Predicting the Epidemic Curve of the Coronavirus (SARS-CoV-2) Disease (COVID-19) Using Artificial Intelligence

Abstract

25Objectives 26 The current form of severe acute respiratory syndrome called coronavirus disease 2019 27 (COVID-19) caused by a coronavirus (SARS-CoV-2) is a major global health problem. The 28 aim of our study was to use the official epidemiological data and predict the possible outcomes 29 of the COVID-19 pandemic using artificial intelligence (AI)-based RNNs (Recurrent Neural 30 Networks), then compare and validate the predicted and observed data. 31 Materials and Methods 32We used the publicly available datasets of World Health Organization and Johns Hopkins 33 University to create the training dataset, then have used recurrent neural networks (RNNs) with 34 gated recurring units (Long Short-Term Memory -LSTM units) to create 2 Prediction Models. 35Information collected in the first t time-steps were aggregated with a fully connected (dense) 36 neural network layer and a consequent regression output layer to determine the next predicted 37 value. We used root mean squared logarithmic errors (RMSLE) to compare the predicted and 38 observed data, then recalculated the predictions again. 39 Results 40The result of our study underscores that the COVID-19 pandemic is probably a propagated 41 source epidemic, therefore repeated peaks on the epidemic curve (rise of the daily number of 42 the newly diagnosed infections) are to be anticipated. The errors between the predicted and 43 validated data and trends seems to be low. 44 Conclusions 45 3The influence of this pandemic is great worldwide, impact our everyday lifes. Especially 46 decision makers must be aware, that even if strict public health measures are executed and 47 sustained, future peaks of infections are possible. The AI-based predictions might be useful 48 tools for predictions and the models can be recalculated according to the new observed data, 49 to get more precise forecast of the pandemic. 50 51 52 53 54 55 56 57 58 59 60 61 4 62

Review of Big Data Analytics, Artificial Intelligence and Nature-Inspired Computing Models towards Accurate Detection of COVID-19 Pandemic Cases and Contact Tracing

“…For instance, LSTM and RNN have been applied to predict the life expectancy from electronic medical records [67]. Additionally, an LSTM and RNN model was used to predict the epidemic of COVID-19 [68]. The AI applications' interventions for the COVID-19 pandemic include the early "detection and diagnosis of the infection", prevention of disease, monitoring the treatment, contact tracing of the individuals, drugs and vaccines development, reducing the workload of healthcare workers and projections of cases and mortality [58].…”

Applications of artificial intelligence in battling against covid-19: A literature review

“…This makes the algorithms able to model temporal information. In [374] , a recurrent neural network is proposed to predict the epidemic curve. Two prediction models are created in this work, first the data are fed to a dense neural network and then a consequent regression output layer is used to predict the value.…”

“…The method consists of a data generation process based on Monte Carlo simulations of SIR epidemiology models. LSTM algorithm, combined with a recurrent neural network is used in [413] to build two prediction model of the pandemic in India. In [414] , recurrent NN based Deep LSTM, convolutional LSTM and bi-directional LSTM are used to predict the pandemic in India.…”

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

“… 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 series [150] April, 2020 Variational-LSTM autoencoder Predict COVID-19 pandemic spread across globe Time series [151] April, 2020 Distinct ML models (RF, MLP, LSTM-R, LSTM-E, M-LSTM) Forecast COVID-19 cases in Iran Text [152] …”