Eventos Anais de eventos
COBEM 2023
27th International Congress of Mechanical Engineering
CLASSIFICATION OF HEART RHYTHM DYNAMICS USING ARTIFICIAL NEURAL NETWORKS
Submission Author:
Igor Fortuna , RJ
Co-Authors:
Igor Fortuna, Marcelo Savi
Presenter: Igor Fortuna
doi://10.26678/ABCM.COBEM2023.COB2023-2404
Abstract
Biological rhythms represent one of the most important manifestations of natural systems and therefore, dynamical analysis can establish relations among responses characteristics and biological functioning. Artificial intelligence developments are motivating automatic systems capable of performing cardiac diagnosis for medical support. This work aims to develop an intelligent system based on artificial neural networks capable of classifying cardiac rhythms from the heart rate variability (HRV) signal extracted from electrocardiograms. Five cardiac rhythms are selected to develop a proof of concept: normal sinus rhythm; atrial fibrillation; sinus bradycardia; premature ventricular contraction; and ventricular tachyarrhythmia. Linear and nonlinear features are employed to feed the artificial neural network, which is analyzed considering different arrangement of input configurations. After the definition of the neural network, clinical cases are analyzed showing satisfactory results, being able to classify the heart rhythm of patients with the same diagnosis offered by cardiologists.
Keywords
nonlinear dynamics, heart rate variability, ECG, cardiovascular rhythms, Artificial Intelligence
