Cardiac Disorder Analysis using Python
📌 Overview
This project presents a computational framework for analyzing ECG (Electrocardiogram) signals to assist in the detection of cardiac abnormalities such as arrhythmias. It focuses on signal preprocessing, feature extraction, and heart rate variability analysis using Python-based tools.
⚙️ Key Features
- 📊 ECG Signal Preprocessing using Wavelet Transform (DWT)
- 🔍 R-Peak Detection based on Pan-Tompkins inspired approach
- ❤️ RR Interval Computation
- 📈 Heart Rate Variability (HRV) Analysis
- 🧠 Basic Machine Learning-based insights for cardiac rhythm analysis
- 📉 Signal Visualization using Python libraries
🧪 Methodology
-
Data Acquisition
- MIT-BIH Arrhythmia Dataset
-
Signal Preprocessing
- Noise removal using wavelet-based filtering
-
Feature Extraction
- QRS detection and R-peak identification
-
Analysis
- RR intervals & HRV computation
- Cardiac rhythm interpretation
🛠️ Tech Stack
- Python
- NumPy, SciPy
- Matplotlib
- PyWavelets (pywt)
- NeuroKit2
📊 Output
- Cleaned ECG signals
- Detected R-peaks
- RR interval graphs
- HRV metrics for cardiac rhythm analysis
🎯 Objective
To demonstrate how signal processing and computational techniques can be used for systematic ECG analysis and early indication of cardiac irregularities.
🚀 Future Scope
- Advanced ML models for arrhythmia classification
- Real-time ECG monitoring integration
- Deployment as a healthcare analytics tool