QRS template matching for recognition of ventricular ectopic beats.

We propose a quasi real-time method for discrimination of ventricular ectopic beats from both supraventricular and paced beats in the electrocardiogram (ECG). The heartbeat waveforms were evaluated within a fixed-length window around the fiducial points (100 ms before, 450 ms after). Our algorithm was designed to operate with minimal expert intervention and we define that the operator is required only to initially select up to three 'normal' heartbeats (the most frequently seen supraventricular or paced complexes). These were named original QRS templates and their copies were substituted continuously throughout the ECG analysis to capture slight variations in the heartbeat waveforms of the patient's sustained rhythm. The method is based on matching of the evaluated heartbeat with the QRS templates by a complex set of ECG descriptors, including maximal cross-correlation, area difference and frequency spectrum difference. Temporal features were added by analyzing the R-R intervals. The classification criteria were trained by statistical assessment of the ECG descriptors calculated for all heartbeats in MIT-BIH Supraventricular Arrhythmia Database. The performance of the classifiers was tested on the independent MIT-BIH Arrhythmia Database. The achieved unbiased accuracy is represented by sensitivity of 98.4% and specificity of 98.86%, both being competitive to other published studies. The provided computationally efficient techniques enable the fast post-recording analysis of lengthy Holter-monitor ECG recordings, as well as they can serve as a quasi real-time detection method embedded into surface ECG monitors.