One of the most difficult challenges in medicine is predicting heart disease at an early stage. In this study, six machine learning (ML) algorithms, viz., logistic regression, K-nearest neighbor, support vector machine, decision tree, random forest classifier, and extreme gradient boosting, were used to analyze two heart disease datasets. One dataset was UCI Kaggle Cleveland and the other was the comprehensive UCI Kaggle Cleveland, Hungary, Switzerland, and Long Beach V. The performance results of the machine learning techniques were obtained. The support vector machine with tuned hyperparameters achieved the highest testing accuracy of 87.91% for dataset-I and the extreme gradient boosting classifier with tuned hyperparameters achieved the highest testing accuracy of 99.03% for the comprehensive dataset-II. The novelty of this work was the use of grid search cross-validation to enhance the performance in the form of training and testing. The ideal parameters for predicting heart disease were identified through experimental results. Comparative studies were also carried out with the existing studies focusing on the prediction of heart disease, where the approach used in this work significantly outperformed their results.

Heart disease is a danger to people’s health because of its prevalence and high mortality risk. Predicting cardiac disease early using a few simple physical indications collected from a routine physical examination has become difficult. Clinically, it is critical and sensitive for the signs of heart disease for accurate forecasts and concrete steps for future diagnosis. The manual analysis and prediction of a massive volume of data are challenging and time-consuming. In this paper, a unique heart disease prediction model is proposed to predict heart disease correctly and rapidly using a variety of bodily signs. A heart disease prediction algorithm based on the analysis of the predictive models’ classification performance on combined datasets and the train-test split technique is presented. Finally, the proposed technique’s training results are compared with the previous works. For the Cleveland, Switzerland, Hungarian, and Long Beach VA heart disease datasets, accuracy, precision, recall, F1-score, and ROC-AUC curves are used as the performance indicators. The analytical outcomes for Random Forest Classifiers (RFC) of the combined heart disease datasets are F1-score 100%, accuracy 100%, precision 100%, recall 100%, and the ROC-AUC 100%. The Decision Tree Classifiers for pooled heart disease datasets are F1-score 100%, accuracy 98.80%, precision 98%, recall 99%, ROC-AUC 99%, and for RFC and Gradient Boosting Classifiers (GBC), the ROC-AUC gives 100% performance. The performances of the machine learning algorithms are improved by using five-fold cross validation. Again, the Stacking CV Classifier is also used to improve the performances of the individual machine learning algorithms by combining two and three techniques together. In this paper, several reduction methods are incorporated. It is found that the accuracy of the RFC classification algorithm is high. Moreover, the developed method is efficient and reliable for predicting heart disease.

Because of its relevance in the growth of tremendous applications in the medical area, data mining is a hugely important domain for exploration. When it comes to fatalities throughout the world, heart disease appears to be the leading cause of death. Recognizing a person’s risk of heart disease, it is a difficult assignment for health professionals since it takes very much time and extensive medical testing in the existing models. For the early prediction of cardiac disease, an improved version of the K-Nearest Neighbors (KNN) and Decision Tree (DT) classifier are applied, which ensures greater accuracy than existing models. Enhanced KNN is used for the correct treatment of patients and preserve consistency in the heart disease prediction system. We have calculated feature relevance, which assigns a score to independent factors based on how well they predict the difference walking. The variables difference walking, stroke and diabetes were the most relevant aspects, as shown in figure 2. We have compared to other existing models, the proposed model outperforms the existing models in terms of heart disease prediction. And the suggested work’s KNN algorithm hasthe greatest accuracy of 90.97 percentage and the highest ROC Curve of 69.97 percentage in predicting heart disease in comparison to Decision Tree (DT). The expenses and duration of treatment are reduced when the condition is detected early.

One of the most difficult challenges in the health-care sector is to anticipate coronary artery disease. Heart disease seems to be more common in males than in women. The quantity of smokers smoked each day, as well as systolic and diastolic blood pressure, all increase the risk of heart disease. As a result, we propose to create an application that can forecast the risk of heart disease based on fundamental symptoms such as age, sex, pulse rate, and so on. The proposed solution makes use of the machine learning methodology logistic regression, which has been proved to be the most accurate and reliable. The model's performance is assessed using publicly available datasets such as the Cleveland Heart Disease Dataset (CHD), with logistic regression achieving the highest accuracy of 89.52 %. And an accuracy of 93.54 % for ROC_ AUC. We describe a predictive analytics-based technique for detecting heart disease in this research.