Machine Learning Model for Predicting Number of COVID-19 Cases in Countries with Low Number of Tests

ABSTRACT

Background: The COVID-19 pandemic has presented a series of new challenges to governments and healthcare systems. Testing is one important method for monitoring and controlling the spread of COVID-19. Yet with a serious discrepancy in the resources available between rich and poor countries, not every country is able to employ widespread testing. Methods and Objective: Here, we have developed machine learning models for predicting the prevalence of COVID-19 cases in a country based on multilinear regression and neural network models. The models are trained on data from US states and tested against the reported infections in European countries. The model is based on four features Number of tests, Population Percentage, Urban Population, and Gini index. Result(s) The population and the number of tests have the strongest correlation with the number of infections. The model was then tested on data from European countries for which the correlation coefficient between the actual and predicted cases R2 was found to be 0.88 in the multi-linear regression and 0.91 for the neural network model Conclusion(s) The model predicts that the actual prevalence of COVID-19 infection in countries where the number of tests is less than 10% of their populations is at least 26 times greater than the reported numbers. Copyright © 2022 Hashim et al.