Intelligent Grouping Methods for Modelling Patient Flow
Grouping patient spells according to their length of stay (LOS) in a computational efficient manner, although believed to be beneficial, is still a problem that has not been fully researched. The aim of this paper is to describe the development of a patient classification methodology, which is statistically robust and clinically meaningful. Health care professionals can use the methodology as a prediction tool to identify groups of patients exhibiting similar resource consumption levels as approximated by patient LOS. Essentially, the methodology comprises of several processing steps orientated around fitting Gaussian mixture models to LOS observations and incorporating a decision tree classifier as a LOS prediction tool. We use the expectation maximisation algorithm for parameter estimation and derive appropriate models using the minimum description length criterion to guide the process of model selection. The classification techniques incorporated into the methodology are able to extract a model that provides a simplified representation of the underlying patient population. Moreover, the Gaussian mixture model provides a new and innovative way to model patient LOS. The methodology may help health care professionals to better understand and describe the case mix of patients cared for by the health facility.
health services length of stay patient grouping Gaussian mixture model expectation maximisation minimum description length
Revlin ABBI Elia EL-DARZI Christos VASILAKIS Peter MILLARD
Harrow School of Computer Science,University of Westminster,London,UK
国际会议
北京
英文
2007-05-30（万方平台首次上网日期，不代表论文的发表时间）