Hybrid neural network models for time series disease prediction confronted by spatiotemporal dependencies

In infectious disease outbreak modeling, there remains a gap in addressing spatiotemporal challenges present in established models. This study addresses this gap by evaluating four established hybrid neural network models for predicting influenza outbreaks. These models were analyzed by employing time series data from eight different countries to challenge the models with imposed spatial difficulties, in a month-on-month structure. The models' predictions were compared using MAPE, and RMSE, as well as graphical representations generated by employed models. The SARIMA-LSTM model excelled in achieving the lowest average RMSE score of 66.93 as well as reporting the lowest RMSE score for three out of eight countries studied. In this case also, GA-ConvLSTM-CNN model comes in second place with an average RMSE score of 68.46. Considering these results and the ability to follow the seasonal trends of the actual values, this study suggests the SARIMA-LSTM model to be more robust to spatiotemporal challenges compared with the other models under examination. This study•Evaluated established methods with unique imposed difficulty.•Addressed spatiotemporal characteristics of the data.•Proposed the SARIMA-LSTM model based on evaluation metrics.