[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125558-en":3,"doc-seo-125558-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125558,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Machine Learning approach for TWA detection relying on ensemble data design - Research article","T-wave alternans (TWA) represents beat-to-beat fluctuations in the ST–T complex of surface electrocardiograms and is clinically useful for sudden cardiac death risk stratification. A gold standard for benchmarking detection methods remains unavailable, limiting algorithm development. The study proposes a machine-learning framework for TWA detection and provides an experimental setup for method benchmarking. It uses open-source databases, real ECG signals with added TWA episodes, and controls intra-patient overfitting and class imbalance.","Heliyon 9 (2023) e12947  \nContents lists available at ScienceDirect  \nHeliyon  \n[journal homepage:](journal homepage: www.cell.com/heliyon)[ www.cell.com/heliyon](journal homepage: www.cell.com/heliyon)  \n| Research article\u003Cbr>Machine Learning approach for TWA detection relying on ensemble data design |  |  |\n| --- | --- | --- |\n| Miriam Gutiérrez Fernández–Calvillo a, Rebeca Goya–Esteban b,\u003Cbr>Fernando Cruz–Roldán a, Antonio Hernández–Madrid c, Manuel Blanco–Velasco a,∗\u003Cbr>a Department of Teoría de la Señal y Comunicaciones, Universidad de Alcalá, Madrid, Spain b Department of Teoría de la Señal y Comunicaciones, Universidad Rey Juan Carlos, Madrid, Spain c Arrhythmia Unit, Ramón y Cajal Hospital, Universidad de Alcalá, Madrid, Spain |  |  |\n| A R T I C L E I N F O\u003Cbr>Keywords:\u003Cbr>Machine Learning (ML)\u003Cbr>Spectral Method (SM)\u003Cbr>Modified Moving Average Method (MMA) Time Method (TM)\u003Cbr>Cross Validation (CV) Repolarization\u003Cbr>T–Wave Alternans (TWA)\u003Cbr>Electrocardiogram (ECG) | A B S T R A C T\u003Cbr>Background and objective: T-wave alternans (TWA) is a fluctuation of the ST–T complex of the surface electrocardiogram (ECG) on an every–other–beat basis. It has been shown to be clinically helpful for sudden cardiac death stratification, though the lack of a gold standard to benchmark detection methods limits its application and impairs the development of alternative techniques. In this work, a novel approach based on machine learning for TWA detection is proposed. Additionally, a complete experimental setup is presented for TWA detection methods benchmarking.\u003Cbr>Methods: The proposed experimental setup is based on the use of open-source databases to enable experiment replication and the use of real ECG signals with added TWA episodes. Also, intra-patient overfitting and class imbalance have been carefully avoided. The Spectral Method (SM), the Modified Moving Average Method (MMA), and the Time Domain Method (TM) are used to obtain input features to the Machine Learning (ML) algorithms, namely, K Nearest Neighbor, Decision Trees, Random Forest, Support Vector Machine and Multi-Layer Perceptron.\u003Cbr>Results: There were not found large differences in the performance of the different ML algorithms. Decision Trees showed the best overall performance (accuracy 0.88 ±0 .04, precision 0.89 ±0 .05, Recall 0.90 ±0 .05, F1 score 0 . 89 ±0 .03). Compared to the SM (accuracy 0.79, precision 0.93, Recall 0.64, F1 score 0.76) there was an improvement in every metric except for the precision. Conclusions: In this work, a realistic database to test the presence of TWA using ML algorithms was assembled. The ML algorithms overall outperformed the SM used as a gold standard. Learning from data to identify alternans elicits a substantial detection growth at the expense of a small increment of the false alarm. |  |\n\n1. Introduction  \nT–wave alternans (TWA) is a beat-to-beat fluctuation in the repolarization morphology of the electrocardiogram (ECG). It can be manifested as a variation in the amplitude, duration, or waveform of the ST–T complex. Several studies relate cardiac risk and  \n* Corresponding author.  \nE-mail addresses: miriam.gutierrez@urjc.es (M.G. Fernández–Calvillo), rebeca.goyaesteban@urjc.es (R. Goya–Esteban), [fernando.cruz@uah.es](fernando.cruz@uah.es) (F. Cruz–Roldán), [antonio.hernandez@uah.es](antonio.hernandez@uah.es) (A. Hernández–Madrid), [manuel.blanco@uah.es](manuel.blanco@uah.es) (M. Blanco–Velasco).  \n[https://doi.org/10.1016/j.heliyon.2023.e12947](https://doi.org/10.1016/j.heliyon.2023.e12947)  \nReceived 23 November 2022; Received in revised form 23 December 2022; Accepted 10 January 2023 Available online 16 January 2023  \n2405-8440/© 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license ([http://creativecommons.org/licenses/by-nc-nd/4.0/](http://creativecommons.org/licenses/by-nc-nd/4.0/)).  \nM.G. Fernández–Calvillo, R. Goya–Esteban, F. Cruz–Roldán et al. Heliyon 9 (2023) e12947  \nin","cbCaikc7mwLfTjc5","https://ap.wps.com/l/cbCaikc7mwLfTjc5","pdf",909385,1,13,"English","en",105,"# Introduction\n## TWA detection background and existing methods\n# Machine Learning approach and experimental setup\n## Feature extraction with SM, MMA, and TM\n## Classifiers used (KNN, DT, Random Forest, SVM, MLP)\n# Results\n## Overall comparison of ML models\n## Performance vs. Spectral Method\n# Conclusions","[{\"question\":\"What problem does the document address for TWA detection?\",\"answer\":\"It addresses the lack of a clinical gold standard for benchmarking T-wave alternans detection methods, which hinders comparison and development of alternative techniques.\"},{\"question\":\"How is the proposed machine-learning approach constructed?\",\"answer\":\"An experimental setup uses open-source databases and real ECG signals with added TWA episodes. Features are extracted using the Spectral Method, Modified Moving Average Method, and Time Domain Method, then fed into multiple ML classifiers.\"},{\"question\":\"Which classifier shows the best overall performance and how does it compare with the Spectral Method?\",\"answer\":\"Decision Trees achieve the best overall performance with accuracy 0.88 ± 0.04, precision 0.89 ± 0.05, recall 0.90 ± 0.05, and F1 0.89 ± 0.03. Compared with the Spectral Method, it improves every metric except precision.\"}]","Machine Learning approach for TWA detection relying on ensemble data design - Research article | PDF",1785899854,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-approach-for-twa-detection-relying-on-ensemble-data-design-research-article","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-approach-for-twa-detection-relying-on-ensemble-data-design-research-article/125558/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the document address for TWA detection?","Question",{"text":75,"@type":76},"It addresses the lack of a clinical gold standard for benchmarking T-wave alternans detection methods, which hinders comparison and development of alternative techniques.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the proposed machine-learning approach constructed?",{"text":80,"@type":76},"An experimental setup uses open-source databases and real ECG signals with added TWA episodes. Features are extracted using the Spectral Method, Modified Moving Average Method, and Time Domain Method, then fed into multiple ML classifiers.",{"name":82,"@type":73,"acceptedAnswer":83},"Which classifier shows the best overall performance and how does it compare with the Spectral Method?",{"text":84,"@type":76},"Decision Trees achieve the best overall performance with accuracy 0.88 ± 0.04, precision 0.89 ± 0.05, recall 0.90 ± 0.05, and F1 0.89 ± 0.03. Compared with the Spectral Method, it improves every metric except precision.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]