• Version
• Download 7
• File Size 626.34 KB
• File Count 1
• Create Date 31 January 2026
• Last Updated 31 January 2026

Heart Attack Prediction using Data Science Tools

Vedant Suryawanshi Tanishq Chavan Shlok Raskar
Guided by
Prof. Jayant Kulkarni

Abstract
Heart disease remains one of the leading causes of mortality worldwide, making early prediction and prevention a critical area of focus in healthcare. This project aims to develop a predictive model for identifying individuals at risk of heart attacks using machine learning techniques. The workflow begins with data collection from a publicly available Kaggle dataset containing various medical parameters related to cardiovascular health. The data is then pre-processed through cleaning, label encoding, feature scaling, and the application of SMOTE to address class imbalance. Exploratory data analysis is conducted to uncover correlations and trends, followed by careful feature selection to enhance model performance. Multiple classification algorithms, including Logistic Regression and K-Nearest Neighbours (KNN), are
evaluated to identify the most effective model. The dataset is split into training and testing sets to ensure unbiased model validation. Model performance is assessed using standard evaluation metrics such as accuracy, precision, F1-score, and confusion matrix. A comparative analysis of models is performed to determine the best performer based on reliability and robustness. The final output of the project is a machine learning model capable of providing early warnings for potential heart attack risk, which can assist healthcare professionals in timely intervention and personalized care. This project not only demonstrates the power of data-driven insights in clinical applications but also highlights the importance of integrating machine learning into preventive healthcare strategies.