Metaheuristic Approaches Integrated with ANN in Forecasting Daily Emergency Department Visits

Abstract

The overall service quality level of Emergency Departments (EDs) can be improved by accurate forecasting of patient visits. Accordingly, this study aims to evaluate the use of three metaheuristic approaches integrated with Artificial Neural Network (ANN) in forecasting daily ED visits. To do this, five performance measures are used for evaluating the accuracy of the proposed approaches, including Bayesian ANN, Genetic Algorithm-based ANN (GA-ANN), and Particle Swarm Optimization algorithm-based ANN (PSO-ANN). The outputs of this study show that the PSO-ANN model provides the most dominant performance in both the training and testing process. The lowest error is obtained with a mean absolute percentage error (MAPE) of 6.3%, Mean Absolute Error (MAE) of 42.797, Mean Squared Error (MSE) of 2499.340, Root Mean Square Error (RMSE) of 49.933, and R-squared (R2) of 0.824 on the training dataset. The lowest error with an MAPE of 6.0%, MAE of 40.888, MSE of 2839.998, RMSE of 53.292, and R2 of 0.791 is also obtained on the testing process.

Enhancing emergency department patient arrival forecasting: a study using feature engineering and advanced machine learning algorithms

“…Studies on ML for predicting patient arrivals typically rely solely on meteorological variables and traditional calendar variables, such as day of the week and month of the year [5], [7], [19], [21], [22], [36]- [38], [48]. The performance of the prediction algorithms was positively impacted by the inclusion of FE variables, especially index.num, yday, week, and qday.…”

“…Our work is the first to compare ML algorithms for predicting patient arrivals using data from 11 EDs across 3 countries. Most studies using ML algorithms have focused on predicting arrivals in a single ED [7], [16], [22], [36]- [38], raising concerns on the statistical significance and generalizability of their findings. An exception is the work of Boyle et al [23], which analyzed data from 27 EDs but did not investigate the use of ML algorithms.…”

“…Pekel et al[36] compared three hybrid ML algorithms in forecasting daily arrivals, using variables such as month of the year, day of the week, holidays, and maximum temperature. The PSO-ANN model achieved the best performance, with MAPE values of 6% and RMSE of 53.29.…”

Short-Term Power Load Forecasting Model Design Based on EMD-PSO-GRU

“…To evaluate the performance of the prediction model, MAPE and RMSE are used as evaluation indicators [24][25][26][27][28][29][30][31][32][33], which are defined as follows:…”