A model for predicting the trend deaths of COVID-19

Saeedi Aghdam, Mehran; Komiak, Sherrie X.Y.; Bahiraie, Alireza; Eshaghi, Majid; Sadeghi, Ahmad

doi:10.22075/ijnaa.2024.21537.2268

A model for predicting the trend deaths of COVID-19

Articles in Press

Document Type : Research Paper

Authors

Mehran Saeedi Aghdam ¹

Sherrie X.Y. Komiak ²

Alireza Bahiraie ³

Majid Eshaghi ³

Ahmad Sadeghi ⁴

¹ Department of Entrepreneurship, Qazvin Branch, Islamic Azad University, Qazvin, Iran

² Faculty of Business Administration, Memorial University of Newfoundland, St. John’s, NL, Canada

³ Department of Mathematics, Semnan University, Semnan, Iran

⁴ Department of Geography, Faculty of Earth Sciences, Shahid Beheshti University, Tehran, Iran

10.22075/ijnaa.2024.21537.2268

Abstract

The novel coronavirus pneumonia (COVID-19) originated in Wuhan and rapidly disseminated across China and subsequently the globe. This study aims to predict the trend of COVID-19-related deaths by optimizing the parameters of deep learning algorithms, particularly focusing on integrating big data. The performance of long-short-term memory (LSTM) learning models was rigorously compared with the auto-regressive integrated moving average (ARIMA) model to forecast future trends in COVID-19 fatalities. Through extensive data analysis and model optimization, the results indicate that the experimental results highlight the performance differences between the ARIMA and LSTM models in predicting COVID-19 outcomes. Specifically, the ARIMA model demonstrates superior performance with an accuracy of 87 percent, compared to the LSTM model's 79 percent accuracy. However, this does not mean ARIMA is unequivocally better than LSTM across all metrics. The findings suggest that the implementation of these predictive models can significantly improve the timeliness of reporting in existing surveillance systems, thereby enhancing public health responses and reducing societal costs associated with the pandemic. The study highlights the potential of using advanced predictive modelling to support healthcare planning and intervention strategies during global health crises.

Keywords

Prediction

LSTM

ARIMA

COVID-19

[1] I. Alon, M. Farrell, and S. Li, Regime type and COVID-19 response, FIIB Bus. Rev. 9 (2020), no. 3, 152–160.

[2] V.H. Buch, I. Ahmed, and M. Maruthappu, Artificial intelligence in medicine: Current trends and future possibilities, Br. J. Gen. Pract 68 (2018), 143–144.

[3] R. Cortez and W. Johnston, The coronavirus crisis in B2B settings: Crisis uniqueness and managerial implications based on social exchange theory, Ind. Market. Manag. 88 (2020), 125–135.

[4] K.R. French, G. William Schwert, and R.F. Stambaugh, Expected stock returns and volatility, J. Financ. Econ. 19 (1987), no. 1, 3–29.

[5] F. Gers, N. Schraudolph, and J. Schmidhuber, Learning precise timing with lstm recurrent networks, J. Machine Learn. Res. 3 (2000), 115–143.

[6] R.J. Hyndman and G. Athanasopoulos, 8.9 Seasonal ARIMA models, oTexts 19 (2015).

[7] L. Jia, K. Li, Y. Jiang, X. Guo, and T. Zhao, Prediction and analysis of coronavirus disease 2019, PloS one 15 (2020), no. 10, e0239960.

[8] D. Kahneman and A. Tversky, Prospect theory: An analysis of decision under risk, Econometrica 47 (1979), 263–291.

[9] M. Koohi-Moghadam, H. Wang, Y. Wang, X. Yang, H. Li, J. Wen Wang, and H. Sun, Predicting disease-associated mutation of metal-binding sites in proteins using a deep learning approach, Nature Machine Intell. 1 (2019), no. 12, 561–567.

[10] X. Li and X. Wu, Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition, IEEE Int. Conf. Acoustics Speech Signal Process., IEEE, 2015, pp. 4520–4524.

[11] H. Sak, A. Senior, and F. Beaufays, Long short-term memory recurrent neural network architectures for large scale acoustic modeling, arXiv preprint arXiv:1402.1128 (2014).

[12] J. Schmidhuber, F. Gers, and D. Eck, Learning nonregular languages: A comparison of simple recurrent networks and lstm, Neural Comput. 14 (2002), no. 9, 2039–2041.

[13] T. Singhal, A review of coronavirus disease-2019 (COVID-19), Ind. J. Pediat. 87 (2020), no. 43, 281–286.

[14] S. Swain, S. Nandi, and P. Patel Development of an ARIMA model for monthly rainfall forecasting over Khordha district, Odisha, India, Recent Findings in Intelligent Computing Techniques, Springer, Singapore, 2018, pp. 325–331.

[15] A. Tversky and D. Kahneman, Rational choice and the framing of decisions, J. Bus. 59 (1986), 251–278.

[16] Q. Wu, A. Boueiz, A. Bozkurt, A. Masoomi, A. Wang, D.L. DeMeo, S.T. Weiss, and W. Qiu, Deep learning methods for predicting disease status using genomic data, J. Biomet. Biostatist. 9 (2018), no. 5.