MACHINE LEARNING BASED HEART ATTACK RISK PREDICTION AND ANALYSIS

Abstract

Heart
related diseases remain one of the
leading causes of death worldwide, often
due to late detection and lack of early
warning systems. This project presents a
machine learning based approach to
estimate the risk of heart attacks using
patient clinical data. Instead of depending
on a single algorithm, multiple models are
developed and compared to identify the
most effective prediction technique. The
system utilizes key medical attributes such
as age, cholesterol level, blood pressure,
and ECG results.
Data preprocessing
techniques including handling missing
values, feature transformation, and
normalization are applied to improve data
quality and model performance.
Experimental results show that ensemble
learning methods provide better accuracy
due to
their ability to capture complex
relationships among features. The system
also includes visualization tools to help
users understand prediction outcomes
easily. This project demonstrates how
intelligent data driven systems can support
early diagnosis and assist healthcare
professionals in making timely decisions.
Keywords: Heart disease prediction,
Machine Learning, XGBoost, CatBoost,
LightGBM, Logistic Regression, Random
Forest, Support Vector Machine, ECG,