Ecg Peak Detection Using Deep Learning Approaches

Abstract

Cardiovascular Diseases (CVDs) Remain A Leading Cause Of Mortality Worldwide, Necessitating Efficient Diagnostic Tools For Early Detection. Electrocardiogram (ECG) Analysis Is A Cornerstone Of Cardiac Diagnosis, But Manual Interpretation Is Time-consuming And Prone To Errors. This Paper Proposes An Automated ECG Classification System Using A Recurrent Convolutional Neural Network (RCNN) To Classify ECG Signals As Normal Or Abnormal. The System Leverages The PTB-XL Dataset, Preprocesses ECG Signals To Remove Noise And Segment Them Into Fixed Windows, And Trains An RCNN Model Combining Convolutional And Recurrent Layers For Spatial And Temporal Feature Extraction. The Proposed Model Achieves An Accuracy Of 92%, Outperforming A Baseline CNN Model (85% Accuracy). A Flask-based Web Interface And Deployment On Streamlit Cloud Ensure Accessibility For Healthcare Professionals. This Work Demonstrates The Potential Of RCNNs For Real-time, Accurate ECG Classification, With Applications In Telemedicine And Emergency Care.

Keywords