SBIR Phase I: Optimal Clinical Workforce Staffing and Scheduling using an Advanced Predictive Modeling System

SBIR第一阶段项目旨在优化急诊科人员配置决策。直接的病人护理人员成本消耗了平均医院运营收入的近50%。随着医院适应快速变化的医疗保健市场，医院管理层往往寻求降低员工成本，以提高运营可行性。这些削减成本的举措带来了重大风险，研究表明，低于目标水平的单位人员配备与死亡率和其他不良患者事件增加有关。人员配备不足导致工作人员感到过度劳累，并导致倦怠，这使医院每年损失超过90亿美元，部分原因是人员流动。优化临床人力配置在急诊科尤为重要，急诊科必须提供按需可用的工作人员，以满足快速变化的患者人群的需求，而不会出现重大延误。美国近一半的医疗服务发生在急诊室，过去十年急诊室就诊人数增加了44%，因此美国公共卫生部门必须优化急诊室人员配置，以确保优质的患者护理和临床结果，同时还提供更好的财务业绩。没有全面的技术存在优化急诊科人员配置决策。该SBIR第一阶段项目将用于：i）开发自动化急诊科患者需求预测引擎，并创建自动化预测模型重新校准过程的软件平台; ii）开发人员柔性推荐器和决策支持引擎，其允许在做出最终人员配置决策之前进行用户输入和临床判断，以及iv）为决策支持引擎开发适合于急诊科的动态临床设置的以人为中心的设计界面。该引擎及其用户界面将与三个测试网站合作开发。在项目成功完成后，该引擎将被用于在拟议的测试站点进行数据驱动的人员配置决策的成本效益分析。该奖项反映了NSF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。

This SBIR Phase I project aims at optimizing emergency department staffing decisions. Direct patient care staffing costs consume nearly 50% of an average hospital's operating revenues. As hospitals adapt to a rapidly changing healthcare market, hospital management often seek to reduce staffing costs to increase operational viability. These cost-cutting initiatives introduce significant risk exposure, with studies showing that staffing a unit below the target level is associated with increased mortality and other adverse patient events. Inadequate staffing causes staff to feel overworked and leads to burnout, which costs hospitals over $9 billion annually, in part because of turnover. Optimizing clinical workforce staffing is especially critical in the emergency department, which must provide on-demand availability of staff to meet the needs of rapidly changing patient populations without significant delay. With nearly half of all medical care in the United States occurring in emergency departments and visits to the emergency department increasing 44% over the past decade, it is essential for U.S. public health to optimize emergency department staffing to ensure quality patient care and clinical outcomes, while also delivering better financial performance. No comprehensive technology exists for optimizing emergency department staffing decisions. This SBIR Phase I project will be used to: i) develop an automated emergency department patient demand predictive engine and create a software platform that automates the predictive model recalibration process; ii) develop a staff flexing recommender and decision support engine, which allows for user input and clinical judgment before a final staffing decisions is made, iii) integrate the recommender engine with real-time patient volume feed, and iv) develop human-centered design interface for the decision support engine that is appropriate for the dynamic clinical setting of the emergency department. The engine and its user interface will be developed in collaboration with three beta sites. Upon successful completion of the project, the engine will be used for cost-benefit analysis of data driven staffing decision making at the proposed beta sites.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.