SBIR Phase I: Nursing Workforce Optimization Algorithm and Software

这项小企业创新研究（SBIR）第一阶段项目具有更广泛的影响/商业潜力，可改善医院的护理操作，从而改善患者的治疗效果。这将通过分析卫生系统有关护士人员配置、日程安排和护士-患者匹配的数据来实现。本研究将分析护士、患者和住院患者临床环境的数据及其与结果的关系，以开发护理设施中独特的算法、软件和数据集。这一点很重要，因为护理人员管理决策的方法会影响护理结果和提供优质护理的成本。这个小企业创新研究（SBIR）第一阶段项目涉及先进的研究技术，旨在优化护士人员配置、调度和护士-患者匹配。关系将在1。2.与护理操作相关的自变量。因变量，包括由医疗保健质量和研究机构制定的患者安全指标变量。对这些关系的探索将有助于回答以下问题：1)每天雇佣和部署多少护士（即人员配置），2)轮班部署护士的数量和补充情况（即调度），以及3)如何在每个班次的每个单元匹配护士和患者（即护士-患者分配）以优化结果。提出的优化过程使数据驱动的方法，以解决人员配备，调度和护士-病人匹配的挑战。方法涉及多元回归分析和机器学习技术，包括自回归积分移动平均（ARIMA）。本研究的目标涉及算法和软件的开发，使医院管理人员具有洞察力和技术，以改善护理和患者的结果。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 improves nursing operations in hospitals for better patient outcomes. This will be achieved through the analysis of a health system’s data regarding nurse staffing, scheduling, and nurse-patient matching. This research will analyze data on nurses, patients, and inpatient clinical environments and their relationship to outcomes to develop unique algorithms, software, and datasets in care facilities. This is significant because the approach to nursing workforce management decisions influences care outcomes and the cost of delivery of quality care. This Small Business Innovation Research (SBIR) Phase I project involves advanced research techniques that aim to optimize nurse staffing, scheduling, and nurse-patient matching. Relationships will be examined between 1. independent variables associated with nursing operations and 2. dependent variables that include patient safety indicator variables developed by the Agency for Healthcare Quality and Research. The exploration of these relationships will help answer questions including 1) how many nurses to employ and deploy day-to-day (i.e. staffing), 2) how many and in what complement to deploy nurses on shifts (i.e. scheduling), and 3) how to match nurses to patients on each unit each shift (i.e. nurse-patient assignments) to optimize outcomes. The proposed optimization process enables a data- driven approach to address staffing, scheduling, and nurse-patient matching challenges. The methods involve multivariate regression analyses and machine learning techniques including autoregressive integrated moving average (ARIMA). The goals of this research involve the development of algorithms and software that empower hospital administrators with the insight and technology to improve nursing care and 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.