Title:-
Machine Learning-Based Detection of Cardiovascular Disease
Using ECG Signals.
Presented By-
Group- 01
Name Roll no.
Soumik Mukherjee 12500121002
Aparna Shukla 12500121008
Sourav Kumar 12500121025
ACKNOWLEDGEMENT
• We sincerely thankful to Dr. Ratul Kumar Majumdar Sir for their
guidance and support throughout this project, Machine Learning-Based
Detection of Cardiovascular Disease Using ECG Signals.
• We also extend our gratitude to head of the department Mr. S.K Abdul
Rahim Sir for providing resources, and to our team members for their
collaboration and dedication.
• Thank you all for your encouragement and support.
ABSTRACT
• Predicts heart disease risk using machine learning.
• Uses the K-Nearest Neighbors (KNN) algorithm.
• Built as a web app with Flask for instant results.
• Simple, affordable, and easy method.
• Improves healthcare access for people in need.
INTRODUCTION
• Cardiovascular diseases are a major cause of death, making early detection
crucial.
• Machine learning, especially KNN, helps predict heart disease risk using
health data.
• This project creates a web-based system to evaluate CVD risk using
factors like age, cholesterol, and blood pressure.
• The goal is to provide an easy-to-use tool for early detection, especially
for people in areas with limited healthcare access.
OBJECTIVE
• Build a system that uses machine learning to predict the risk of heart
disease using ECG signals.
• Create an easy-to-use web app that gives real-time risk assessments.
• Provide an early, simple, and affordable way to detect heart disease.
• Make healthcare more available, especially for people in areas with
limited resources.
PROBLEM DEFINITION
• Heart disease is often not found until it becomes serious, leading to major
health problems.
• Current tests are costly, involve medical procedures, and need doctors,
making them hard to access.
• There is a need for an affordable, simple, and effective way to detect heart
disease early.
• This project offers a machine learning system to predict heart disease early
using health data.
NEED OF THE SYSTEM
• Early Detection: Heart disease often doesn’t show signs until it’s too late, but catching it
early can save lives.
• Affordable: Traditional tests are expensive and hard to access, especially in less-
developed areas.
• Painless: The system uses ECG signals and health data, so there’s no need for painful
tests.
• Easy to Access: The web app makes it simple for anyone to check their heart disease risk,
improving healthcare access for everyone.
• Prevention: Helps users understand their health and take action early to prevent
problems.
WHAT IS CARDIO-VASCULAR DISEASE?
• Cardiovascular Disease (CVD) affects the heart and blood vessels.
• It includes conditions like heart attacks, strokes, and heart failure.
• Causes include blocked arteries, high blood pressure, and unhealthy habits.
• Symptoms may include chest pain, trouble breathing, dizziness, and tiredness,
but not always.
• CVD is a leading cause of death worldwide, making early detection and
prevention important.
WHAT IS MACHINE LEARNING?
• Machine Learning (ML) is a type of AI that learns from data.
• It finds patterns and improves over time.
• Used in speech recognition, image classification, and
predictions.
• This project uses ML to predict heart disease risk.
STEPS OF MACHINE LEARNING
• Data Collection: Gather health data like ECG, age, cholesterol, and blood pressure.
• Data Preprocessing: Clean and format the data, handle missing values, and
normalize.
• Feature Selection: Choose important features affecting heart disease risk.
• Model Training: Train the KNN model on the prepared data.
• Model Testing: Evaluate model accuracy using test data.
• Prediction: Use the trained model to predict heart disease risk.
• Model Improvement: Continuously update the model for better performance.
REQUIREMENTS
• Hardware Requirements
• Processor: Intel i3 or higher
• RAM: 4 GB or more
• Storage: 500 GB HDD/SSD
• Software Requirements
• Languages: Python
• Libraries: Flask, scikit-learn, NumPy, Pandas
• IDE: Visual Studio Code
• Web Browser: Chrome
SYSTEM ARCHITECTURE DIAGRAM
ALGORITHMS USED
• K-Nearest Neighbors (KNN):
• A supervised machine learning algorithm used for classification tasks.
• It classifies data points based on the majority class of their nearest
neighbors.
• In this project, KNN is used to predict the risk of cardiovascular disease
based on health data such as ECG signals, cholesterol levels, and age.
TECHNOLOGIES & LIBRARIES USED
• Python: Main language for the model and web app.
• Flask: Framework for building the web app.
• scikit-learn: Library for the KNN algorithm.
• NumPy: Used for data arrays and math operations.
• Pandas: Handles and pre-processes data.
• Matplotlib: Visualizes data and results.
IMPLEMENTATION OF WORK
• Frontend:
• Built using HTML, CSS, and JavaScript for user interface design.
• Provides an interactive and user-friendly platform where users input their health
data for predictions.
• Backend:
• Developed using Python and the Flask web framework.
• Handles data processing, connects the user interface to the KNN machine
learning model, and provides real-time predictions.
CURRENT IMPLEMENTED WORK
OUTPUTS
APPLICATIONS
• Healthcare Monitoring: Allows users to track heart health and spot risks
early.
• Telemedicine: Provides easy access to heart disease risk predictions from
anywhere.
• Preventive Healthcare: Promotes early action by giving users risk
assessments.
• Healthcare Research: Supports research in understanding heart disease
patterns and causes.
FUTURE SCOPE
• Advanced Models: Use better machine learning models for higher accuracy.
• Larger Datasets: Include more data to improve the system’s performance for different
people.
• Wearable Devices: Connect with smartwatches for real-time data and predictions.
• Mobile App: Create a mobile app for easier access.
• Multilingual Support: Add multiple languages to reach more users globally.
CONCLUSION
• The system uses machine learning for early heart disease detection with
the KNN algorithm and health data.
• It provides a simple, affordable, and easy solution through a user-friendly
web app.
• This project improves early diagnosis, promoting better health outcomes
and reducing the global impact of heart disease.
THANK YOU
