Death/Recovery Prediction for Covid-19 Patients using Machine Learning

Abstract

Covid19 is a newly discovered corona virus that has been officially announced as a pandemic by the World Health Organization in March 2020. It is a new virus in the medical field that has no specific treatment and no vaccines until this moment. Covid19 is spreading very fast as the medical systems over the world are not able to hospitalize all the patients which lead into a significant increase in the number of the virus death. This work uses machine learning models to predict which patient has a higher probability of death. Three different algorithms such as multilayer perceptron, support vector machine and K nearest neighbor were used in this work. The accuracies achieved were between 92% to 100% with MLP, SVM and KNN. SVM achieved the highest accuracy. The models were evaluated through precision, accuracy, recall and F measure.