Leveraging a discriminative dictionary learning algorithm for single-lead ECG classification

Detecting and classifying cardiovascular diseases and their underlying etiology is necessary in critical-care patient monitoring. This paper presents a novel sparse-based classification algorithm for electrocardiogram (ECG) signals. We demonstrate dictionary learning and classification processes simultaneously following the detection of supraventricular and ventricular heartbeats using a single-lead ECG. Such a discriminative label-consistent learning procedure for adapting both dictionaries and classifier to a specified ECG signal, rather than employing pre-defined dictionaries, is our work´s novelty. Because our results demonstrate a classification accuracy of 94.61% for Supra Ventricular Ectopic Beats (SVEB) class and 97.18% for Ventricular Ectopic Beats (VEB) class at sampling rate of 114 Hz on MIT-BIH database, a lower sampling rate of 114 Hz provides sufficient discriminatory power for the classification task.