并补充现有的临床工作流程。 这个小型企业创新研究（SBIR）第一阶段项目旨在开发一个支持机器学习的电子病历访问工具集，旨在自动化和简化保险表格文档的准备。美国医疗体系的一个主要问题是医疗服务提供者通过医疗保险公司寻求报销的过程。提交索赔和寻求保险公司对程序或测试的事先授权是一个缓慢且容易出错的手动过程，通常会导致治疗延迟甚至拒绝，危及患者健康，并导致更高的成本。该技术专为医生设计，将使用预先训练的自然语言模型来促进索赔建立，以从各种输入中提取医疗文本和关系，包括患者和提供者人口统计信息以及付款人信息，临床分类学，功能特征，该奖项反映了NSF的法定使命，并被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准。

The broader impact /commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to provide a new tool for physicians to potentially automate the preparation of insurance documentation and facilitate claim building which may help to lower provider costs and increase patient access to and quality of care. Physicians can spend up to 50% of their time performing non-clinical tasks which have also been associated with physician burnout, a psychological condition known to result in medical errors, lower quality of care, higher costs, and overall poorer patient outcomes. The proposed innovation is a proprietary algorithm that leverages data to automate the completion of insurance form documentation. This new technology aims to resolve workflow bottlenecks and complement existing clinical workflows by delivering a simpler provider experience by streamlining the preparation of medical form documentation. This Small Business Innovation Research (SBIR) Phase I project aims to develop a machine learning-enabled electronic medical record access toolset designed to automate and streamline the preparation of insurance form documentation. A major issue in the US healthcare system is the process through which healthcare providers seek reimbursement through health insurance companies. Filing claims and seeking prior authorizations on procedures or tests from insurance companies is a manual process that is slow and error prone, often resulting in delays in treatment or even rejection, jeopardizing patient health, and resulting in higher costs. Designed for physicians, the proposed technology will facilitate claim building using pre-trained natural language models to extract medical text and relationships from various inputs including patient and provider demographic information as well as payer information, clinical taxonomy, functional features, and relations.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.