Abstract
Background: With new variants of COVID-19 causing challenges, we need to focus on integrating multiple deep-learning frameworks to develop intelligent healthcare systems for early detection and diagnosis.
Objective: This article suggests three hybrid deep learning models, namely CNN-LSTM, CNN-Bi- LSTM, and CNN-GRU, to address the pressing need for an intelligent healthcare system. These models are designed to capture spatial and temporal patterns in COVID-19 data, thereby improving the accuracy and timeliness of predictions. An output forecasting framework integrates these models, and an optimization algorithm automatically selects the hyperparameters for the 13 baselines and the three proposed hybrid models.
Methods: Real-time time series data from the five most affected countries were used to test the effectiveness of the proposed models. Baseline models were compared, and optimization algorithms were employed to improve forecasting capabilities.
Results: CNN-GRU and CNN-LSTM are the top short- and long-term forecasting models. CNNGRU had the best performance with the lowest SMAPE and MAPE values for long-term forecasting in India at 3.07% and 3.17%, respectively, and impressive results for short-term forecasting with SMAPE and MAPE values of 1.46% and 1.47%.
Conclusion: Hybrid deep learning models, like CNN-GRU, can aid in early COVID-19 assessment and diagnosis. They detect patterns in data for effective governmental strategies and forecasting. This helps manage and mitigate the pandemic faster and more accurately.
Keywords: Time series data, RNN, LSTM, long and short-term forecasting, hybrid model, baseline model, hyperparameter optimization algorithm.
[http://dx.doi.org/10.1016/S0140-6736(20)30559-6] [PMID: 32199074]
[http://dx.doi.org/10.1016/j.arcontrol.2021.04.006]
[http://dx.doi.org/10.1016/j.chaos.2020.110072] [PMID: 32834616]
[http://dx.doi.org/10.3934/mbe.2008.5.145] [PMID: 18193936]
[http://dx.doi.org/10.1016/j.patrec.2021.07.027] [PMID: 34413555]
[http://dx.doi.org/10.1007/978-3-030-79753-9]
[http://dx.doi.org/10.1016/j.chaos.2021.110885] [PMID: 33776250]
[http://dx.doi.org/10.1016/j.idm.2020.04.001]
[http://dx.doi.org/10.1186/s12889-020-08671-z] [PMID: 32331516]
[http://dx.doi.org/10.1098/rsif.2020.0494] [PMID: 32752997]
[http://dx.doi.org/10.1016/j.chaos.2020.110212] [PMID: 32839642]
[http://dx.doi.org/10.1016/j.neucom.2021.10.035] [PMID: 34690432]
[http://dx.doi.org/10.1371/journal.pone.0262708] [PMID: 35089976]
[http://dx.doi.org/10.1016/j.rinp.2021.104137] [PMID: 33898209]
[http://dx.doi.org/10.1016/j.ibmed.2020.100013] [PMID: 33169117]
[http://dx.doi.org/10.1016/j.bj.2020.05.001] [PMID: 32426387]
[http://dx.doi.org/10.1016/j.eswa.2020.113661] [PMID: 32834556]
[http://dx.doi.org/10.1109/ACCESS.2020.3010326]
[http://dx.doi.org/10.1016/j.chaos.2020.110121] [PMID: 32834633]
[http://dx.doi.org/10.1016/j.chaos.2020.109864] [PMID: 32390691]
[http://dx.doi.org/10.1016/j.chaos.2020.110511]
[http://dx.doi.org/10.1111/biom.13802]
[http://dx.doi.org/10.1201/9780367548445]
[http://dx.doi.org/10.1007/978-3-030-79753-9_14]
[http://dx.doi.org/10.1109/ACCESS.2020.3044929] [PMID: 34812374]
[http://dx.doi.org/10.1109/ACCESS.2021.3078080]
[http://dx.doi.org/10.1007/s11783-023-1688-y]
[http://dx.doi.org/10.1007/s11269-022-03414-8]
[http://dx.doi.org/10.3390/en16052283]
[http://dx.doi.org/10.1016/j.jbi.2021.103791] [PMID: 33915272]
[http://dx.doi.org/10.1155/2021/8785636]
[http://dx.doi.org/10.1109/5.726791]
[http://dx.doi.org/10.1162/neco_a_00990] [PMID: 28599112]
[http://dx.doi.org/10.1142/S1469026818500086]
[http://dx.doi.org/10.3389/fgene.2022.844391] [PMID: 35559018]
[http://dx.doi.org/10.1016/j.bbe.2022.06.003]
[http://dx.doi.org/10.1016/j.patter.2022.100567] [PMID: 36124301]