An Efficient COVID-19 Pandemic Survival Analysis to Compare Random Forest and Support Vector Machine for Classifying Performance in Censored Data

Abstract

The aim of the study is to predict the survival of COVID-19 patients using the random forest and support vector machine. Materials and methods: Novel random forest algorithm and novel support vector machine algorithms are iterated 20 times with a sample size of 10 to predict the survival analysis of COVID-19 patients. Result: The novel random forest algorithm significantly has better accuracy of 93.8% compared to SVM with the accuracy of 88.5%. The significance of linear regression (p<0.05 independent sample T-test) is high. Conclusion: Within the limit of the study, the results proved that novel random forest helps in analyzing the data with higher accuracy classifier performance.