Machine Learning Approaches for Early Detection of Heart Diseases

The main objective of the study is to predict the probability of developing heart disease using a Decision Tree Classifier, K-nearest neighbors, and Support Vector Machine, Logistic Regression. Age, sexual pressure, quantity, and levels are among the variables included in the Kaggle dataset. A combination of accuracy, sensitivity, and specificity was used to train and evaluate the algorithms. Based on the accuracy of participants' predictions, the results suggest that learning algorithms could help treat heart disease.The "Heart Disease Prediction"project contains all project information and results. Contributing to the use of multiple algorithms improves patient outcomes to enhance the detection and treatment of heart diseases. Logistic Regression has achieved an accuracy of 86.41%. A module capable of predicting heart disease in a patient has been implemented. A variety of techniques are employed to assess models, including F-measure, ROC, precision, recall, and accuracy. The bagging set learning method using logistic regression provides the best performance, according to the data.