A Hybrid SEIHCRDV-UKF Model for COVID-19 Prediction. Application on real-time data

The prevalence of COVID-19 has been the most serious health challenge of the 21th century to date, concerning national health systems on a daily basis, since December 2019 when it appeared in Wuhan City. Prediction of pandemic spread plays an important role in effectively reducing this highly contagious disease. Nevertheless, most of the proposed mathematical methodologies, which aim to describe the dynamics of the pandemic, rely on deterministic models that are not able to reflect the true nature of the spread of COVID. In this paper, we propose a SEIHCRDV model - an extension of the classic SIR compartmental model - which also takes into consideration the populations of exposed, hospitalized, admitted in intensive care units (ICU), deceased and vaccinated cases, in combination with an unscented Kalman filter (UKF), providing a dynamic estimation of the time dependent parameters of the system. Apparently, this new consideration could be useful for examining also other pandemics. We examine the reliability of our model over a long period of 265 days, where we observe two major waves of infection, starting in January 2021 which signified the start of vaccinations in Europe, providing quite encouraging predictive performance. Finally, special emphasis is given to proving the non-negativity of SEIHCRDV model, to achieve a representative basic reproductive number R0 and to investigating the existence and stability of disease equilibriums in accordance with the formula produced to estimate R0.


Incorporating global dynamics to improve the accuracy of disease models: Example of a COVID-19 SIR model

Mathematical models of infectious diseases exhibit robust dynamics such ...

COVID-19 Pandemic Outbreak in the Subcontinent: A data-driven analysis

Human civilization is experiencing a critical situation that presents it...

The starting dates of COVID-19 multiple waves

The severe acute respiratory syndrome of coronavirus 2 spread globally v...

Machine learning in front of statistical methods for prediction spread SARS-CoV-2 in Colombia

An analytical study of the disease COVID-19 in Colombia was carried out ...

Comparison of ARIMA, ETS, NNAR and hybrid models to forecast the second wave of COVID-19 hospitalizations in Italy

Coronavirus disease (COVID-19) is a severe ongoing novel pandemic that h...

EDAC: Efficient Deployment of Audio Classification Models For COVID-19 Detection

The global spread of COVID-19 had severe consequences for public health ...

Bayesian dynamical estimation of the parameters of an SE(A)IR COVID-19 spread model

In this article, we consider a dynamic epidemiology model for the spread...

Please sign up or login with your details

Forgot password? Click here to reset