Risk Prediction Analysis of Ventricular Tachycardia Using QRS Complex Features
Keywords:
Ventricles, QRS Complex Shape, Electrocardiography (ECG), ECG signalsAbstract
Early detection of Ventricular Tachycardia (VT) has the potential to save many patients' lives.VT is a ‘Heart Rhythm' condition(arrhythmia) caused by abnormality in the sinus rhythm,which is initially generated in the lower chambers (ventricles) of the heart. A normal heart beats faster than usual in this condition. An ECG signal is crucial in the first identification and examination of cardiac abnormalities. This study proposes a noise filtering, distinct collection of ECG characteristics, and machine learning-based classifier model for the prediction of ventricular tachycardia arrhythmia. Before extracting the signal's features, the signal is
detrended and denoised to remove the noise and improve feature detection. We will be using "QRS" complex shape features to improve VT prediction performance.
References
Jianwei Zheng,: A High-Precision Machine Learning Algorithm to Classify Left and Right Outflow Tract Ventricular Tachycardia. Front. Physiol.12:641066 (2021).
TimSmole,: A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy. Comput Biol Med. 135:104648 (2021).
Ryan Missel, Prashnna,: A hybrid machine learning approach to localizing the origin of ventricular tachycardia using 12-lead electrocardiograms. Comput Biol Med. 126:104013 (2020).
