Caracterización de Fibrilación Ventricular para Predicción de Riesgo de Muerte Súbita Cardíaca basado en Análisis Wavelet

Sudden Cardiac Death describes unexpected natural death from a cardiac cause in a short period of time, this is one of the main causes of death in the world and represents more than 50% of deaths from Cardiovascular Diseases and Ventricular Fibrillation is the most frequent peculiarity that leads to...

ver descrição completa

Detalhes bibliográficos
Autor: Miguel Loria
Formato: tesis de maestría
Estado:Versión aceptada para publicación
Fecha de publicación:2022
País:México
Recursos:Instituto Nacional de Astrofísica, Óptica y Electrónica
Repositorio:Repositorio Institucional del INAOE
Idioma:español
OAI Identifier:oai:inaoe.repositorioinstitucional.mx:1009/2371
Acesso em linha:http://inaoe.repositorioinstitucional.mx/jspui/handle/1009/2371
Access Level:acceso abierto
Palavra-chave:info:eu-repo/classification/Inspec/ECG
info:eu-repo/classification/Inspec/Fibrilación Ventricular
info:eu-repo/classification/Inspec/Muerte Súbita Cardíaca
info:eu-repo/classification/Inspec/Wavelet
info:eu-repo/classification/cti/1
info:eu-repo/classification/cti/22
info:eu-repo/classification/cti/2209
info:eu-repo/classification/cti/220990
Descrição
Resumo:Sudden Cardiac Death describes unexpected natural death from a cardiac cause in a short period of time, this is one of the main causes of death in the world and represents more than 50% of deaths from Cardiovascular Diseases and Ventricular Fibrillation is the most frequent peculiarity that leads to this as it can lead to the inability of the heart to pump blood effectively and thus its survival rate decreases by every minute until it leads to death due to sudden cardiac arrest. Therefore, early prediction of this arrhythmia is very important for timely treatment and a higher survival rate. The Electrocardiogram is one of the most important techniques for diagnosing heart disease, to deal with these problems. In this paper, we propose a method to classify these signals using Wavelet Packet Entropy. Specifically, we first decompose the QT complexes of these signals with the help of Wavelet Packet Decomposition, and then calculate the entropy from the decomposed coefficients as representative features, and finally train a Random Forest-based classification model with which carry out experiments that allow the characterization of Ventricular Fibrillation to predict the risk of Sudden Cardiac Death. The experimental results show that the proposed methodology is promising for Electrocardiogram classification, allowing prediction with greater anticipation, accuracy and precision than the state of the art.