Length of stay as a performance indicator: robust statistical methodology

Abstract

Length of stay (LOS) is an important performance indicator for costing and hospital management and a key measure of efficiency of NHS. However, LOS is difficult to analyse because its statistical distribution is non-normal and LOS data habitually have many outliers. Furthermore, the usefulness of LOS for improving NHS performance is undermined because no adjustments are made for some key factors. This paper addresses both these problems. Health episodes statistics data from the UK NHS for 1997/98, and 1998/99 are analysed to investigate the effects of five key variables: admission method, discharge destination, provider (hospital) type, speciality and NHS region. All are found to influence LOS. The effects of some factors are substantial, and were not previously known, and so are not included in planned future NHS performance measures, e.g. LOS is at least 25% longer for patients transferred from other hospitals rather than admitted as an emergency; and LOS for patients discharged to private institutions is more than twice that for patients discharged to NHS institutions or their own home. The problem of finding the most appropriate statistical analysis for data of the LOS type is addressed by comparing standard general linear model methods with an advanced robust method called truncated maximum likelihood (TML). The TML methods are shown to have several advantages over standard methods, in terms of model fit and accuracy of parameter estimation. Implications of these findings for future use of LOS are considered.

On the performance ofL2Eestimation in modelling heterogeneous count responses with extreme values

“…Usually, any delay in admission makes patients deteriorate in health, which requires them to be transported directly to the emergency care. This also explains why the admission type is significant in our second component [7,21]. Furthermore, our L 2 E fit shows that unmarried women may marginally sustain longer stay among the small subpopulation of long-stayers, but rural patients Downloaded by [North Dakota State University] at 10:44 13 October 2014 and those with private insurance coverage may marginally sustain longer stay among the main subpopulation of normal-stayers.…”

“…Despite attempts to manage the LOS for frequently performed medical procedures, many service providers cannot achieve the target range allowed by the managed care system. Consequently, as an important component in the consumption of hospital resources, LOS in hospital has drawn considerable attention in the healthcare literature; see, for instance, [6][7][8]17]. The LOS also provides important information for health planning and formation of payment policy [18][19][20]; hence, it is a key performance indicator for hospital management and a key measure of hospital efficiency.…”

“…For example, the count data on number of office-based physician visits [4] and the LOS data [6][7][8] contain a fraction of extreme values. These extreme values cannot be immediately judged as outliers because one plausibly can have a large number of doctor visits in a year, for example, if one is on dialysis.…”

LOSH Prediction using Data Mining

“…K. Kulinskaya and H. D. Gao [5] used the health statistical data from UK NHS for 1997/98 and 1998/99 for analyzing five variable i.e. admission method, discharge destination, provider type, specialty and NHS region; these can directly affect the prediction of the LOS of the patient.…”

Patients Flow: A Mixed-Effects Modelling Approach to Predicting Discharge Probabilities

“…Average length of stay (LOS) has been shown to be a good proxy for hospital resource consumption and disease severity [1]. In the literature, LOS in health and social care systems has been described using patient flow models.…”