Noise Detection and Classification in Chagasic ECG Signals Based on One-Dimensional Convolutional Neural Networks

Caldas, Weslley L.; Madeiro, João Paulo do Vale; Pedrosa, Roberto Coury; Gomes, João P. P.; Du, Wencai; Marques, João Alexandre Lôbo

doi:10.1007/978-3-031-12127-2_8

Cited by 1 publication

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both studies employed the Physionet Challenge 2011 Dataset for testing their approaches and producing their outcomes. In another study, [Caldas et al 2023] used CNN and SVM to develop various methods for binary and multi-class classification. For each type of classification, 10 experiments were conducted using 24h-ECG holter records from the University Hospital Clementino Fraga Filho (HUCFF/UFRJ) collected from patients with Chagas Heart Disease [Alberto et al 2020].…”

Section: Related Workmentioning

confidence: 99%

“…Electrocardiogram (ECG) signals have been widely used as a tool for diagnosing heart diseases , predicting cardiac arrests [Kwon et al 2020], and monitoring cardiorespiratory activity [Brüser et al 2015], being one of the most effective ways to aid to the medical decision to prevent the progression of heart diseases [Caldas et al 2023]. Automated ECG analysis systems require high accuracy in determining ECG signal fiducial points for precise and reliable measurements of morphological features (including amplitudes, area, wave durations, and electrical axis) of local waves such as P wave, QRS complex and T wave, and the interval features (including RR-interval, PR-interval, PRsegment, and QT-interval) [Satija et al 2018].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Automated Machine Learning Method to Efficiently Classify the 12-lead ECG Signal Acquisition Quality

O. Júnior,

Evangelista,

Baronetti

et al. 2023

Anais Do XXIII Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2023)

View full text Add to dashboard Cite

Given their low cost and non-invasive nature, ElectroCardioGram (ECG) signals have been widely used as a useful tool for diagnosing heart diseases. However, acquisition issues such as electrode interchange and oscillation noise may negatively impact expert exam interpretation and even automatic classification tasks. Here we propose an automated machine learning method to efficiently classify the 12-lead ECG signal acquisition quality. It consists of a two-stage classification process. Firstly, the ECG signals are processed and segmented aiming to classify them as noisy or acceptable signals. Then, the second classification stage yields the binary classification correct acquisition or limb electrodes interchange. Concerning the electrode positioning, the Random Forest technique presented interesting results (precision of 97%, recall of 89%, and F1-Score of 93%). Concerning noise detection, Random Forest presented a general accuracy of 85%, a recall of 57%, and a precision of 91%. All the obtained results yield to consider the proposed framework for application within a real telemedicine environment.

show abstract

Section: Related Workmentioning

confidence: 99%