Prediction of Bradycardia using Decision Tree Algorithm and Comparing the Accuracy with Support Vector Machine
Gowtham Devisetty, Neelam Sanjeev Kumar
Abstract
This study compares the Accuracy of Support Vector Machine (SVM) Classifier and Decision Tree (DT) Classifier in predicting Innovative Bradycardia disease diagnosis. Materials and Methods: There are 7,500 records in the dataset that was used for this investigation. 40 records are utilized in the test to get a 95% confidence level in Accuracy and a 1% margin of error. There are 12 qualities or features per record. Using Decision Tree and SVM, Innovative Bradycardia disease is detected. Results: According to the statistical analysis, the Accuracy of the Decision Tree Classifier was 92.62%, P<0.05, and the Accuracy of the SVM was 87.5%, P<0.05. The p value was calculated as 0.001 (p<0.05, independent sample t-test indicating a statistically significant difference in the accuracy rates between the two algorithms (SVM and DT). Conclusion: In the Innovative Bradycardia prediction task, the Decision Tree Classifier (92.5%) exhibited a significant improvement over the SVM (87.5%), as demonstrated by the findings of the present study.