Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec 15:11:1279364.
doi: 10.3389/fpubh.2023.1279364. eCollection 2023.

Predicting COVID-19 pandemic waves including vaccination data with deep learning

Ahmed Begga  1 , Òscar Garibo-I-Orts  1 , Sergi de María-García  1 , Francisco Escolano  2 , Miguel A Lozano  2 , Nuria Oliver  3 , J Alberto Conejero  1
Affiliations

Predicting COVID-19 pandemic waves including vaccination data with deep learning

Ahmed Begga et al. Front Public Health. .

Abstract

Introduction: During the recent COVID-19 pandemics, many models were developed to predict the number of new infections. After almost a year, models had also the challenge to include information about the waning effect of vaccines and by infection, and also how this effect start to disappear.

Methods: We present a deep learning-based approach to predict the number of daily COVID-19 cases in 30 countries, considering the non-pharmaceutical interventions (NPIs) applied in those countries and including vaccination data of the most used vaccines.

Results: We empirically validate the proposed approach for 4 months between January and April 2021, once vaccination was available and applied to the population and the COVID-19 variants were closer to the one considered for developing the vaccines. With the predictions of new cases, we can prescribe NPIs plans that present the best trade-off between the expected number of COVID-19 cases and the social and economic cost of applying such interventions.

Discussion: Whereas, mathematical models which include the effect of vaccines in the spread of the SARS-COV-2 pandemic are available, to the best of our knowledge we are the first to propose a data driven method based on recurrent neural networks that considers the waning effect of the immunization acquired either by vaccine administration or by recovering from the illness. This work contributes with an accurate, scalable, data-driven approach to modeling the pandemic curves of cases when vaccination data is available.

Keywords: COVID-19; SARS-CoV-2; computational epidemiology; data science for public health; non-pharmaceutical interventions; recurrent neural networks; vaccination.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Weibull distributions to model the decay effect of the 8 vaccines (OA, CA, MO, SP, SV, GA, JA, and PB) on infected and fully vaccinated individuals.
Figure 2
Figure 2
Given the previous contexts Rn-1j and actions An-1j on GEO j up to the n−1-th day, the model computes an estimated R^nj which is the infection rate at n-th day for GEO j as a result of combining both branches with a lambda function.
Figure 3
Figure 3
Predictions from 25th January to 11th February of the number of COVID-19 cases vs. the ground truth (yellow dashed line) for Europe with MAE per 100,000 inhabitants.
Figure 4
Figure 4
Prediction of the number of COVID-19 cases vs. the ground truth for Poland with MAE per 100,000 inhabitants in January 2021.
Figure 5
Figure 5
Predictions of the number of COVID-19 cases vs. the ground truth for France with MAE per 100,000 inhabitants in February 2021.
Figure 6
Figure 6
Predictions of the number of COVID-19 cases vs. the ground truth for Ireland with MAE per 100,000 inhabitants in March 2021.
Figure 7
Figure 7
Predictions of the number of COVID-19 cases vs. the ground truth for Italy with MAE per 100,000 inhabitants in April 2021.
See this image and copyright information in PMC

References

    1. Dong E, Du H, Gardner L. An interactive web-based dashboard to track COVID-19 in real time. Lancet Infect Dis. (2020) 20:533–4. 10.1016/S1473-3099(20)30120-1 - DOI - PMC - PubMed
    1. Mathieu E, Ritchie H, Ortiz-Ospina E, Roser M, Hasell J, Appel C, et al. . A global database of COVID-19 vaccinations. Nature Hum Behav. (2021) 5:947–53. 10.1038/s41562-021-01122-8 - DOI - PubMed
    1. Arenas A, Cota W, Gómez-Gardeñes J, Gómez S, Granell C, Matamalas JT, et al. . Modeling the spatiotemporal epidemic spreading of COVID-19 and the impact of mobility and social distancing interventions. Phys Rev X. (2020) 10:041055. 10.1103/PhysRevX.10.041055 - DOI
    1. Bertozzi AL, Franco E, Mohler G, Short MB, Sledge D. The challenges of modeling and forecasting the spread of COVID-19. Proc Natl Acad Sci USA. (2020) 117:16732–8. 10.1073/pnas.2006520117 - DOI - PMC - PubMed
    1. Mwalili S, Kimathi Mv, Ojiambo V, Gathungu D, Mbogo R. SEIR model for COVID-19 dynamics incorporating the environment and social distancing. BMC Res Notes. (2020) 13:352. 10.1186/s13104-020-05192-1 - DOI - PMC - PubMed

Publication types

Supplementary concepts