A Comparison of Multivariate SARIMA and SVM Models for Emergency Department Admission Prediction

A comparison of multivariate SARIMA model with a multivariate regression-based time series based on a Support Vector Machine model was performed for emergency department admissions prediction. The same input variables were used in both models. Both models were trained with consecutive daily samples of data corresponding to the January 2009 – August 2012 period (n=1339). Performance was evaluated on the September 2012 test dataset (n=30). The results obtained with the Support Vector Machine were found to be more accurate with a 46,53% RMSE improvement and a 48,89% MAE improvement on the train set. The experiment was repeated six times with varying time periods. The SVM approach produced better results in all cases. Error measurements on the test set were compared with a paired T test. The differences between all comparisons were found to be statistically significant in all cases with a 95% CI.

[1]  G. Hejblum,et al.  A systematic review of models for forecasting the number of emergency department visits , 2009, Emergency Medicine Journal.

[2]  Enric Monte,et al.  ON THE SELF-SIMILAR DISTRIBUTION OF THE EMERGENCY WARD ARRIVALS TIME SERIES , 2002 .

[3]  E. Seow,et al.  Forecasting daily attendances at an emergency department to aid resource planning , 2009, BMC emergency medicine.

[4]  Brian H Rowe,et al.  Air pollution and emergency department visits for cardiac and respiratory conditions: a multi-city time-series analysis , 2009, Environmental health : a global access science source.

[5]  S. McMillan,et al.  Predicting patient visits to an urgent care clinic using calendar variables. , 2001, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[6]  S. Sathiya Keerthi,et al.  Improvements to the SMO algorithm for SVM regression , 2000, IEEE Trans. Neural Networks Learn. Syst..

[7]  Gad Abraham,et al.  Short-Term Forecasting of Emergency Inpatient Flow , 2009, IEEE Transactions on Information Technology in Biomedicine.

[8]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[9]  S. Zeger,et al.  The challenge of predicting demand for emergency department services. , 2008, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[10]  R. Darlington,et al.  Regression and Linear Models , 1990 .

[11]  Jon Pearson,et al.  Forecasting Demand of Emergency Care , 2002, Health Care Management Science.

[12]  E. Ionides,et al.  Forecasting models of emergency department crowding. , 2009, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[13]  Richard Broome,et al.  Emergency department visits, ambulance calls, and mortality associated with an exceptional heat wave in Sydney, Australia, 2011: a time-series analysis , 2012, Environmental Health.