Retrospective identification of latent subgroups of emergency department patients: A machine learning approach.

OBJECTIVE: This research aims to (i) identify latent subgroups of ED presentations in Australian public EDs using a data-driven approach and (ii) compare clinical, socio-demographic and time-related characteristics of ED presentations broadly using the subgroups. METHODS: We examined presentations to four public hospital EDs in Queensland from 2009 to 2014. An unsupervised machine learning algorithm, Clustering Large Applications, was used to cluster ED presentations. RESULTS: There were six subgroups common across the EDs, primarily distinguishable by age, and subsequently by triage category, ED length of stay, arrival mode, departure status and several time-related attributes. Around 10% to 30% of the total presentations had high resource utilisation, with half of these from older patients (55+ years). ED resource utilisation per population was highest among the oldest cohort (75+ years). Children and young adults more frequently presented to the ED outside general-practitioner hours, mostly on Sundays. Older persons were more likely to present at any time, rather than specific hours, days or seasons. ED service performance measured against commonly used access-target indicators were rarely satisfied for older people and frequently satisfied for children. CONCLUSION: Clustering Large Applications is effective in finding latent groups in large-scale mixed-type data, as demonstrated in the present study. Six types of ED presentations were identified and described using clinically relevant characteristics. The present study provides evidence for policy makers in Australia to develop alternative ED models of care tailored around the care needs of the differing groups of patients and thereby supports the sustainable delivery of acute healthcare.

Identifying and quantifying general practice-type emergency department presentations.

OBJECTIVE: This research aims to (i) identify general practice-type (GP-type) presentations to EDs in South-East Queensland, Australia and (ii) compare and quantify the clinical, socio-demographic and time-varying characteristics between GP-type and non-GP-type presentations. METHODS: Data were collected from presentations to four EDs in Queensland from 2009 to 2014. A modified version of the Australasian College for Emergency Medicine (ACEM) method for identifying GP-type ED presentations was used. RESULTS: The four EDs have different proportions of GP-type presentations, between 7% and 33%. Between 2009 and 2014, the amount of GP-type presentations increased in three EDs, by between 5% and 16%, and decreased by 30% in the other ED. Different holidays, for example, the public holidays over the Christmas to New Year period, impact GP-type presentations. Over 50% of GP-type presentations occurred in those aged 0-34 years, and <1% were aged 85+ years. Injury-related diagnoses made up around 37% of the GP-type presentations, and around 13% did not wait for a diagnosis, averaged over the EDs. GP-type presentations are more likely to present to EDs outside standard general practitioner hours. CONCLUSIONS: Existing methods for identifying GP-type presentations have drawbacks, and modified methods are required to better identify these types of presentations. Temporal effects not previously investigated in Australian studies, such as holidays, are significantly associated with GP-type presentations. These findings aid strategic planning and interventions to support review of GP-type presentations, instead, in primary-care facilities, and such interventions may be assistive in some EDs more than others.

Forecasting daily counts of patient presentations in Australian emergency departments using statistical models with time-varying predictors.

OBJECTIVE: This research aimed to (i) assess the effects of time-varying predictors (day of the week, month, year, holiday, temperature) on daily ED presentations and (ii) compare the accuracy of five methods for forecasting ED presentations, including four statistical methods and a machine learning approach. METHODS: Predictors of ED presentations were assessed using generalised additive models (GAMs), generalised linear models, multiple linear regression models, seasonal autoregressive integrated moving average models and random forest. The accuracy of short-term (14 days), mid-term (30 days) and long-term (365 days) forecasts were compared using two measures of forecasting error. RESULTS: The data are the numbers of presentations to public hospital EDs in South-East Queensland, Australia, from 2009 to 2015. ED presentations are largely affected by year of presentation, and to a lesser extent by month, day of the week and holidays. Maximum daily temperature is also a significant predictor of ED presentations. Of the four statistical models considered, the GAM had the greatest forecasting accuracy, and produced consistent and coherent forecasts, likely due to its flexibility in modelling complex time-varying effects. The random forest machine learning approach had the lowest forecasting accuracy, likely due to overfitting the data. CONCLUSIONS: Calendar and temperature variables, not previously considered in the Australian literature, were found to significantly impact ED presentations. This study also demonstrates the potential of GAMs as a dual explanatory and forecasting method for the modelling, and more accurate prediction, of ED presentations.