Predictability of COVID-19 Infections Based on Deep Learning and Historical Data
Source abstract
Abstract
The COVID-19 disease has spread worldwide since 2020, causing a high number of deaths as well as infections, and impacting economic, social and health systems. Understanding its dynamics may facilitate a better understanding of its behavior, reducing the impact of similar diseases in the future. Classical modeling techniques have failed in predicting the behavior of this disease, since they have been unable to capture hidden features in the data collected about the disease. The present research benefits from the high capacity of modern computers and new trends in artificial intelligence (AI), specifically three deep learning (DL) neural networks: recurrent neural network (RNN), gated recurrent unit (GRU), and long short-term memory (LSTM). We thus modelled daily new infections of COVID-19 in four countries (Saudi Arabia, Egypt, Italy, and India) that vary in their climates, cultures, populations, and health systems. The results show that a simple-structure RNN algorithm is better at predicting daily new infections and that DL techniques have promising potential in disease modeling and can be used efficiently even in the case of limited datasets.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: COVID-19 diagnosis using AI · COVID-19 epidemiological studies · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Public Health, College of Public Health and Health Informatics, University of Ha’il, Ha’il 55476, Saudi Arabia
Department of Computer & Network Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah 21959, Saudi Arabia
Department of Health Informatics, College of Public Health and Health Informatics, University of Ha’il, Ha’il 55476, Saudi Arabia
Department of Health Management, College of Public Health and Health Informatics, University of Ha’il, Ha’il 55476, Saudi Arabia
Computational Biology and Systems Biomedicine, Biodonostia Health Research Institute, C/Doctor Beguiristain s/n, 20014 San Sebastián, Spain
IKERBASQUE, Basque Foundation for Science, C/María Díaz Harokoa 3, 48013 Bilbao, Spain
Department of Cell Biology and Histology, Faculty of Medicine and Nursing, University of Basque Country (UPV/EHU), 48940 Leioa, Spain
Funding
Scientific Research Deanship at University of Ha’il—Saudi Arabia
References (36)
Show source-provided references
1. A pneumonia outbreak associated with a new coronavirus of probable bat origin10.1038/s41586-020-2012-7 ↗
2. Coronaviridae Study Group of the International Committee on Taxonomy of Viruses. The species Severe acute respiratory syndrome-related coronavirus: Classifying 2019-nCoV and naming it SARS-CoV-210.1038/s41564-020-0695-z ↗
3. Nikolaidis, M., Papakyriakou, A., Chlichlia, K., Markoulatos, P., Oliver, S.G., and Amoutzias, G.D. (2022). Comparative Analysis of SARS-CoV-2 Variants of Concern, Including Omicron, Highlights Their Common and Distinctive Amino Acid Substitution Patterns, Especially at the Spike ORF. Viruses, 14.10.3390/v14040707 ↗
4. The Neighborhood of the Spike Gene Is a Hotspot for Modular Intertypic Homologous and Nonhomologous Recombination in Coronavirus Genomes10.1093/molbev/msab292 ↗
5. Broadly neutralizing antibodies overcome SARS-CoV-2 Omicron antigenic shift10.1038/s41586-021-04386-2 ↗
6. Amoutzias, G.D., Nikolaidis, M., Tryfonopoulou, E., Chlichlia, K., Markoulatos, P., and Oliver, S.G. (2022). The Remarkable Evolutionary Plasticity of Coronaviruses by Mutation and Recombination: Insights for the COVID-19 Pandemic and the Future Evolutionary Paths of SARS-CoV-2. Viruses, 14.10.3390/v14010078 ↗
7. Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM10.1016/j.chaos.2020.110212 ↗
8. A deep learning algorithm for modeling and forecasting of COVID-19 in five worst affected states of India10.1016/j.aej.2020.09.037 ↗
9. Nathan, C. (2022, March 20). A Deep Learning Model for Predicting COVID-19 Transmission in Connecticut 2021. Honors Scholar Theses. 782. Available online: https://opencommons.uconn.edu/srhonors_theses/782.
10. Nonpharmaceutical Stochastic Optimal Control Strategies to Mitigate the COVID-19 Spread10.1109/TASE.2021.3111338 ↗
11. Model predictive control to mitigate the COVID-19 outbreak in a multi-region scenario10.1016/j.arcontrol.2020.09.005 ↗
12. Analysis and Modeling of COVID-19 Epidemic Dynamics in Saudi Arabia Using SIR-PSO and Machine Learning Approaches10.3855/jidc.15004 ↗
13. Scarabaggio, P., Carli, R., Cavone, G., Epicoco, N., and Dotoli, M. (2021, January 23–27). Modeling, Estimation, and Optimal Control of Anti-COVID-19 Multi-dose Vaccine Administration. Proceedings of the 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France.10.1109/CASE49439.2021.9551418 ↗
14. Inefficiency of SIR models in forecasting COVID-19 epidemic: A case study of Isfahan10.1038/s41598-021-84055-6 ↗
15. A SIR model assumption for the spread of COVID-19 in different communities10.1016/j.chaos.2020.110057 ↗
16. Forecasting the spread of the COVID-19 pandemic in Saudi Arabia using ARIMA prediction model under current public health interventions10.1016/j.jiph.2020.06.001 ↗
17. On the accuracy of ARIMA based prediction of COVID-19 spread10.1016/j.rinp.2021.104509 ↗
18. Generalized Richards model for predicting COVID-19 dynamics in Saudi Arabia based on particle swarm optimization Algorithm10.3934/publichealth.2020064 ↗
19. A novel approach based on combining deep learning models with statistical methods for COVID-19 time series forecasting10.1007/s00521-021-06548-9 ↗
20. CoBiD-net: A tailored deep learning ensemble model for time series forecasting of covid-1910.1007/s41324-021-00408-3 ↗
21. Convolutional neural networks and temporal CNNs for COVID-19 forecasting in France10.1007/s10489-021-02359-6 ↗
22. Deep learning methods for forecasting COVID-19 time-Series data: A Comparative study10.1016/j.chaos.2020.110121 ↗
23. Deep learning model for forecasting COVID-19 outbreak in Egypt10.1016/j.psep.2021.07.034 ↗
24. Deep learning-based forecasting model for COVID-19 outbreak in Saudi Arabia10.1016/j.psep.2020.10.048 ↗
25. Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks10.1016/j.rinp.2021.104137 ↗
26. Forecasting of COVID-19 cases using deep learning models: Is it reliable and practically significant?10.1016/j.rinp.2021.103817 ↗
27. Recurrent Neural Network and Reinforcement Learning Model for COVID-19 Prediction10.3389/fpubh.2021.744100 ↗
28. SIRVD-DL: A COVID-19 deep learning prediction model based on time-dependent SIRVD10.1016/j.compbiomed.2021.104868 ↗
29. Time series forecasting of COVID-19 transmission in Asia Pacific countries using deep neural networks
30. Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods10.1016/j.rinp.2021.104495 ↗
31. Time series predicting of COVID-19 based on deep learning10.1016/j.neucom.2021.10.035 ↗
32. Tanaka, H., Ogata, T., Shibata, T., Nagai, H., Takahashi, Y., Kinoshita, M., Matsubayashi, K., Hattori, S., and Taniguchi, C. (2022). Shorter Incubation Period among COVID-19 Cases with the BA.1 Omicron Variant. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph19106330 ↗
33. Wastewater monitoring as a supplementary surveillance tool for capturing SARS-COV-2 community spread. A case study in two Greek municipalities10.1016/j.envres.2021.111749 ↗
34. Ahmad, H.F., Khaloofi, H., Azhar, Z., Algosaibi, A., and Hussain, J. (2021). An Improved COVID-19 Forecasting by Infectious Disease Modelling Using Machine Learning. Appl. Sci., 11.10.3390/app112311426 ↗
35. Shahin, A.I., and Almotairi, S. (2021). A Deep Learning BiLSTM Encoding-Decoding Model for COVID-19 Pandemic Spread Forecasting. Fractal Fract., 5.10.3390/fractalfract5040175 ↗
36. An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number Rt in Italy10.3390/ai3010009 ↗