Cardiovascular Disease Risk Prediction Based on ECG Signals

This project presents a web-based platform designed to assist in the prediction of cardiovascular disease risk using electrocardiogram (ECG) signals and machine learning techniques. The system integrates ECG signal analysis, feature extraction, and predictive models in order to support medical analysis and research related to cardiovascular conditions.

Cardiovascular diseases represent one of the leading causes of mortality worldwide. Early detection and accurate risk assessment are essential for improving prevention strategies and treatment outcomes. This platform aims to support these objectives by providing tools for ECG data analysis and cardiovascular risk prediction through machine learning algorithms.

The application allows users to upload ECG data, extract relevant features from the signals, and apply trained machine learning models to estimate the risk of cardiovascular disease. The platform also provides functionalities for managing patient information, analyzing medical data, and generating statistical insights useful for both clinicians and researchers.

Project Overview

The system is implemented as a web application that combines backend processing, machine learning models, and a user-friendly interface for interacting with medical data.

The main objectives of the project are:

• processing ECG signals for medical analysis
• extracting relevant features from ECG data
• applying machine learning algorithms for cardiovascular risk prediction
• providing an interface for medical staff and researchers
• supporting statistical analysis and visualization of patient data

The application supports different types of users such as medical staff, patients, and researchers, each having access to specific functionalities within the platform.

Technologies Used

The platform is developed using modern web technologies and machine learning tools.

Main technologies used in the project include:

• Python
• Django
• Machine Learning algorithms (Logistic Regression, Random Forest, Decision Tree, Support Vector Machine)
• HTML and CSS
• Tailwind CSS
• SQLite database

Machine learning models are trained to analyze ECG-derived features and classify potential cardiovascular risks based on the available medical data.

Main Functionalities

The platform provides several core functionalities:

• patient management and medical data storage
• ECG dataset upload and processing
• feature extraction from ECG signals
• cardiovascular disease risk prediction using machine learning models
• statistical analysis and visualization
• role-based dashboards for different types of users

Researchers can also import datasets and run machine learning analysis to evaluate prediction models and analyze cardiovascular risk patterns.

Machine Learning Models

The system integrates multiple machine learning algorithms used for cardiovascular risk prediction:

• Logistic Regression
• Random Forest
• Decision Tree
• Support Vector Machine (SVM)

These models are trained on ECG-derived datasets and are used to classify patient risk levels based on extracted features.

Project Structure

The repository contains the following main components:

• medicare – Django project configuration and settings
• users – application responsible for user management and medical functionalities
• models – trained machine learning models used for prediction
• theme – frontend styling and interface components
• manage.py – Django project management script
• requirements.txt – project dependencies