Abstract:
The prevalence of heart diseases is increasing at an alarming rate, underscoring the
critical need for accurate and timely diagnosis. Predicting the likelihood of heart
disease is a challenging task that demands precision and efficiency. This study focuses
identifying patients at higher risk of developing heart diseases based
medical attributes. To address this, we developed a Heart Disease Prediction System
capable of determining whether a patient is likely to be diagnosed with heart disease
by analyzing their medical history. The system leverages multiple machine learning
algorithms, including Convolutional Neural Networks (CNN) and XGBoost to predict
and classify heart disease cases. The proposed model emphasizes the accurate
prediction of four major types of heart diseases: Coronary Heart Disease, Heart Failure,
Peripheral Artery Disease, and Heart Attack. CNN was employed for ECG signal
processing, and XGBoost for achieving notable accuracy, powered an AI Chatbot
designed to assist users with queries related to heart health. The performance of the
model demonstrated promising results, successfully identifying the likelihood of heart
ith high accuracy and reliability. By reducing the complexities associated
ith diagnosis, this system significantly alleviates the burden on healthcare providers,
wi
on various
enhances medical care quality, and minimizes associated costs. This project has
provided valuable insights into the application of advanced technologies for predicting
heart disease and improving patient outcomes
