SBIR Phase I: RightFit: An Intelligent Patient-Provider Scheduling System for Healthcare Facilities

这项小企业创新研究（SBIR）第一阶段项目的更广泛影响/商业潜力将来自改善美国医疗保健质量，并通过循证驱动的医患匹配降低普通选择性手术程序的相关成本。这项技术将提高护理质量，减少与这些程序相关的成本变化。该平台将更好地装备卫生设施，使其能够在一个正在向基于价值的保健过渡的行业中提供可持续的高质量护理。该项目的商业影响将来自为医疗保健设施节省开支。个性化的医生安排可以帮助患者获得最有益的护理，并有可能减少并发症和改善患者的预后。通过该技术实现的设施级成本降低和患者预后改善不仅转化为患者的成本节约，而且还提高了医疗保健设施的能力。这个小企业创新研究（SBIR）第一阶段项目将解决减少选择性医疗程序的结果和成本差异的需求，这些差异涉及的因素包括医生的可用性、护理团队对医疗结果和成本的影响，以及医生培训和学习的长期影响。该方法将基于数据分析、随机过程和机器学习的独特组合，应用于患者-提供者匹配问题。本项目需要解决的技术挑战包括医生力量的动态性、难以将结果归因于团队中的个别医生，以及在适应卫生设施数据库方面面临的挑战。该团队将与医疗保健合作伙伴密切合作，利用医生和团队绩效的历史数据以及他们的反馈来开发一个有影响力且科学合理的原型。预期的技术成果包括拟定研究结果的文件和用于医疗机构一级的技术原型版本。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 will result from improving the quality of healthcare in the United States and reducing the associated costs for common elective surgery procedures through evidence-driven patient-physician matching. This technology will improve the quality of care and reduce the variation in costs associated with these procedures. The platform will better equip health facilities to deliver sustainable, high-quality care in an industry that is transitioning towards value-based care. The commercial impact of the project will result from generating savings to healthcare facilities. Personalized physician scheduling helps patients access the most beneficial care and has the potential to reduce complications and improve patient outcomes. Facility-level cost reduction and patient outcome improvement enabled by this technology not only translates to cost savings for patients, but also increased capacity for the healthcare facilities.This Small Business Innovation Research (SBIR) Phase I project will address the need for reducing the variations in outcomes and costs in elective medical care procedures with respect to factors including physician availability, the impact of care teams on medical outcomes and cost, and the effects of physician training and learning over time. The approach will be based on a unique combination of data analytics, stochastic processes, and machine learning, applied to the patient-provider matching problem. The technical challenges to be addressed in this project include the dynamic nature of physician strengths, the difficulty in attribution of outcomes to individual physicians in a team, and the challenges in adapting to the databases of health facilities. The team will closely collaborate with healthcare partners, leveraging historical data on physician and team performance over time as well as their feedback to develop an impactful and scientifically justified prototype. Anticipated technical results include documentation of the results of the proposed research and a prototype version of the technology for use at the healthcare facility level.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.