This paper explores a data-driven approach to predicting heart disease through the application of modern data science techniques. It emphasizes the use of machine learning algorithms, data preprocessing, and model evaluation to identify high-risk individuals based on clinical parameters. The studyleverages real-world medical datasets to construct predictive models that assist in early diagnosis. The proposed methodology enhances decision-making in healthcare by improving accuracy and reducing diagnostic delays, thereby supporting proactive treatment planning. Index Terms—Heart Disease Prediction, Data Science, Machine Learning, Clinical Data, Predictive Modeling, Healthcare Ana lytics, Early Diagnosis, Medical Data Mining, Risk Assessment, Supervised Learning.

TBU..