An initiative in the direction to predict heart disease earlier using various parameters input to a machine learning model trained on a dataset (UCI Cleveland dataset). It is a term work project fulfilled towards the course 19CCE213 - Machine Learning & Artificial Intelligence.
The dataset contains a total of 76 attributes but only 14 features are extracted to predict heart disease. Each attribute is visually plotted using appropriate graph and the effect of each feature on the output class - Acquired Heart Disease is also plotted. Machine learning models such as Naive Bayes classifier, Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbour (KNN) are used to train on the dataset and the accuracy results of the ML models are compared with one another.
The project documentation contains addtional details on methodology, feature set, plots and comprehensive analysis of ML models listed above trained using the dataset.