A new SEAIRD pandemic prediction model with clinical and epidemiological data analysis on COVID-19 outbreak

Abstract

Measuring the spread of disease during a pandemic is critically important for accurately and promptly applying various lockdown strategies, so to prevent the collapse of the medical system. The latest pandemic of COVID-19 that hits the world death tolls and economy loss very hard, is more complex and contagious than its precedent diseases. The complexity comes mostly from the emergence of asymptomatic patients and relapse of the recovered patients which were not commonly seen during SARS outbreaks. These new characteristics pertaining to COVID-19 were only discovered lately, adding a level of uncertainty to the traditional SEIR models. The contribution of this paper is that for the COVID-19 epidemic, which is infectious in both the incubation period and the onset period, we use neural networks to learn from the actual data of the epidemic to obtain optimal parameters, thereby establishing a nonlinear, self-adaptive dynamic coefficient infectious disease prediction model. On the basis of prediction, we considered control measures and simulated the effects of different control measures and different strengths of the control measures. The epidemic control is predicted as a continuous change process, and the epidemic development and control are integrated to simulate and forecast. Decision-making departments make optimal choices. The improved model is applied to simulate the COVID-19 epidemic in the United States, and by comparing the prediction results with the traditional SEIR model, SEAIRD model and adaptive SEAIRD model, it is found that the adaptive SEAIRD model's prediction results of the U.S. COVID-19 epidemic data are in good agreement with the actual epidemic curve. For example, from the prediction effect of these 3 different models on accumulative confirmed cases, in terms of goodness of fit, adaptive SEAIRD model (0.99997) ≈ SEAIRD model (0.98548) > Classical SEIR model (0.66837); in terms of error value: adaptive SEAIRD model (198.6563) < < SEAIRD model(4739.8577) < < Classical SEIR model (22,652.796); The objective of this contribution is mainly on extending the current spread prediction model. It incorporates extra compartments accounting for the new features of COVID-19, and fine-tunes the new model with neural network, in a bid of achieving a higher level of prediction accuracy. Based on the SEIR model of disease transmission, an adaptive model called SEAIRD with internal source and isolation intervention is proposed. It simulates the effects of the changing behaviour of the SARS-CoV-2 in U.S. Neural network is applied to achieve a better fit in SEAIRD. Unlike the SEIR model, the adaptive SEAIRD model embraces multi-group dynamics which lead to different evolutionary trends during the epidemic. Through the risk assessment indicators of the adaptive SEAIRD model, it is convenient to measure the severity of the epidemic situation for consideration of different preventive measures. Future scenarios are projected from the trends of various indicators by running the adaptive SEAIRD model.

Keywords: Asymptomatic cases; COVID-19; Disease transmission; Enhanced surveillance; Interventions; Novel coronavirus; Risk assessment; SEAIRD; SEIR; Severity.

Fig. 1

Number of deaths and infected population by gender

Fig. 2

Age distribution in the U.S. states

Fig. 3

Error between normalized smoking rate and fatalities rate

Fig. 4

Residual case order plot (smoking rate vs infected rate & smoking rate vs fatalities rate)

Fig. 5

Five Major Symptoms of SARS-CoV-2

Fig. 6

Other symptoms

Fig. 7

Droplet nucleus transmission

Fig. 8

Timeline of from exposure to coronavirus onset by gender

Fig. 9

SARS-CoV-2 natural history

Fig. 10

Timeline of from exposure to coronavirus onset by age

Fig. 11

Flow chart of overall analysis

Fig. 12

Adaptive SEIARD dynamic model

Fig. 13

Structure diagram of asymptomatic patients in two scenarios

Fig. 14

Simulation of infected cases

Fig. 15

Simulation of infected cases after neural fitting

Fig. 16

The performance of neural fitting and error analysis

Fig. 16

The performance of neural fitting and error analysis

Fig. 17

Simulation of Fatalities

Fig. 18

Simulation of Fatalities after Neural Fitting

Fig. 19

The training performance of daily fatality cases

Fig. 19

The training performance of daily fatality cases

Fig. 20

Fitting Curve of Different Model

Fig. 21

Experiment of Validation Model

Fig. 22

Simulation of other parameters in SEIARD model

Fig. 23

Simulation of other parameters in SEIARD model after neural fitting

Fig. 24

Singapore outbreak simulation data

Fig. 25

Simulation of the indices of risk assessment

Fig. 26

Simulation of the index of risk assessment after neural fitting

Fig. 27

Lymphocytes counts of different severity

Fig. 28

Neutrophil counts of different severity

Fig. 29

Alanine Aminotransferase Content of Different Severity

Fig. 30

Aspartate aminotransferase content of different severity

Fig. 31

Total bilirubin content of different severity