Heart Disease Classification Using Enhanced Machine Learning Techniques

This study builds upon existing machine learning-based heart disease classification models by incorporating an extended exploratory data analysis and refined validation techniques. In contrast to the original work, we introduced visual analytics such as histograms and pairplots to better understand feature distributions and interrelationships. Boxplot analysis was utilized to identify potential outliers in the dataset. Subsequently, correlation insights were further enhanced using a confusion matrix. A critical part of our work involved training models both with and without outliers, and evaluating their performance using 5-fold and 10-fold cross-validation strategies.