Blogs

ECG Heartbeat Classification Model This project contains a machine learning model for classifying ECG (Electrocardiogram) heartbeats using scikit-learn and Keras.

ecg

Overview The ECG heartbeat classification model is trained on the MIT-BIH Arrhythmia Database, which contains ECG recordings with annotations for different types of arrhythmias. The model uses a combination of feature extraction with scikit-learn and deep learning with Keras to classify each heartbeat into one of five classes: image

Normal Premature Ventricular Contraction (PVC) Premature Atrial Contraction (PAC) Left Bundle Branch Block (LBBB) Right Bundle Branch Block (RBBB)

Requirements To run this project, you’ll need the following libraries and tools:

Python 3.6 or higher scikit-learn Keras TensorFlow NumPy Matplotlib

Results The ECG heartbeat classification model achieves an accuracy of XX% on the test set, with a precision of XX%, recall of XX%, and F1 score of XX%.

Acknowledgments The MIT-BIH Arrhythmia Database for providing the ECG recordings and annotations. The scikit-learn and Keras libraries for providing the machine learning tools. Any other resources or people you’d like to acknowledge

https://github.com/SamerKharboush/ECG