Machine learning based detection of T-wave alternans in real ambulatory conditions
Authors
Pascual Sánchez, Lidia; Goya Esteban, Rebeca; Cruz Roldán, Fernando; Hernández Madrid, Antonio; Blanco Velasco, ManuelIdentifiers
Permanent link (URI): http://hdl.handle.net/10017/61283DOI: 10.1016/j.cmpb.2024.108157
ISSN: 0169-2607
Publisher
Elsevier
Date
2024-04-03Funders
Universidad de Alcalá
Agencia Estatal de Investigación
Bibliographic citation
Pascual Sánchez, L., Goya Esteban, R., Cruz Roldán, F., Hernández Madrid, A. & Blanco Velasco, M. 2024, "Machine learning based detection of T-wave alternans in real ambulatory conditions", Computer Methods and Programs in Biomedicine, vol. 249, art. no. 108157, pp. 1-10.
Keywords
Machine learning (ML)
Spectral method (SM)
Modified moving average method (MMA)
Time method (TM)
Cross validation (CV)
RepolarizationT-wave alternans (TWA)
Electrocardiogram (ECG)
Project
info:eu-repo/grantAgreement/UAH//EPU-INV%2F2020%2F002
info:eu-repo/grantAgreement/UAH//PIUAH23%2FIA-014
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2022-140786NB-C32/ES/DISEÑO DE UN PATRON ORO Y METODOS INTERPRETABLES BASADOS APRENDIZAJE AUTOMATICO PARA LA CARACTERIZACION ALTERNANCIAS DE LA ONDA T EN REGISTROS AMBULATORIOS/
Document type
info:eu-repo/semantics/article
Version
info:eu-repo/semantics/publishedVersion
Publisher's version
https://doi.org/10.1016/j.cmpb.2024.108157Rights
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
© 2024 The authors
Access rights
info:eu-repo/semantics/openAccess
Abstract
Background and objective
T-wave alternans (TWA) is a fluctuation in the repolarization morphology of the ECG. It is associated with cardiac instability and sudden cardiac death risk. Diverse methods have been proposed for TWA analysis. However, TWA detection in ambulatory settings remains a challenge due to the absence of standardized evaluation metrics and detection thresholds.
Methods
In this work we use traditional TWA analysis signal processing-based methods for feature extraction, and two machine learning (ML) methods, namely, K–nearest–neighbor (KNN) and random forest (RF), for TWA detection, addressing hyper–parameter tuning and feature selection. The final goal is the detection in ambulatory recordings of short, non-sustained and sparse TWA events.
Results
We train ML methods to detect a wide variety of alternant voltage from 20 to 100 μV, i.e., ranging from non–visible micro–alternans to TWA of higher amplitudes, to recognize a wide range in concordance to risk stratification. In classification, RF outperforms significantly the recall in comparison with the signal processing methods, at the expense of a small lost in precision. Despite ambulatory detection stands for an imbalanced category context, the trained ML systems always outperform signal processing methods.
Conclusions
We propose a comprehensive integration of multiple variables inspired by TWA signal processing methods to fed learning-based methods. ML models consistently outperform the best signal processing methods, yielding superior recall scores.
Files in this item
Files | Size | Format |
|
---|---|---|---|
Machine_Pascual_Comput_Methods ... | 1.285Mb |
|
Files | Size | Format |
|
---|---|---|---|
Machine_Pascual_Comput_Methods ... | 1.285Mb |
|
Collections
- TSENCOM - Artículos [58]