Prediction of Patients Severity at Emergency Department Using NARX and Ensemble Learning

Early detection of adverse events at hospitals could be useful in terms of reducing costs, morbidity, and mortality. Therefore, in this paper, we present a personalized real-time hybrid model based on Nonlinear Autoregressive Exogenous (NARX) model and Ensemble Learning (EL) to predict patients' severity during hospitalization at Emergency Departments (ED). This model utilizes vital signs of patients, including Pulse Rate (PR), Respiratory Rate (RR), Arterial Blood Oxygen Saturation (SpO2) and Systolic Blood Pressure (SBP), which are collected automatically during the treatment to predict the illness severity of hospitalized patients at ED in the next hour based on their vital signs of the previous two hours. Two EL algorithms, including Random Forest (RF) and Adaptive Boosting (AdaBoost) are considered to build hybrid models. The performance of NARX-EL models is compared with Auto Regressive Integrated Moving Average (ARIMA), combination of NARX and Linear Regression (LR), Support Vector Regression (SVR) and K-Nearest Neighbors Regression (KNN). The results show that our proposed hybrid models can predict patients' severity with significantly higher accuracy. It is also found that NARX-RF has the best performance in the prediction of sudden changes and unexpected adverse events in patients' vital signs (R
²
score =0.978, NRMSE =6.16%).