Related Experiment Videos
Detection of cardiac pathologies in electrocardiogram signals using empirical mode decomposition and neural networks
Juan Manuel Lopez-Pasten1, Juan Manuel Ramirez-Cortes1, Jose Hugo Barron-Zambrano1
1Coordinación de Electrónica, Instituto Nacional de Astrofísica, Óptica y Electrónica, Luis Enrique Erro 1, 72840 Tonantzintla, Puebla Mexico.
Insights
An Artificial Intelligence system accurately classifies cardiac pathologies from Electrocardiogram (ECG) signals. This non-invasive tool achieved high accuracy, aiding in preliminary diagnosis of heart conditions.
Area of Science:
- Cardiology
- Artificial Intelligence
- Biomedical Signal Processing
Background:
- Electrocardiogram (ECG) signals are crucial for diagnosing cardiac pathologies.
- Accurate and efficient diagnostic tools for heart conditions are in high demand.
- Artificial Intelligence (AI) offers potential for advanced medical diagnostics.
Purpose of the Study:
- To develop an AI-based system for classifying individuals as healthy or with cardiac pathology using ECG signals.
- To create a non-invasive and efficient diagnostic tool for cardiac conditions.
- To distinguish between healthy individuals and those with specific cardiac pathologies.
Main Methods:
- Utilized a publicly available database of 2580 ECG signals.
- Applied Empirical Mode Decomposition (EMD) for signal processing.
- Extracted statistical features from EMD modes to create feature vectors.
- Employed an optimized Neural Network (NN) model for classification with cross-validation.
Main Results:
- Achieved a mean accuracy of 96.03% for training.
- Demonstrated a mean accuracy of 92.06% for validation.
- Attained a mean accuracy of 92.20% for testing.
- The system showed high classification accuracy for various cardiac pathologies.
Conclusions:
- The proposed AI system effectively classifies cardiac pathologies from ECG signals with high accuracy.
- The system is computationally efficient, making it valuable for preliminary diagnosis.
- This AI-driven approach provides a promising tool for ECG signal analysis and cardiac health assessment.
Abstract:
The purpose of this work is to develop an Artificial Intelligence-based system capable of classifying individuals as either healthy or having a cardiac pathology (Myocardial Ischemia, Cardiomyopathy, Bundle Branch Block, Dysrhythmia, or Ventricular Hypertrophy) based on the processing of Electrocardiogram (ECG) signals. This system aims to serve as a non-invasive and efficient diagnostic tool. The ECG signals used in this study were obtained from a publicly available database. Signal processing is performed using Empirical Mode Decomposition (EMD). From the decomposition, statistical features are extracted from the modes obtained and structured into a feature vector that represents the signal. Classification is achieved using an optimized Neural Network (NN) model, which uses 2580 ECG signals to distinguish between healthy individuals and those with cardiac disease, considering cross-validation. After implementing the system, the mean accuracy achieved was 96.03% for training, 92.06% for validation, and 92.20% for testing. The proposed system successfully demonstrated high classification accuracy for cardiac pathologies while being computationally efficient, making it a valuable tool for preliminary diagnosis and further analysis of ECG signal.
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and the T...
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac muscle...