Разработка методов прогнозирования динамики заболеваемости на примере COVID-19
Работая с нашим сайтом, вы даете свое согласие на использование файлов cookie. Это необходимо для нормального функционирования сайта, показа целевой рекламы и анализа трафика. Статистика использования сайта отправляется в «Яндекс» и «Google»
Научный журнал Моделирование, оптимизация и информационные технологииThe scientific journal Modeling, Optimization and Information Technology
Online media
issn 2310-6018

Development of methods for forecasting the dynamics of morbidity in the case of COVID-19

idKashirina I.L. Matykina O.V.  

UDC 004.8
DOI: 10.26102/2310-6018/2023.42.3.014

  • Abstract
  • List of references
  • About authors

The COVID-19 pandemic has had global repercussions and has led to severe restrictive measures in all areas of activity that have changed the working and living conditions of the world's population. Even after the end of the pandemic, predicting the incidence of COVID-19 remains an important task as it is necessary to monitor the development of the situation and the results of research on this issue can be extrapolated to other epidemics. Scientific studies on the analysis of factors that have a significant impact on the course of the epidemic have a particular importance. This study proposes a set of models and machine learning algorithms based on big data processing to predict the dynamics of the spread of the COVID-19 virus at the mesolevel, which analyzes the impact of various exogenous factors on the incidence. As the initial data for building machine learning models, we use a depersonalized data set provided by Voronezh Regional Clinical Consultative and Diagnostic Center and containing information on all tests for COVID-19 conducted in Voronezh Oblast. To effectively combat epidemics, it is necessary to forecast the development of the incidence dynamics for a sufficiently long period of time, e.g. from two weeks or more, while various studies, in general, propose short-term methods that allow making a fairly accurate forecast only for 1–5 days. Therefore, the goal of this study is to find the optimal method for predicting incidence over an average period of time using exogenous factors. Information about the weather, day of the week and month, and the popularity of search queries related to COVID-19 were selected as exogenous variables to improve the quality of forecasting.

1. Braga M.D.B., Fernandes R.D.S., de Souza G.N., et al. Artificial neural networks for short-term forecasting of cases, deaths, and hospital beds occupancy in the COVID-19 pandemic at the Brazilian Amazon. PLoS One. 2021;16(3):e0248161. DOI: 10.1371/journal.pone.0248161.

2. Naumov A., Moloshnikov I., Serenko A., Sboev A., Rybka R. Baseline accuracies of forecasting covid-19 cases in Russian regions on a year in retrospect using basic statistical and machine learning methods. Procedia Computer Science. 2021;193:276–284. DOI: 10.1016/j.procs.2021.10.028.

3. Kashirina I.L., Ershov D.O. Analiz, modelirovanie i prognozirovanie COVID-19 na osnove dannyh Voronezhskoj oblasti. Aktual'nye problemy prikladnoj matematiki, informatiki i mehaniki: Sbornik trudov Mezhdunarodnoj konferencii; 13–15 December 2021; Voronezh. Voronezh: Nauchno-issledovatel'skie publikatsii; 2022. p. 174–180. (In Russ.).

4. Kashirina I.L., Azarnova T.V., Bondarenko Yu.V. Analysis of the COVID-19 pandemic impact on the development of human capital in the region using machine learning algorithms. Modeling, Optimization and Information Technology. 2022;10(1). URL: https://moitvivt.ru/ru/journal/pdf?id=1137. DOI: 10.26102/2310-6018/2022.36.1.004 (accessed on 02.07.2023) (In Russ.).

5. Ayyoubzadeh S.M., Ayyoubzadeh S.M., Zahedi H., Ahmadi M., R Niakan Kalhori S. Predicting COVID-19 incidence through analysis of Google Trends data in Iran: data mining and deep learning pilot study. JMIR Public Health Surveill. 2020;6(2):e18828. DOI: 10.2196/18828.

6. Venkatesh U., Aravind Gandhi P. Prediction of COVID-19 outbreaks using google trends in India: a retrospective analysis. Healthc Inform Res. 2020;26(3):175–184. DOI: 10.4258/hir.2020.26.3.175.

7. Pickering L., Viana J., Li X., Chhabra A., Patel D., Cohen K. Identifying factors in COVID-19 AI case predictions. In: 2020 7th International Conference on Soft Computing & Machine Intelligence (ISCMI); 2020; Stockholm, Sweden. p. 192–196. DOI: 10.1109/ISCMI51676.2020.9311583.

8. Jakovenko N.V., Azarnova T.V., Kashirina I.L., Bondarenko Ju.V., Shhepina I.N. Instrumental methods of human capital assessment: Theory and practical aspects. Voronezh, Cifrovaja poligrafija; 2022. 177 p. (In Russ.).

9. Ketu S., Mishra P.K. India perspective: CNN-LSTM hybrid deep learning model-based COVID-19 prediction and current status of medical resource availability. Soft Comput. 2022;26(2):645–664. DOI: 10.1007/s00500-021-06490-x.

10. Lecun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE. 1998;86(11):2278–2324. DOI: 10.1109/5.726791.

11. Devaraj J., Madurai Elavarasan R., Pugazhendhi R., Shafiullah G.M., Ganesan S., Jeysree A.K., Khan I.A., Hossain E. Forecasting of COVID-19 cases using deep learning models: Is it reliable and practically significant? Results Phys. 2021;21:103817. DOI: 10.1016/j.rinp.2021.103817.

Kashirina Irina Leonidovna
Doctor of Technical Sciences Associate Professor

WoS | Scopus | ORCID | eLibrary |

Voronezh State University

Voronezh, the Russian Federation

Matykina Olga Vyacheslavovna

Voronezh State University

Voronezh, the Russian Federation

Keywords: COVID-19, machine learning, time series, dynamics prediction, hybrid neural network

For citation: Kashirina I.L. Matykina O.V. Development of methods for forecasting the dynamics of morbidity in the case of COVID-19. Modeling, Optimization and Information Technology. 2023;11(3). Available from: https://moitvivt.ru/ru/journal/pdf?id=1434 DOI: 10.26102/2310-6018/2023.42.3.014 (In Russ).


Full text in PDF

Received 03.08.2023

Revised 25.08.2023

Accepted 06.09.2023

Published 07.09.2023