An innovative approach of QRS segmentation based on first-derivative, Hilbert and Wavelet Transforms

Area of Science:

• Biomedical Engineering
• Signal Processing
• Cardiology

Background:

• Accurate QRS detection and segmentation are crucial for electrocardiogram (ECG) analysis, impacting feature extraction, P and T wave segmentation, and heart rate variability (HRV) analysis.
• Existing methods may require extensive preprocessing or struggle with diverse QRS morphologies.

Purpose of the Study:

• To develop and validate an innovative algorithm for precise QRS complex detection and segmentation in ECG signals.
• To evaluate the algorithm's performance across different ECG databases and QRS morphologies.

Main Methods:

• The proposed algorithm integrates adaptive thresholding, Hilbert Transform, and Wavelet Transform techniques.
• A surface indicator approach is employed for QRS onset and offset detection, minimizing the need for full ECG signal preprocessing.

Main Results:

• The algorithm achieved high sensitivity (99.15-99.75%) and positive predictability (99.18-99.65%) on the MIT-BIH Arrhythmia and QT databases.
• Average segmentation errors for QRS onset and offset were minimal (2.85±9.90ms and 2.83±12.26ms, respectively) on the QT database.

Conclusions:

• The developed algorithm demonstrates high accuracy and robustness in detecting and segmenting QRS complexes across various morphologies.
• The method effectively adapts to morphological variations within ECG records, offering reliable performance for HRV and other ECG analyses.