Maximum likelihood-based extended Kalman filter for COVID-19 prediction

Song, Jialu; Xie, Hujin; Gao, Bingbing; Zhong, Yongmin; Gu, Chengfan; Choi, Kup‐Sze

doi:10.1016/j.chaos.2021.110922

Cited by 42 publications

(43 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For high values of v, the Student's t distribution resembles the Gaussian distribution. For this reason we prefer to use a normal error, which in turn has other advantages [26][27][28], and is given by…”

Section: Model Fitting and Assessmentmentioning

confidence: 99%

A new model of unreported COVID-19 cases outperforms three known epidemic-growth models in describing data from Cuba and Spain

Ramirez-Torres

Castañeda²,

Rández

et al. 2021

Preprint

View full text Add to dashboard Cite

Estimating the unreported cases of Covid-19 in a region/country is a complicated problem. We propose a new mathematical model that, combined with a deterministic model of the total growth of cases, describes the time evolution of the unreported cases for each reported Covid-19 case. The new model considers the growth of unreported cases in plateau periods and the decrease towards the end of an epidemic wave. We combined the new model with a Gompertz-growth model, a generalized logistic model, and a susceptible-infectious-removed (SIR) model; and fitted them via Bayesian methods to data from Cuba and Spain. The combined-model fits yielded better Bayesian-Information-Criterion values than the Gompertz, logistic, and SIR models alone. This suggests the new model can achieve improved descriptions of the evolution of a Covid-19 epidemic wave.

show abstract

Section: Model Fitting and Assessmentmentioning

confidence: 99%

A new model of unreported COVID-19 cases outperforms three known epidemic-growth models in describing data from Cuba and Spain

Ramirez-Torres

Castañeda²,

Rández

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…T , z i are the measured variables and Q id,i ∈ R 4×4 is a weight matrix calculated to normalize measurements from early stages of the pandemic to July 1 st 2021 according to Equation (17). All integration therein state estimators are solved with cvodes via CasADI/MATLAB.…”

Section: /16mentioning

confidence: 99%

“…Zhu et al 16 estimated states and parameters into an augmented state with an Extended Kalman Filter (EKF). Song et al 17 estimated states with an EKF and parameters with a proposed strategy based on maximum likelihood. Nonetheless, state and parameter estimations in the literature are based on simple models and the authors did not evaluate virus mutations and vaccination dynamics with the estimator results.…”

Section: Introductionmentioning

confidence: 99%

Recursive State and Parameter Estimation of COVID-19 Circulating Variants Dynamics

Silva

Secchi

2021

Preprint

View full text Add to dashboard Cite

COVID-19 pandemic response with non-pharmaceutical interventions is an intrinsic control problem. Governments balance social distancing policies to avoid overload on health system without major economic impact. A control strategy requires reliable predictions to be efficient on long-term. SARS-CoV-2 mutability, vaccination coverage and time-varying restrictive measures change virus evolution dynamics frequently. State and parameter estimations are an option do deal with these uncertainties. In this paper, a SIR-based model is proposed considering data available and feedback corrections over time. State and parameter estimations were done on state estimators with augmented states. Three observers were implemented: Constrained Extended Kalman Filter (CEKF), CEKF and Smoother (CEKF&S) and Moving Horizon Estimator (MHE). The parameters estimated therein are based on vaccine efficacy studies regarding transmissibility, severeness of disease and lethality. Social distancing is a measured disturbance calculated with Google mobility data. Six federative units from Brazil are used to evaluate proposed strategy: Amazonas, Mato Grosso do Sul, Rio Grande do Norte, Rio Grande do Sul, Rio de Janeiro and São Paulo. State and parameter estimations were realized from October 1 st 2020 to July 1 st 2021 during which Zeta and Gamma variants emerged. Results showed an efficient detection of circulating variants from proposed parameter estimation. In addition, it asserted dynamics related to virus mutations. Zeta mutations increase lethality between 19 and 45%, and increased transmissibility between 20 and 38%. Gamma mutations, on the other hand, increased lethality between 62 and 110% while increasing transmissibility between 52 and 107%. Furthermore, parameter estimation indicated existence and temporal change of subnotification on hospitalized and deceased individuals. Overall, dynamics estimated were within expectations and are applicable to control theory.

show abstract

“…The inadequate contact tracing, lack of population-wide PCR testing and short-term policy changes also cause the uncertainties in reported data on COVID-19 [ 32 ]. However, the existing studies on COVID-19 modelling are dominated by deterministic epidemiological models for describing the epidemiological evolution deterministically via ordinary differential equations, unable to model the stochastic behaviours of the COVID-19 epidemic [ 9 , 10 ]. Therefore, it is also necessary to develop a stochastic epidemiological model to account for random or stochastic events involved in the COVID-19 transmission system.…”

Section: Introductionmentioning

confidence: 99%

“…However, the predator-prey interaction mechanism described by the Lotka-Volterra model has a very limited capacity to model the complex characteristics of the natural transmission process of COVID-19. Song et al studied a novel maximum likelihood based EKF to estimate COVID-19 spread [ 9 ]. However, since this method is based on a deterministic epidemiological model, it is incapable of characterizing the stochastic characteristics of COVID-19 spread.…”

Section: Introductionmentioning

confidence: 99%

Extended Kalman filter based on stochastic epidemiological model for COVID-19 modelling

Zhu

Gao

Zhong

et al. 2021

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

This paper presents a new stochastic-based method for modelling and analysis of COVID-19 spread. A new deterministic Susceptible, Exposed, Infectious, Recovered (Re-infected) and Deceased-based Social Distancing model, named SEIR(R)D-SD, is proposed by introducing the re-infection rate and social distancing factor into the traditional SEIRD (Susceptible, Exposed, Infectious, Recovered and Deceased) model to account for the effects of re-infection and social distancing on COVID-19 spread. The deterministic SEIRD(R)D-SD model is further converted into the stochastic form to account for uncertainties involved in COVID-19 spread. Based on this, an extended Kalman filter (EKF) is developed based on the stochastic SEIR(R)D-SD model to simultaneously estimate both model parameters and transmission state of COVID-19 spread. Simulation results and comparison analyses demonstrate that the proposed method can effectively account for the re-infection and social distancing as well as uncertain effects on COVID-19 spread, leading to improved accuracy for prediction of COVID-19 spread.

show abstract

Maximum likelihood-based extended Kalman filter for COVID-19 prediction

Cited by 42 publications

References 28 publications

A new model of unreported COVID-19 cases outperforms three known epidemic-growth models in describing data from Cuba and Spain

A new model of unreported COVID-19 cases outperforms three known epidemic-growth models in describing data from Cuba and Spain

Recursive State and Parameter Estimation of COVID-19 Circulating Variants Dynamics

Extended Kalman filter based on stochastic epidemiological model for COVID-19 modelling

Contact Info

Product

Resources

About