Application of Machine Learning for SARS-CoV-2 Outbreak

Abstract

The plan to overcome disease outbreaks due to the novel Coronavirus (SARS-CoV-2) can be viewed from various sides, including the role of computer technology namely machine learning. This technology has been used to solve many problems, including medical-related problems. Due to the importance of research study of machine learning on COVID-19 issues, this research aim is to review literature of application of machine learning for COVID-19 outbreak by using PRISMA methodology. We obtained sixteen research articles as research data. As a result, we identified there three main aims of research study of machine learning on COVID-19 issues, including patient detection (based on the symptoms), epidemic trends or prediction, and social impact. Moreover, the method of machine learning that has been identified to solve COVID-19 issues, including Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (K-NN), Logistic Growth Forecasting Model, Naïve Bayes, Unbiased Hierarchical Bayesian Estimator, Biterm Topic Model (BTM), Support Vector Regression (SVR), Confidence-Aware Anomaly Detection (CAAD), Deep Learning Survival Cox (DLSC), Partial Derivative Regression and Nonlinear Machine Learning (PDR-NML).