Analyzing Covid-19 Data Using Various Algorithms

Abstract

The world strives to combat Covid-19, which has spread very quickly across the world after the disease was first confirmed in Dec 2019 in Wuhan District, China. This disease has infected millions and kills thousands in most countries until today. Machine learning and artificial intelligence are promising technologies that have an effective role in developing business in many sectors. Recent studies have shown the importance of using artificial intelligence and machine learning in the health sector. The results show that they lead to increased processing capability, reliability, and even superiority over the human's performance in particular healthcare tasks. In this research, we applied several machine learning algorithms such as Logistic Regression (LR), Linear Discriminant Analysis (LDA), Classification and Regression Trees (CART), Support Vector Machines (SVM), Gaussian Naive Bayes (NB), and k-Nearest Neighbors (KNN) on Covid-19 dataset provided via Kaggle website to predict the patient's death or survival depending on the patient's health status and some other factors. To evaluate the performance of these algorithms, we used the confusion matrix.