EPIDEMIC FORECASTING AS A DIRECTION OF USING ARTIFICIAL INTELLIGENCE IN PUBLIC HEALTH
DOI:
https://doi.org/10.11603/1681-2786.2025.3.15637Keywords:
public health; artificial intelligence; epidemic forecasting; model; COVID-19.Abstract
Purpose: analysis of modern methods of epidemic forecasting using artificial intelligence, assessment of their effectiveness and determination of development prospects. Materials and Methods. the analysis used data from peer-reviewed articles, reports of international organizations and company cases for the period 2020–2025. The results are supplemented by a comparison with traditional methods, an assessment of ethical and technical challenges, as well as a discussion of their significance for public health. Results. It was found that artificial intelligence methods showed high efficiency in short-term forecasts (1–4 weeks), where recurrent neural network models and long short-term memory achieved 85–90% accuracy in predicting morbidity and hospitalizations. Spatio-temporal models based on convolutional neural networks and hybrid architectures allowed to determine the risk areas of the spread of infections with an accuracy of up to 90%. At the same time, the accuracy of long-term forecasts (more than 1 month) was lower – 60–75% due to the influence of unpredictable factors, such as changes in population behavior and mutation of pathogens. Conclusions. The use of artificial intelligence in 2020–2025 significantly increased the effectiveness of epidemiological forecasting, ensuring the accuracy of short-term models at the level of 85–90%, the possibility of early detection of outbreaks and exceeding the results of traditional approaches. The best results were demonstrated by hybrid models that combine artificial intelligence with classical epidemiological methods, ensuring a balance between accuracy and interpretation. The use of the latest models of epidemic processes allows developing effective, scientifically sound and effective strategies for preventing morbidity and controlling the spread of epidemics.
References
Butkevych М., Meniailov I., Bazilevych K., Y Parfeniuk Y., Chumachenko D. Simulation of influenza dynamics with LSTM deep learning model. Proceedings IDDM’24: 7th International Conference on Informatics & Data-Driven Medicine., UK, Birmingham, November 14–16. 2024. Vol. 3892. P. 115–125. URL: https://ceur-ws.org/Vol-3892/
Wang L., Zhang Y., Wang D., Tong X., Liu T., Zhang S., Huang J., Zhang L., Chen L., Fan H., & Clarke M. Artificial Intelligence for COVID-19: A Systematic Review. Frontiers in medicine. 8. 2021. 704256. https://doi.org/10.3389/fmed DOI: https://doi.org/10.3389/fmed.2021.704256
Zhou L., Zhao C., Liu N., Yao X., Cheng Z. Improved LSTM-based deep learning model for COVID-19 prediction using optimized approach. Engineering Applications of Artificial Intelligence. 2023. Т. 122. Р. 106157. DOI: 10.1016/j.engappai.2023.106157. DOI: https://doi.org/10.1016/j.engappai.2023.106157
Guo X., Xie W., Li X. Spatial-Temporal Correlation Neural Network for Long Short-Term Demand Forecasting During COVID-19. IEEE Access. 2023. Vol. 11. P. 75573–75586. DOI: 10.1109/ACCESS.2023.3297143. DOI: https://doi.org/10.1109/ACCESS.2023.3297143
Чумаченко Д.І., Чумаченко Т.О. Імітаційне моделювання епідемічних процесів: прикладні аспекти : монографія. Харків : Панов А.М., 2023. 300 с. DOI: https://doi.org/10.30837/SMEP.2023
World Health Organization. World health statistics 2021: monitoring health for the SDGs, sustainable development goals. Geneva: World Health Organization. 2021. URL: https://iris.who.int/bitstream/handle/10665/342703/9789240027053-eng.pdf
González-Escamilla M., Pérez-Ibave D.C., Burciaga-Flores C.H., Ortiz- Murillo V.N., Ramírez-Correa G.A., Rodríguez-Niño P., Piñeiro-Retif R., Rodríguez-Gutiérrez H.F., Alcorta-Nuñez F., González-Guerrero J.F., Vidal-Gutiérrez O., Garza-Rodríguez M.L. Epidemiological Algorithm for Early Detection of COVID-19 Cases in a Mexican Oncologic Center. Healthcare (Basel, Switzerland). 2022. Vol. 10, no. 3. P. 462. DOI: 10.3390/healthcare10030462. DOI: https://doi.org/10.3390/healthcare10030462
Silva P.C.L., Batista P.V.C., Lima H.S., Alves M.A., Guimarães F.G., Silva R.C.P. COVID-ABS: An agent-based model of COVID-19 epidemic to simulate health and economic effects of social distancing interventions. Chaos, solitons, and fractals. 2020. Vol. 139. P. 110088. DOI: 10.1016/j.chaos.2020.110088. DOI: https://doi.org/10.1016/j.chaos.2020.110088
Al Kuwaiti A., Nazer K., Al-Reedy A., Al-Shehri S., Al-Muhanna A., Subbarayalu A.V., Al Muhanna D., Al-Muhanna F.A. A Review of the Role of Artificial Intelligence in Healthcare. Journal of Personalized Medicine. 2023. Vol. 13, no. 6. P. 951. DOI: 10.3390/jpm13060951. DOI: https://doi.org/10.3390/jpm13060951
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
1. The authors reserve the right to authorship of the work and pass the journal right of first publication of this work is licensed under a Creative Commons Attribution License, which allows others to freely distribute the work published with reference to the authors of the original work and the first publication of this magazine.
2. Authors are entitled to enter into a separate agreement on additional non-exclusive distribution of work in the form in which it was published in the magazine (eg work place in the electronic repository institution or publish monographs in part), provided that the reference to the first publication of this magazine.
3. Policy magazine allows and encourages authors placement on the Internet (eg, in storage facilities or on personal websites) manuscript of how to submit the manuscript to the editor and during his editorial processing, since it contributes to productive scientific discussion and positive impact on the efficiency and dynamics of citing published work (see. The Effect of Open Access).
