A Clinical Data Analysis Based Diagnostic Systems for Heart Disease Prediction Using Ensemble Method

Abstract

The correct diagnosis of heart disease can save lives, while the incorrect diagnosis can be lethal. The UCI machine learning heart disease dataset compares the results and analyses of various machine learning approaches, including deep learning. We used a dataset with 13 primary characteristics to carry out the research. Support vector machine and logistic regression algorithms are used to process the datasets, and the latter displays the highest accuracy in predicting coronary disease. Python programming is used to process the datasets. Multiple research initiatives have used machine learning to speed up the healthcare sector. We also used conventional machine learning approaches in our investigation to uncover the links between the numerous features available in the dataset and then used them effectively in anticipation of heart infection risks. Using the accuracy and confusion matrix has resulted in some favorable outcomes. To get the best results, the dataset contains certain unnecessary features that are dealt with using isolation logistic regression and Support Vector Machine (SVM) classification.

Enhanced Detection of Chronic Heart Disease: A Novel Approach With Extreme Gradient Boosting-Logistic Regression Algorithm

“…Therefore, the OCI-DBN method may compare the trial findings with other cuttingedge methods to enhance the system's performance [9]. Similarly, Support Vector Machine (SVM) algorithms can achieve high coronary heart disease prediction accuracy by processing datasets with essential features [10].…”