Forecasting and Evaluating Multiple Interventions for COVID-19 Worldwide

Abstract

As the Covid-19 pandemic surges around the world, questions arise about the number of global cases at the pandemic's peak, the length of the pandemic before receding, and the timing of intervention strategies to significantly stop the spread of Covid-19. We have developed artificial intelligence (AI)-inspired methods for modeling the transmission dynamics of the epidemics and evaluating interventions to curb the spread and impact of COVID-19. The developed methods were applied to the surveillance data of cumulative and new COVID-19 cases and deaths reported by WHO as of March 16th, 2020. Both the timing and the degree of intervention were evaluated. The average error of five-step ahead forecasting was 2.5%. The total peak number of cumulative cases, new cases, and the maximum number of cumulative cases in the world with complete intervention implemented 4 weeks later than the beginning date (March 16th, 2020) reached 75,249,909, 10,086,085, and 255,392,154, respectively. However, the total peak number of cumulative cases, new cases, and the maximum number of cumulative cases in the world with complete intervention after 1 week were reduced to 951,799, 108,853 and 1,530,276, respectively. Duration time of the COVID-19 spread was reduced from 356 days to 232 days between later and earlier interventions. We observed that delaying intervention for 1 month caused the maximum number of cumulative cases reduce by −166.89 times that of earlier complete intervention, and the number of deaths increased from 53,560 to 8,938,725. Earlier and complete intervention is necessary to stem the tide of COVID-19 infection.

Artificial Intelligence (AI) and Big Data for Coronavirus (COVID-19) Pandemic: A Survey on the State-of-the-Arts

“…Another interesting work in [69] proposed a modified autoencoder (MAE) for modeling the transmission dynamics of COVID-19 in the world. Using the data collected from the WHO situation reports, it is shown that the proposed MAE model can predict the outbreak site accurately with an average error less than 2.5%.…”

A survey on artificial intelligence approaches in supporting frontline workers and decision makers for the COVID-19 pandemic

“…A third approach was developed by Hu et al [134] , who attempted to develop an AI-based modified auto-encoder (MAE) that modeled multiple public health interventions by using real data to forecast a potential COVID-19 pandemic outbreak in a large geographic region and subsequently calculating the potential impact of interventions to curb the pandemic. The proposed architecture consisted of two single auto-encoders, each having three feedforward neural network layers.…”

“… Text [132] June, 2020 Partial derivative regression and nonlinear ML method (PDR-NML) COVID-19 pandemic outbreak prediction across globe Text [141] June, 2020 ML-based models (SVM, Linear Regression, and Polynomial Regression) COVID-19 epidemic prediction, transmission rate analysis, and growth rates and migration type analysis. Text [134] May, 2020 Modified Auto-Encoders To estimate pandemic transmission and evaluate interventions and measurements to halt COVID-19 spread Time series [142] May, 2020 Unsupervised Self-Organizing Maps Spatially grouping countries that share similar COVID-19 cases Time series [143] May, 2020 ML-based method with Cloud computing Potential threat and growth prediction of COVID-19 Time series [144] April, 2020 Linear Regression with LSTM Predicting outbreak trends and COVID-19 incidence in Iran. Time series [145] April, 2020 Regression tree and Wavelet transform methods Risk assessment and forecasting COVID-19 outbreak in multiple countries Time series [146] April, 2020 SEIR, SIR models and Neural Network Forecast COVID-19 spread in Italy, South Korea, USA, and Wuhan (China) Time series [147] April, 2020 Hybridized DL-based Composite Monte-Carlo (CMC) with Fuzzy rule induction Forecasting future possibilities w.r.t COVID-19 epidemic Time series [148] April, 2020 SEIR and Regression Model COVID-19 outbreak prediction in India Time series [149] April, 2020 Topological Autoencoder (Simplified Soft-supervisied-TA) Visualization of COVID-19 transmission across globe Time s...…”

Application of artificial neural networks to predict the COVID-19 outbreak

“…They estimated the end of the COVID-19 pandemic in China to be after 20 March 2020, while about 52,000 to 68,000 infected and 2400 death cases were predicted [ 14 ]. Additionally, Hu et al [ 15 ] proposed a method called modified stacked auto-encoder, which was inspired by an artificial intelligence (AI) model, for real-time forecasting of COVID-19. Also, they predicted the middle of April as the end of the epidemics of COVID-19 [ 15 ].…”

“…Additionally, Hu et al [ 15 ] proposed a method called modified stacked auto-encoder, which was inspired by an artificial intelligence (AI) model, for real-time forecasting of COVID-19. Also, they predicted the middle of April as the end of the epidemics of COVID-19 [ 15 ]. Moreover, Yang et al [ 16 ] developed a SEIR model and AI approach, which was trained by the 2003 SARS data for prediction of COVID-19 in China.…”