Proper management of patient wait times and service times may support smarter and proactive decisions in managing patient flow. Those decisions usually impact on resource allocation and hospital process management. For example, how can the hospital know where to provide more staff to reduce the increased wait times in the hospital? Given that additional resource allocation comes with increased cost and there are competing priorities, the hospital decision makers need to determine which course of action is the most appropriate one to take. Decisions made based on information within a departmental silo may not be the optimal one. Such decisions may only transfer the patient flow bottleneck to another department. In this thesis, we propose a state monitoring engine (SME) for inferring and managing states that is an improvement over traditional CEP approaches. Our proposed engine is based on an application meta-model for care process monitoring developed by (Baarah & Peyton, 2012). In addition, to inferring and managing states, the SME dynamically populates a real-time data warehouse for care process monitoring by mapping the events and inferred states into an Online Analytical Process
Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.
Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.