Comparative study of machine learning methods for COVID-19 transmission forecasting

Novel informatics approaches to COVID-19 Research: From methods to applications

“…Methods for short-term forecasting are usually data-driven, but they can also incorporate domain knowledge in the form of compartmental modelling (i.e., SIR-type models – see [48] ), as a means of integrating and simultaneously forecasting in a coherent manner multiple epidemiological indicators, such as cases, hospitalizations, and deaths. The study by Swaraj et al [21] uses a statistical data-driven approach, Aljaaf et al [22] , Dairi et al [23] , and Safari et al [24] use a machine learning data-driven approach, while Jing et al [25] uses compartmental modelling. Most of the forecasting studies were conducted as stand-alone evaluations or comparisons of methods by researchers who were not directly affiliated with public health authorities mandated to perform surveillance.…”

“… Original Research [22] A fusion of data science and feed-forward neural network-based modelling of COVID-19 outbreak forecasting in IRAQ Aljaaf, A. J. Original Research [23] Comparative study of machine learning methods for COVID-19 transmission forecasting Dairi, A. Original Research [24] A novel deep interval type-2 fuzzy LSTM (DIT2FLSTM) model applied to COVID-19 pandemic time-series prediction Safari, A.…”

Multiple Output and Multi-Steps Prediction of COVID-19 Spread Using Weather and Vaccination Data

“…Ayoobi et al [12] have examined six different DL methods, including LSTM, convolutional LSTM, GRU, and bidirectional extension of each method to predict new cases and new deaths in Australia and Iran countries for one, three, and seven days ahead in the next 100 days. Dairi et al [13] have investigated the performance of DL methods, including hybrid convolutional neural networks-Long short-term memory (LSTM-CNN), hybrid gated recurrent unit-convolutional neural networks (GAN-GRU), GAN, CNN, LSTM, and Restricted Boltzmann Machine (RBM), as well as basic ML methods, namely logistic regression (LR) and SVR, to predict confirmed and recovered COVID-19 cases from seven affected countries: Brazil, France, India, Mexico, Russia, Saudi Arabia, and the United States. Nabi et al [14] have evaluated four DL models: LSTM, gated recurrent unit (GRU), CNN, and multivariate convolutional neural network (MCNN), to predict new COVID-19 cases in Brazil, Russia, and the United Kingdom in the long term.…”

Machine learning-based forecasting of firemen ambulances’ turnaround time in hospitals, considering the COVID-19 impact

“…On 12th January 2020, the World Health Organization (WHO) announced [12] a novel Coronavirus [13] , [14] , [15] , [16] , [17] , [18] , which was officially named as ‘COVID-19’ (coronavirus disease 2019) [19] on the 11th of February. Further, with the spread of COVID-19 across the world, it was declared as a pandemic [20] on 11th March 2020.…”

“…To the authors’ knowledge, there is no research trying to forecast the TT of ambulances in hospitals, as we present in this paper, but rather for the prediction of patients’ waiting time in ED [35] , [36] , [37] . On the other hand, within the context of COVID-19, multiple works have investigated machine-learning-based solutions to help to fight the outbreak, e.g., forecasting of ED volume [38] and forecasting the number of confirmed COVID-19 cases [39] , [40] , [41] , [42] ; we refer the readers to recent survey works on ML forecasting models and COVID-19 in [17] , [18] .…”