Predicting Patient Length of Stay in Australian Emergency Departments Using Data Mining

Abstract

Length of Stay (LOS) is an important performance metric in Australian Emergency Departments (EDs). Recent evidence suggests that an LOS in excess of 4 h may be associated with increased mortality, but despite this, the average LOS continues to remain greater than 4 h in many EDs. Previous studies have found that Data Mining (DM) can be used to help hospitals to manage this metric and there is continued research into identifying factors that cause delays in ED LOS. Despite this, there is still a lack of specific research into how DM could use these factors to manage ED LOS. This study adds to the emerging literature and offers evidence that it is possible to predict delays in ED LOS to offer Clinical Decision Support (CDS) by using DM. Sixteen potentially relevant factors that impact ED LOS were identified through a literature survey and subsequently used as predictors to create six Data Mining Models (DMMs). An extract based on the Victorian Emergency Minimum Dataset (VEMD) was used to obtain relevant patient details and the DMMs were implemented using the Weka Software. The DMMs implemented in this study were successful in identifying the factors that were most likely to cause ED LOS > 4 h and also identify their correlation. These DMMs can be used by hospitals, not only to identify risk factors in their EDs that could lead to ED LOS > 4 h, but also to monitor these factors over time.

Factors Relating to Decision Delay in the Emergency Department: Effects of Diagnostic Tests and Consultations

“…Besides the patients requiring other requests, the ones for which consultation was requested had the lowest WT and the highest LOS on average compared to the ones for which laboratory-type or imaging-type tests were ordered ( Table 2 ). Since ordering diagnostic tests or consultation can be related to clinical acuity or complexity of ED patients, 19 , 21 , 32 , 33 these results showed that although patients with higher acuity or complexity levels wait significantly lower in EDs, they stay longer in the system. Additional requests such as diagnostic tests and consultation may cause delays in making decisions on these patients.…”

Factors Associated with Extended Length of Stay for Paediatric Mental Health Presentations to Emergency Departments in South Western Sydney, Australia

“…Several factors, including sociodemographic, clinical, and hospital-related characteristics, are linked to extended LOS in ED. Previous studies in Australia have shown that factors such as patient age, mode of arrival, triage category, and reason for ED presentations were significantly associated with extended ED LOS [17,18]. However, these studies include all age groups including the elderly population, hence may have missed specific factors associated with extended LOS in ED among the paediatric population -a key focus of this study.…”

Advances in E-Health and Mobile Health Monitoring

“…The application of such techniques requires a combination of the technical expertise of computer scientists, as well as domain knowledge to prepare the data sets for analysis and the interpretation of the results. In the sixth article [6], Gurazada, with her colleagues, explored a common problem of a prolonged length of stay in an emergency department. The article presents a review of potential data-mining techniques that have been applied to predict what factors affect the length of stay of patients.…”