Variations of length of stay: a case study using control charts in the CRISP-DM framework

Abstract

In-patient length of stay (LOS) at hospitals is considered a critical 'catch-all' metric because it is widely used to measure the overall efficiency of healthcare services. The goal of this paper is to effectively analyse and monitor hospital LOS to help improve healthcare quality. Given the fact that abnormal LOS results in increasing cost for all stakeholders, this study proposes a new framework based on cross-industry standard process for data mining framework (CRISP-DM) and Six Sigma methodology, including control charts for monitoring and improving LOS. The utility of the proposed method is demonstrated through a case study involving 11,722 internal medicine patients at a large hospital in Southwest Virginia. Outcomes of this study have potential to support decision makers at hospitals to detect abnormal LOS by identifying effective and efficient ways to minimise it, thereby reducing costs.