Morphological heart arrhythmia detection using Hermitian basis functions and kNN classifier

Area of Science:

• Biomedical Engineering
• Cardiology
• Signal Processing

Background:

• Heart arrhythmias are irregular heart rhythms that can lead to serious health issues.
• Accurate and timely detection of arrhythmias is crucial for effective patient management.
• Electrocardiography (ECG) is a primary tool for diagnosing cardiac arrhythmias.

Purpose of the Study:

• To develop and evaluate a novel method for morphological heart arrhythmia detection.
• To utilize Hermitian basis functions (HBF) for modeling ECG signals.
• To assess the efficiency of a k-nearest neighbor (kNN) classifier for arrhythmia classification.

Main Methods:

• ECG signals were sourced from the MIT/BIH arrhythmia database.
• ECG beats were modeled using Hermitian basis functions (HBF) with optimized width parameter (sigma).
• A feature vector derived from HBF parameters was input into a k-nearest neighbor (kNN) classifier.

Main Results:

• The proposed method achieved high sensitivity (99.00%) and specificity (99.84%) in detecting seven types of arrhythmias.
• The classification process was completed in under 0.6 seconds.
• Performance metrics are comparable to existing state-of-the-art methods.

Conclusions:

• The HBF modeling approach combined with kNN classification provides an effective method for heart arrhythmia detection.
• The system's speed makes it suitable for real-time cardiac monitoring and diagnosis.
• This technique offers a promising advancement in automated arrhythmia analysis.