PVC discrimination using the QRS power spectrum and self-organizing maps

Area of Science:

• Biomedical Engineering
• Cardiology
• Signal Processing

Background:

• Premature Ventricular Contractions (PVCs) are common arrhythmias requiring accurate detection.
• Traditional methods for PVC detection can be complex and computationally intensive.
• Analyzing the fractal behavior of electrocardiogram (ECG) signals offers a potential new avenue for arrhythmia analysis.

Purpose of the Study:

• To develop and evaluate a novel method for discriminating Premature Ventricular Contraction (PVC) arrhythmia.
• To utilize the fractal characteristics of QRS complex power spectrum density for beat classification.
• To assess the efficacy of the proposed method using a standard clinical database.

Main Methods:

• Linear interpolation of QRS complex power spectrum density in Bode diagrams to obtain slopes in two frequency intervals.
• Utilizing the scatter plot of these slopes to identify distinct regions for normal and PVC beats.
• Employing a self-organizing map (SOM) trained with the derived slopes for PVC classification.
• Validation using 46 records from the MIT-BIH arrhythmia database.

Main Results:

• The scatter plot of slopes clearly delineated regions corresponding to normal and PVC beats.
• The self-organizing map achieved a sensitivity of 82.71% and a specificity of 88.06% in PVC discrimination.
• The proposed method demonstrated effectiveness in classifying premature ventricular contractions.

Conclusions:

• The fractal analysis of QRS complex power spectrum density provides a viable approach for PVC arrhythmia detection.
• The proposed method, utilizing slope analysis and self-organizing maps, offers a promising tool for automated arrhythmia classification.
• This technique shows potential for improving the accuracy and efficiency of cardiac arrhythmia monitoring.