Real-time Detection of Pace Pulses in a Single Lead ECG

This paper presents an algorithm for real-time pace pulses detection in a single-lead ECG, based on assessment of the cumulative slope of the ECG signal calculated in a narrow time window. The algorithm is trained and tested on an artificial database containing 780 ECGs in lead II (390 for training, 390 for testing) that represent different arrhythmias, combined with artificially superimposed pace pulses, which cover the wide ranges of rising edge $(< 10\ {\mu s\ {to}}\ 100\ {\mu s})$ and total pulse durations (100 μ s to 2 ms) and correspond to various pacemaker modes. The achieved accuracy is Se=99.3%, PPV=99.0% for ECGs sampled at Fs=32kHz, and Se=97.1%, PPV=96.8% for Fs=16kHz.