SBIR Phase II: Linking eLearning to patient outcomes

SBIR第二阶段项目的更广泛/商业影响侧重于改善慢性病的管理，使以团队为基础的初级保健成为实现临床结果和利用新的“基于价值”的支付改革的关键。根据美国疾病控制中心的数据，十分之六的成年人患有慢性病，全国年度医疗支出的90%花在患有这些疾病的人身上。我们的技术建议应用精确教育教学理论来增强初级保健团队的能力，并促进情景意识、加强沟通、明确角色、改善协调和领导支持，以改善患者结局，这与国家科学基金会促进科学以促进国家健康的使命直接一致。这个项目是为联邦合格健康中心(FQHC)的商业使用而设计的，这些中心为美国每12个人中就有一个提供服务。美国有1,373家FQHC，每年为医疗服务不足地区的2700万患者提供服务。公共和私人支付模式正在迅速转向基于团队的护理的激励/奖金，并证明结果有所改善。改善慢性病患者的护理成本和结果将为国家带来巨大的社会和经济效益。这个SBIR第二阶段项目使用机器学习将个人水平的临床和社会特征整合到建议的治疗路径中，并应用精确培训技术来提高护理团队个人成员的技能。我们的目标是验证机器学习的可行性，根据患者数据中确定的护理趋势和差距，为卫生专业人员提供建议的工作流程和继续教育。该方法包括用于指导强化学习的计算引擎。机器学习使统计模型的开发成为可能，以建立临床干预的效果大小，基于患者的结果对卫生团队成员进行个性化指导和支持。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader/commercial impact of this SBIR Phase II project focuses on improving the management of chronic disease by enabling team-based primary care is key to achieving clinical results and taking advantage of new “value based" payment reforms. According to the United States Centers for Disease Control, six out of ten adults have a chronic disease and 90% of the national annual healthcare expenditures are spend on people with these conditions. Our technology proposes to apply precision-education instructional theory to enhance primary care team competencies and promote situational awareness, enhanced communication, defined role clarity, improved coordination and leadership support to improve patient outcomes which is directly aligned to the National Science Foundation’s mission of promoting science to advance the nation’s health. This project is being designed for commercial use in Federally Qualified Health Centers (FQHCs) which serve one in twelve people in the United States. There are 1,373 FQHCs in the US serving 27 million patients annually in medically underserved areas. Public and private payment models are rapidly moving toward incentives/bonuses for team-based care and demonstrated outcome improvements. Improvements in the cost and outcomes of care for this patients with chronic disease will have enormous social and economic benefit for the Nation.This SBIR Phase II project uses machine learning to integrate individual-level clinical and social characteristics into suggested treatment paths and to apply precision training techniques that improve the skills of individual members of the care team. Our objectives focus on validating the feasibility of machine learning to provide health professionals with recommended workflows and continued education based on trends and gaps in care identified from patient data. The method includes a computational engine to guide reinforcement learning. Machine learning has made possible the development of statistical models to establish effect sizes of clinical interventions, enabling personalized instruction and support to health team members based on patient outcomes.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.