Skip to Main Content
Ventricular tachycardia is ventricular cardiac arrhythmia that could be calamitous and life threatening. The ability to provide accurate and well-timed predictions of ventricular tachycardia events can save lives. This research investigates the possibility of using a semantic mining algorithm to predict the onset of ventricular tachycardia in electrocardiogram (ECG) signals. A total of thirteen subjects were obtained from Creighton University Ventricular Tachyarrhythmia Database and MIT-BIH Arrhythmia Database. Based on these downloaded data, damping ratios, natural frequencies and input parameters were extracted using semantic mining algorithm. The data were segmented into ten sec periods before applying them to semantic mining. It was found that extracted parameters from the semantic mining were successful in forecasting ventricular tachycardia one to four minutes earlier than the onset. In brief, this work provides a new method for advanced researches in predicting the onset of heart rhythm irregularities.