An investigation on the estimation of the impact factors of pandemic deaths with artificial neural network and multiple regression algorithms: Covid-19 case

Abstract

This article aims to successfully estimate the number of deaths in a pandemic, with the appro-priate implementation of two new modelling approaches, artificial neural network and mul-tiple regression analysis. Then, these methods have been used comparatively to predict death cases for the future course of the COVID-19 outbreak. These approaches proposed for estima-tion appear to result in few errors and perform well in providing information on the course of deaths in the epidemic. The agreement between the predicted results by these methods, and the actual data proves the superiority of the proposed ones in forecasting accuracy in future cases. This is expected to provide significant benefits in increasing the effectiveness of health policies to be implemented within the scope of the measures to be taken for the future of this and similar epidemics. As this investigation reveals that the current modelling methods have undeniable advantages in predicting epidemic trends, using our models is believed to provide an accurate estimate of death rates and guide policymakers in formulating research, health, socio-economic and fiscal policies. All these findings can be widely regarded as significant milestones and essential guides for researchers examining potential future epidemic tenden-cies. In addition, although this epidemic is quite complex and varies from country-to-country and various factors, the proposed approaches offer a great opportunity to model the outbreak in other epidemics as well as in other countries.

Keywords

• Artificial Intelligence Modelling
• COVID-19
• Epidemic Disease
• Forecasting Model
• Regression Model

References

1. REFERENCES
2. [1] World Health Organization. Coronavirus disease (COVID-2019) situation reports. Available at: https://www.who.int/emergencies/diseases/novel-coronavirus-2019/situation-reports. Accessed on May 7, 2024.
3. [2] Wu JT, Leung K, Leung GM. Nowcasting and forecasting the potential domestic and international spread of the 2019-nCoV outbreak originating in Wuhan, China: A modelling study. Lancet 2020;395:689697. [CrossRef]
4. [3] Giordano G, Blanchini F, Bruno R, Colaneri P, Di Filippo A, Di Matteo A, et al. Modelling the COVID-19 epidemic and implementation of population-wide interventions in Italy. Nat Med 2020;26(6):855860.
5. [4] Maier BF, Brockmann D. Effective containment explains subexponential growth in recent confirmed COVID-19 cases in China. Science 2020;368:742746. [CrossRef]
6. [5] Anastassopoulou C, Russo L, Tsakris A, Siettos C. Data-based analysis, modelling and forecasting of the COVID-19 outbreak. PLoS One 2020;15:e0230405. [CrossRef]
7. [6] Turkyilmazoglu M. Explicit formulae for the peak time of an epidemic from the SIR model. Physica D 2021;422:132902. [CrossRef]
8. [7] Turkyilmazoglu M. An extended epidemic model with vaccination: Weak-immune SIRVI. Physica A 2022;598:127429.

9. [8] Turkyilmazoglu M. A restricted epidemic SIR model with elementary solutions. Phsysica A 2022;600:127570. [CrossRef]
10. [9] Tunc H, Sari M, Kotil SE. Effect of sojourn time distributions on the early dynamics of COVID-19 outbreak. Nonlinear Dyn 2023;111:1168511702. [CrossRef]
11. [10] Saba AI, Elsheikh AH. Forecasting the prevalence of COVID-19 outbreak in Egypt using nonlinear autoregressive artificial neural networks. Process Saf Environ Prot 2020;141:18. [CrossRef]
12. [11] Ardabili SF, Mosavi A, Ghamisi P, Ferdinand F, Varkonyi-Koczy AR, Reuter U, et al. COVID-19 outbreak prediction with machine learning. Available at: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3580188. Accessed on May 7, 2024.
13. [12] Benvenuto D, Giovanetti M, Vassallo L, Angeletti S, Ciccozzi M. Application of the ARIMA model on the COVID-2019 epidemic dataset. Data Brief 2020;29:105340. [CrossRef]
14. [13] Al-Qaness MAA, Ewees AA, Fan H, Abd El Aziz M. Optimization method for forecasting confirmed cases of COVID-19 in China. J Clin Med 2020;9:674. [CrossRef]
15. [14] Ozturk T, Talo M, Yildirim EA, Baloglu UB, Yildirim O, Rajendra Acharya U. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Comput Biol Med 2020;121:103792. [CrossRef]
16. [15] Ceylan Z. Estimation of COVID-19 prevalence in Italy, Spain, and France. Sci Total Environ 2020;729:138817. [CrossRef]
17. [16] Bapir SY, Kareem SM. COVID-19 and functionality: By providing social distancing of indoor common spaces in residental building. J Stud Sci Eng 2021;1:3645. [CrossRef]
18. [17] Xue H, Bai Y, Hu H, Liang H. Influenza activity surveillance based on multiple regression model and artificial neural network. IEEE Access 2017;6:563575. [CrossRef]
19. [18] Liu X, Jiang B, Gu W, Liu Q. Temporal trend and climate factors of hemorrhagic fever with renal syndrome epidemic in Shenyang City, China. BMC Infect Dis 2011;11:331. [CrossRef]
20. [19] Balkhy HH, Abolfotouh MA, Al-Hathlool RH, Al-Jumah MA. Awareness, attitudes, and practices related to the swine influenza pandemic among the Saudi public. BMC Infect Dis 2010;10:42. [CrossRef]
21. [20] Ahmad S, Mehfuz S, Mebarek-Oudina F, Beg J. RSM analysis based cloud access security broker: A systematic literature review. Cluster Comput 2022;25:37333763. [CrossRef]
22. [21] Guan P, Huang DS, Zhou BS. Forecasting model for the incidence of hepatitis A based on artificial neural network. World J Gastroenterol 2004;10:35793582. [CrossRef]
23. [22] Faisal T, Taib MN, Ibrahim F. Neural network diagnostic system for dengue patients risk classification. J Med Syst 2012;36:661–676. [CrossRef]
24. [23] Elveren E, Yumuşak N. Tuberculosis disease diagnosis using artificial neural network trained with genetic algorithm. J Med Syst 2011;35:329332. [CrossRef]
25. [24] Baridam B, Irozuru C. The prediction of prevalence and spread of HIV/AIDS using artificial neural network–the case of rivers State in the Niger Delta, Nigeria. Int J Comput Appl 2012;44:42–45. [CrossRef]
26. [25] Aburas HM, Cetiner BG, Sari M. Dengue confirmed-cases prediction: A neural network model. Expert Syst Appl 2010;37:42564260. [CrossRef]
27. [26] Koliopoulos TK, Papakonstantinou D, Ciarkowska K, Antonkiewicz J, Gambus F, Mebarek-Oudina F, et al. Green Designs in Hydraulics - Construction Infrastructures for Safe Agricultural Tourism and Sustainable Sports Tourism Facilities Mitigating Risks of Tourism in Crisis at Post COVID-19 Era. In: de Carvalho JV, Liberato P, Peña A, editors. Advances in Tourism, Technology and Systems. Smart Innovation, Systems and Technologies. 2nd ed. New York: Springer; 2022. p. 3747. [CrossRef]
28. [27] Chaurasia V, Pal S. COVID-19 pandemic: ARIMA and regression model-based worldwide death cases predictions. SN Comput Sci 2020;1:288. [CrossRef]
29. [28] Amar LA, Taha AA, Mohamed MY. Prediction of the final size for COVID-19 epidemic using machine learning: A case study of Egypt. Infect Dis Model 2020;5:622634. [CrossRef]
30. [29] Niazkar HR, Niazkar M. Application of artificial neural networks to predict the COVID-19 outbreak. Glob Health Res Policy 2020;5:50. [CrossRef]
31. [30] Melin P, Monica JC, Sanchez D, Castillo O. Multiple ensemble neural network models with fuzzy response aggregation for predicting COVID-19 time series: The case of mexico. Healthcare (Basel) 2020;8:181. [CrossRef]
32. [31] Tamang SK, Singh PD, Datta B. Forecasting of Covid-19 cases based on prediction using artificial neural network curve fitting technique. Glob J Environ Sci Manag 2020;6:5364.
33. [32] Moftakhar L, Seif M, Safe MS. Exponentially increasing trend of infected patients with COVID-19 in Iran: A comparison of neural network and arima forecasting models. Iran J Public Health 2020;49:92100. [CrossRef]
34. [33] Nakip M, Copur O, Guzelis C. Comparative study of forecasting models for COVID-19 outbreak in Turkey. Available at: https://www.iitis.pl/sites/default/files/pubs/Covid_19_Forecasting%20%281%29.pdf. Accessed on May 7, 2024.
35. [34] Toğa G, Atalay B, Toksari MD. COVID-19 prevalence forecasting using Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN): Case of Turkey. J Infect Public Health 2021;14:811816. [CrossRef]
36. [35] Guleryuz D. Forecasting outbreak of COVID-19 in Turkey; Comparison of Box-Jenkins, Brown's exponential smoothing and long short-term memory models. Process Saf Environ Prot 2021;149:927935. [CrossRef]
37. [36] Demir E, Canitez MN, Elazab M, Hameed AA, Jamil A, Al-Dulaimi AA. Assessing the spreading behavior of the Covid-19 epidemic: A case study of Turkey. Available at: https://acikerisim.istinye.edu.tr/xmlui/handle/20.500.12713/3242. Accessed on May 7, 2024.
38. [37] Kuvvetli Y, Deveci M, Paksoy, T, Garg H. A predictive analytics model for COVID-19 pandemic using artificial neural networks. Decis Anal J 2021;1:100007. [CrossRef]
39. [38] Caglar O, Ozen F. A comparison of Covid-19 cases and deaths in Turkey and in other countries. Netw Model Anal Health Inform Bioinform 2022;11:45. [CrossRef]
40. [39] Kırbaş İ, Sözen A, Tuncer AD, Kazancıoğlu FŞ. Comparative analysis and forecasting of COVID-19 cases in various European countries with ARIMA, NARNN and LSTM approaches. Chaos Solitons Fractals 2020;138:110015. [CrossRef]
41. [40] Weisberg S. Applied Linear Regression. 3th ed. New Jersey: John Wiley & Sons, Inc; 2005. [CrossRef]
42. [41] Fox J. Applied Regression Analysis: Linear Models and Related Methods. California: SagePublication; 1997.
43. [42] Skapura DM. Building Neural Networks. 1st ed. Boston: Addison-Wesley; 1995.
44. [43] Haykin S. Neural Networks: A Comprehensive Foundation. New York: Macmillian College Publishing Company Inc; 1994.
45. [44] Chaudhuri BB, Bhattacharya U. Efficient training and improved performance of multilayer perceptron in pattern classification. Neurocomput 2000;34:1127. [CrossRef]
46. [45] PRT-DTO, 2020. Presidency of The Republic of Turkey Digital Transformation Office. Available at: https://cbddo.gov.tr/ Accessed on May 7, 2024.
47. [46] T.C Sağlık Bakanlığı – Covid-19 Bilgilendirme Platformu. Günlük Covid-19 aşı tablosu. Available at: https://covid19.saglik.gov.tr/. Accessed on May 7, 2024.
48. [47] Zhang G, Patuwo BE, Hu MY. Forecasting with artificial neural networks: The state of the art. Int J Forecast 1998;14:3562. [CrossRef]
49. [48] Spangler WE, May JH, Vargas LG. Choosing datamining for multiple classification: Representational and performance measurement implications for decision support. J Manag Inf Syst 1999;16:3762. [CrossRef]
50. [49] Uysal M, Roubi SE. Artificial neural networks versus multiple regression in tourism demand analysis. J Travel Res 1999;38:111118. [CrossRef]
51. [50] Fadlalla A, Lin CH. An analysis of the applications of neural networks in finance. Interfaces 2001;31:112122. [CrossRef]
52. [51] Nguyen N, Cripps A. Predicting housing value: a comparison of multiple regression analysis and artificial neural networks. J Real Estate Res 2001;22:313336. [CrossRef]
53. [52] Gorr WL. Research prospective on neural network forecasting. Int J Forecast 1994;10:14. [CrossRef]
54. [53] Hill T, Remus W. Neural network approach for intelligent support of managerial decision making. Decis Support Syst 1994;11:449459. [CrossRef]
55. [54] Wray B, Palmer A, Bejou D. Using neural network analysis to evaluate buyer-seller relationship. Eur J Market 1994;28:3248. [CrossRef]