Heart Disease Prediction

Heart Disease Prediction project involves developing a predictive model to identify individuals at risk of heart disease using a dataset from Kaggle. The project includes comprehensive data cleaning and preprocessing, applying Decision Tree and K-Nearest Neighbors (KNN) algorithms that achieved accuracies of 86% and 90%, respectively. Following a hybrid Crisp-DM and Waterfall model, the workflow encompassed stages from data preparation and feature selection to model evaluation. Emphasizing the importance of data quality and insightful visualizations, the project provides valuable insights for healthcare professionals to enhance heart disease prevention and management strategies. The study demonstrates that robust data analysis and statistical modeling are essential for timely diagnosis and effective mitigation of heart disease risks, showcasing the application of machine learning techniques in the healthcare domain and highlighting the impact of data-driven insights on patient outcomes and healthcare management.