Analysis and Comparison for Innovative Prediction of COVID-19 using Logistic Regression Algorithm over the Decision Tree Algorithm with Improved Accuracy

Abstract

Aim: The major goal of this research is to increase the accuracy of innovation prediction and examine the COVID-19. Materials and Method: This study relied on data collected from Kaggle’s website and samples are divided into two groups, GROUP 1 (N=20) for Logistic regression and GROUP 2 (N=20) for Decision tree in accordance with the total sample size calculated using clinical.com by keeping 0.05 alpha error-threshold, 95% confidence interval, enrolment ratio as 0:1, and G power at 80%. It involves the software implementation program in MatLab 2021a validating with 20 validations. Results: The accuracy, sensitivity, and precision rates are compared using SPSS software and an Independent sample T-Test. In comparison the Logistic regression 95.98% accuracy with P=0.001, (p<0.05), 94.65% sensitivity (with P=0.001, (p<0.05) and 96.20% precision with P=0.001, (p<0.05) produces a superior outcome than the Decision tree 93.91% accuracy with P=0.001, (p<0.05), 94.33% sensitivity with P=0.001, (p<0.05), 92.00% precision with P=0.001, (p<0.05). Conclusion: The Logistic regression algorithm produces better results compared to the Decision tree.