Comparison of Machine learning approaches to predict COVID-19 infection

Abstract

In today’s world, the SARS-CoV2 virus, which causes COVID-19 (coronavirus) has become a pandemic and has spread all over the world. Because of increasing number of cases day by day, it takes time to interpret the laboratory findings thus the limitations in terms of both treatment and findings are emerged. Due to such limitations, the need for clinical decisions making system with predictive algorithms has arisen. Predictive algorithms could potentially ease the strain on healthcare systems by identifying the diseases. In this study, we perform clinical predictive models that estimate, using machine learning. To evaluate the predictive performance of our models, precision, F1-score, recall, AUC, and accuracy scores calculated. The experimental results indicate that our predictive models identify the future confirmed cases (COVID- 19 disease) at accuracy of 94.60%, F1-score of 93.38%, precision of 89.48%, recall of 96.48%, and AUC of 78.50%. It is observed that predictive models trained on datasets could be used to predict COVID-19 infection, and can be helpful for medical experts to prioritize the resources correctly. The models (available at (https://github.com/JananiPrabu/COVID-19-Machine-learning-comparision))can be used to assist the medical experts and clinical prediction studies.