GOALI: Statistical Quality Control Methods for Health Systems Problems

这项学术联系机会奖(GOALI)的研究目标是为医疗保健不良事件开发新的统计质量控制，如用药和实验室差错、医院获得性感染以及其他可预防的问题和错误。三种新的方法是基于反二项抽样和混合非相同分布的罕见事件控制方法，将Logistic回归和其他方法结合到一个通用的风险质量控制框架中，并同时结合这些控制方法。将开发和使用数值程序来研究这些方法的统计性能和操作特性，并将开发和实施优化搜索算法以确定方法的最优经济和统计经济设计。开发的方法还将使用两家学术医院的大型数据库药物事件、针刺损伤和耐甲氧西林金黄色葡萄球菌进行经验验证。如果成功，这项研究的好处将导致改进监测方法，并减少可预防的不良医疗事件的发生，据估计，这些事件将导致200万患者受伤，4.5万至9.8万人死亡，全国每年的成本为88亿美元。开发的方法将提供更大的统计能力来检测罕见不良事件发生率的变化，并将准确地考虑聚集的同类患者。确定每种方法的运行特性和最佳设计将有助于减少发现问题的时间和相关成本。结果将用于比较建议的医院监测方法和传统的医院监测方法，确定每种方法比其他方法更好的条件，并制定设计和选择指南。所提出的研究也将有益于高产量制造业和其他行业中类似的质量控制问题。

The research objectives of this Grant Opportunities for Academic Liaison with Industry (GOALI) award are to develop new statistical quality control for healthcare adverse events, such as medication and laboratory errors, hospital-acquired infections, and other preventable problems and mistakes. Three new methods will be control rare events based on inverse binomial sampling and mixtures of non-identical distributions, to incorporate logistic regression and other approaches into a general risk quality control framework, and to combine these control methods simultaneously. Numeric programs will be developed and used to investigate the statistical performance and operating characteristics of these methods, and an optimization search algorithm will be developed implemented to determine the optimal economic and statistical-economic designs of methods. Developed methods also will be validated empirically using large database drug events, needle stick injuries, and methicillin-resistant Staphylococcus aurous at two academic hospitals.If successful, the benefits of this research will lead to improved surveillance methods and reduce the occurrence of preventable adverse healthcare events, estimated to result to 2 million patient injuries, 45,000 to 98,000 deaths, and $8.8 billion in costs annual nationwide. The developed methods will provide greater statistical power to detect changes in the occurrence rates of infrequent adverse events and will accurately account for aggregation homogeneous patients. Determining the operating characteristics and optimal design of each method will help reduce the time to detect problems and the associated costs. Results will be used to compare proposed and traditional hospital surveillance methods, identify conditions under which each method performs better than others, and develop design and selection guidelines. The proposed research also will benefit similar quality control problems in high yield manufacturing and other industries.