Machine Learning-Based Application for Long-Term Electrocardiogram Analysis

Machine Learning-Based Application for Long-Term Electrocardiogram Analysis

Jonathan Araujo Queiroz, Juliana M. Silva, Yonara Costa Magalhães, Will Ribamar Mendes Almeida, Bárbara Barbosa Correia, José Ricardo Santo de Lima, Edilson Carlos Silva Lima, Marcos Jose Dos Passos Sa, Allan Kardec Barros Filho
Copyright: © 2024 |Pages: 14
DOI: 10.4018/979-8-3693-0851-6.ch004
OnDemand:
(Individual Chapters)
Available
$33.75
List Price: $37.50
Current Special Offers
10% Discount:-$3.75
TOTAL SAVINGS: $3.75

Abstract

Electrocardiogram (ECG) analyses can only be performed by health professionals whose demand for care is often greater than the availability. In this context, this work consists of the development of an application capable of processing long-lasting ECG signals to assist health professionals in making decisions. The application has an interactive interface that allows view the entire ECG signal in a single image generated by all overlapping cardiac cycles. The proposed application still has email communication between users with the objective of facilitating patient follow-up. The application was tested on three different ECG signals, one artificial and two real. The first signal was an artificial signal generated in software Matlab. The second ECG signal has normal sinus rhythm, available in the MIT-BIH normal sinus rhythm database. The third ECG sign diagnosed with arrhythmia can be found in the MIT-BIH arrhythmia database. The results obtained by the proposed method can be used to support decision-making in clinical practice.
Chapter Preview
Top

Background

Usually, cardiac variability is used to provide temporal information of the ECG signal. The cardiac variability is obtained by the R-R interval, which is defined like Eq.1

interval R-R = RR = Rm − Rm−1,(1)

m being the time point of the m-th peak R.

Several authors use the R-R interval, which is the difference between two consecutive R waves, as a source of data extraction. However, the analysis of RR intervals does not is able to measure changes in other ECG signal waves, such as the P wave distortions for AF and the appearance of the F wave in the atrial flutter (Maan et al.,2014). The proposed method in our previous study uses the voltage variability in each heartbeat, unlike the R-R interval, in which each cardiac cycle is associated with a single real number, the proposed method associates each cardiac cycle to a set of points, that is, to a vector.

This method uses the variation of tension in each cardiac cycle is defined as

b = (b1, b2, · · ·, bm),(2)

where b is a cardiac cycle, bm the m-th sample in millivolt (mV) of b with

LI(b) ≤ m ≤ LS(b), in such a way that LS(b) is the upper limit and LI(b) the lower limit of m. The upper limit LS(b) and lower LI(b) are given by Eq.3

LS(b) = PR + Fsλ,(3)

Complete Chapter List

Search this Book:
Reset