Detection of Ventricular Late Potentials in Electrocardiograms Using Machine Learning

Fagan, Xavier; Ivanko, K.; Ivanushkina, N.

doi:10.1007/978-3-030-55506-1_44

Cited by 4 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In turn, the following parameters of vector magnitude indicate the presence of LAP: P wave dura�on (PWD) > 115 ms, root-mean-square voltage of the last 20 ms P wave (RMS20) < 2.2 microvolts. The presence of late poten�als was declared if at least two of the three condi�ons for LVP and both condi�ons for LAP were obtained [11]. Therefore, based on this method, a test database was obtained, in which there are 137 recordings with available LVPs, 47 recordings with available LAPs, 14 recordings with available LVPs and LAPs, and 351 recordings without available late poten-�als.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

The Method of Preprocessing of ECG Signals for Detection of Atrial and Ventricular Late Potentials

Mnevets

Ivanushkina

2023

Microsyst., Electron. & Acoust.

View full text Add to dashboard Cite

This article is aimed at analyzing and improving the methods of preprocessing ECG signals for the task of detecting low-amplitude regular components. This study analyzed the main advantages and disadvantages of existing ECG signal preprocessing methods for the detection of late ventricular and atrial potentials. Based on this analysis, a cardiac cycle averaging method was proposed in order to increase the accuracy of detection of late potentials by various algorithms and improve the quality of preprocessing of the ECG signal aimed at detection of low-amplitude components. The main feature of the proposed method is the division of a large number of cardiocycles for averaging into smaller aggregates (epochs), and the subsequent application of linear matrix decomposition to suppress irregular inclusions. Also, when dividing into epochs, it can be used overlapping. It can reduce the difference between epochs, and increase the number of cardiocycles for averaging. The use of this approach allows to minimize irregular inclusions in the ECG signal and increase the accuracy of the selection of low-amplitude late potentials. In addition, the division into epochs and overlapping makes possible to avoid blurring of low-amplitude high-frequency components during averaging as a result of heart rate variability, as well as to improve the quality of averaging with a reduced number of cardiocycles. To test the proposed method, various approaches were used to assess the ECG signal preprocessing. Mostly, we compared the cardiac cycles obtained as a result of different averaging algorithms and the proposed method with the template. To test the averaging method, an artificial ECG signal was developed with existing noise, late ventricular and atrial potentials, heart rate variability, and a high-amplitude component that occurs at a random location every two heartbeats. The template cardiac cycle was obtained from the original artificial signal without any distortion or noise. Firstly, we visually compared and evaluated different averaging methods with the template. Secondly, we calculated the similarity metrics of the late potentials on the averaged cardiac cycle with the late potentials on the template signal. Based on these metrics, the curves of dependence of the similarity values on the amplitude of late potentials on the ECG signal were calculated. Thirdly, we evaluated the impact of the proposed averaging method on the classification results of various machine learning algorithms on real ECG signals with available late potentials. The overall testing result showed that the proposed averaging method is able to reproduce the morphology of low-amplitude regular components by 10-30% more accurately and improve the classification accuracy by 5-12%.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Methods for extrac�ng late poten�als based on the wavelet transform are also widely used. They are used both for denoising [10] and for the efficient detec-�on of late poten�als [11]. It has both a number of posi-�ve and nega�ve features.…”

Section: Introductionmentioning

confidence: 99%

The Method of Preprocessing of ECG Signals for Detection of Atrial and Ventricular Late Potentials

Mnevets

Ivanushkina

2023

Microsyst., Electron. & Acoust.

View full text Add to dashboard Cite

show abstract

“…A maximum sensitivity, specificity, and accuracy of about 94.04%, 99.71%, and 98.82%, respectively, at a rate of AQRS/AVLP equal to 20 dB was achieved. In Reference 22, 15 lead HR‐ECG signals was filtered and denoised for the improvement of signal‐to‐noise ratio. Five features were extracted and used as inputs of a classifier based on a machine learning approach.…”

Section: Introductionmentioning

confidence: 99%

An efficient machine learning based ventricular late potential detection and classification technique for cardiac healthcare

Lilda¹,

Jayaparvathy²,

Balaji

2022

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARY Cardiovascular diseases (CVD) are a major cause of death worldwide each year, with myocardial infarction (MI) accounting for the highest percentage of deaths. The rate of mortality can be reduced if electrical homogeneity of the cardiac tissue is detected early. The presence of the ventricular late potential (VLP) at the conclusion of the QRS complex and the start of the ST segment of the electrocardiogram (ECG) signal indicates a violation. Existing research use a wavelet‐based decomposition of the ECG signal for VLP detection, which is a multistage process. The use of empirical mode decomposition (EMD) to automatically distinguish normal ECG signal and signal with the presence of VLP is proposed in this work. Furthermore, utilizing machine learning classifiers, this research aims to enable automated diagnosis of cardiac arrhythmia. Intrinsic mode functions (IMF) are amplitude and frequency modulated waves that result from the decomposition of ECG using the EMD. Each IMF's peak amplitudes, spectral entropy, and mean of the ECG in the EMD are retrieved and used as input features for various machine learning techniques (ML). According to simulation findings, the bagging classifier achieves accuracy and specificity of 98.93% and 98.62%, respectively, while the AdaBoost classifier based on machine learning technique achieves sensitivity of 99.84%. The observed performance is considered to be the best when compared to existing approaches.

show abstract

Arrhythmogenic sites identification in post-ischemic ventricular tachycardia electrophysiological studies by explainable deep learning

Pitzus,

Baldazzi,

Orrù

et al. 2025

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Detection of Ventricular Late Potentials in Electrocardiograms Using Machine Learning

Cited by 4 publications

References 10 publications

The Method of Preprocessing of ECG Signals for Detection of Atrial and Ventricular Late Potentials

The Method of Preprocessing of ECG Signals for Detection of Atrial and Ventricular Late Potentials

An efficient machine learning based ventricular late potential detection and classification technique for cardiac healthcare

Arrhythmogenic sites identification in post-ischemic ventricular tachycardia electrophysiological studies by explainable deep learning

Contact Info

Product

Resources

About