QRS complex detection based on simple robust 2-D pictorial-geometrical feature.

Area of Science:

• Biomedical Engineering
• Signal Processing
• Cardiology

Background:

• Traditional QRS complex detection methods often require extensive signal preprocessing.
• There is a need for simpler, more efficient algorithms for real-time ECG analysis.

Purpose of the Study:

• To develop a novel heuristic method for QRS complex detection that eliminates the need for preprocessing.
• To introduce a new 2-D geometrical feature space for ECG signal analysis.

Main Methods:

• A sliding window approach was used to generate artificial images from ECG segments.
• A geometrical feature extraction technique based on curve-length and angle of the highest point was applied.
• Machine learning classifiers including K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Adaptive Network Fuzzy Inference Systems (ANFIS) were implemented.

Main Results:

• The proposed method achieved high performance in QRS complex detection.
• Average sensitivity (Se) of 99.93% and positive predictivity (P+) of 99.92% were obtained.
• The method was validated on high-resolution Holter data.

Conclusions:

• The developed heuristic method offers a simple yet effective approach for QRS complex detection without preprocessing.
• This technique demonstrates potential for efficient and accurate automated cardiac analysis.