Project URL: https://github.com/Jack-Merrett/data-electrocardiograms

Introduction

This project focuses on building a classification model for electrocardiograms (ECG) to predict whether a patient's heartbeat is "at risk" of cardiovascular disease or not. The dataset used in this project contains numerically represented heartbeats along with corresponding binary labels.

Dataset

The dataset used in this project can be downloaded from the following link: ECG Dataset.

The dataset contains the following features:

• Numerically represented heartbeats extracted from ECG readings.
• Binary target labels indicating whether the heartbeat is at risk of cardiovascular disease (1) or not (0).

Model Building

In this project, we aim to develop a classification model that can accurately predict the risk of cardiovascular disease based on ECG readings. We will leverage machine learning techniques, specifically logistic regression, to train and evaluate the model.

Requirements

To run the code and reproduce the results, you will need the following libraries:

• Python (Version 3.10.6 or above)
• NumPy
• Pandas
• SciKit-Learn

Getting started:

• Download the dataset from the provided link.
• Install the required libraries.
• Run the Python code to train the classification model.
• Evaluate the model's performance on test data.
• Interpret the results and make predictions for new ECG readings.

Feel free to explore the code and modify it according to your requirements.

Conclusion

By developing an accurate classification model for electrocardiograms, we can potentially assist in early detection and intervention for individuals at risk of cardiovascular disease. This project aims to contribute to the field of medical diagnostics and provide valuable insights into heart health.

Please refer to the Jupyter Notebook or Python script in this repository for detailed implementation and analysis

License

This project is licensed under Le Wagon.