{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T23:25:31Z","timestamp":1783553131680,"version":"3.55.0"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:p>According to the World Health Organization, cardiovascular diseases (CVDs) account for an estimated 17.9 million deaths annually. CVDs refer to disorders of the heart and blood vessels such as arrhythmia, atrial fibrillation, congestive heart failure, and normal sinus rhythm. Early prediction of these diseases can significantly reduce the number of annual deaths. This study proposes a novel, efficient, and low-cost transformer-based algorithm for CVD classification. Initially, 56 features were extracted from electrocardiography recordings using 1,200 cardiac ailment records, with each of the four diseases represented by 300 records. Then, random forest was used to select the 13 most prominent features. Finally, a novel transformer-based algorithm has been developed to classify four classes of cardiovascular diseases. The proposed study achieved a maximum accuracy, precision, recall, and F1 score of 0.9979, 0.9959, 0.9958, and 0.9959, respectively. The proposed algorithm outperformed all the existing state-of-the-art algorithms for CVD classification.<\/jats:p>","DOI":"10.3389\/fdgth.2025.1548448","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T05:24:34Z","timestamp":1745904274000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["A novel transformer-based approach for cardiovascular disease detection"],"prefix":"10.3389","volume":"7","author":[{"given":"Nimra","family":"Noor","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Bilal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saadullah Farooq","family":"Abbasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omid","family":"Pournik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodoros N.","family":"Arvanitis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/technologies9030052","article-title":"Effect of data scaling methods on machine learning algorithms and model performance","volume":"9","author":"Ahsan","year":"2021","journal-title":"Technologies"},{"key":"B2","doi-asserted-by":"publisher","first-page":"17574","DOI":"10.1038\/s41598-023-44763-7","article-title":"Detection and classification of adult epilepsy using hybrid deep learning approach","volume":"13","author":"Srinivasan","year":"2023","journal-title":"Sci Rep"},{"key":"B3","doi-asserted-by":"publisher","first-page":"104738","DOI":"10.1016\/j.bspc.2023.104738","article-title":"Pre-processed and combined EEG data for epileptic seizure classification using deep learning","volume":"84","author":"Zaid","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"B4","doi-asserted-by":"publisher","first-page":"183025","DOI":"10.1109\/ACCESS.2020.3028182","article-title":"EEG-based neonatal sleep-wake classification using multilayer perceptron neural network","volume":"8","author":"Abbasi","year":"2020","journal-title":"IEEE Access"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e22195","DOI":"10.1016\/j.heliyon.2023.e22195","article-title":"Automatic neonatal sleep stage classification: a comparative study","volume":"9","author":"Abbasi","year":"2023","journal-title":"Heliyon"},{"key":"B6","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1109\/TAI.2022.3159505","article-title":"Detection of cardiovascular diseases in ECG images using machine learning and deep learning methods","volume":"4","author":"Abubaker","year":"2022","journal-title":"IEEE Trans Artif Intell"},{"key":"B7","doi-asserted-by":"publisher","first-page":"104796","DOI":"10.1016\/j.bspc.2023.104796","article-title":"Heart disease classification based on ECG using machine learning models","volume":"84","author":"Malakouti","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"B8","doi-asserted-by":"publisher","first-page":"100093","DOI":"10.1016\/j.cmpbup.2023.100093","article-title":"Multi-lead ECG heartbeat classification of heart disease based on HOG local feature descriptor","volume":"3","author":"Goharrizi","year":"2023","journal-title":"Comput Methods Programs Biomed Update"},{"key":"B9","doi-asserted-by":"publisher","first-page":"22588","DOI":"10.1038\/s41598-023-49962-w","article-title":"Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction","volume":"13","author":"Noroozi","year":"2023","journal-title":"Sci Rep"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-021-01736-y","article-title":"ECG signal classification based on deep CNN and BILSTM","volume":"21","author":"Cheng","year":"2021","journal-title":"BMC Med Inf Decis Mak"},{"key":"B11","doi-asserted-by":"publisher","first-page":"104531","DOI":"10.1016\/j.bspc.2022.104531","article-title":"Atrial fibrillation classification and detection from ECG recordings","volume":"82","author":"G\u00fcnd\u00fcz","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"B12","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.compbiomed.2017.08.022","article-title":"A deep convolutional neural network model to classify heartbeats","volume":"89","author":"Acharya","year":"2017","journal-title":"Comput Biol Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"105420","DOI":"10.1016\/j.bspc.2023.105420","article-title":"Classification of cardiac disorders using weighted visibility graph features from ECG signals","volume":"87","author":"Kutluana","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"B14","volume-title":"Cardiovascular Physiology Concepts","author":"Klabunde","year":"2011"},{"key":"B15","volume-title":"Medical Physiology: A Cellular and Molecular Approach","author":"Boron","year":"2003"},{"key":"B16","doi-asserted-by":"publisher","first-page":"6000","DOI":"10.5555\/3295222.3295349","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1002\/grl.50288","article-title":"GPT2: empirical slant delay model for radio space geodetic techniques","volume":"40","author":"Lagler","year":"2013","journal-title":"Geophys Res Lett"},{"key":"B18","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","article-title":"GPT-3: its nature, scope, limits, and consequences","volume":"30","author":"Floridi","year":"2020","journal-title":"Minds Mach"},{"key":"B19","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":""},{"key":"B20","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1038\/s41467-020-17591-w","article-title":"Earthquake transformer\u2014an attentive deep-learning model for simultaneous earthquake detection and phase picking","volume":"11","author":"Mousavi","year":"2020","journal-title":"Nat Commun"},{"key":"B21","doi-asserted-by":"publisher","first-page":"118128","DOI":"10.1016\/j.eswa.2022.118128","article-title":"Stock market index prediction using deep transformer model","volume":"208","author":"Wang","year":"2022","journal-title":"Expert Syst Appl"},{"key":"B22","doi-asserted-by":"publisher","first-page":"113913","DOI":"10.1016\/j.rser.2023.113913","article-title":"Deep learning based on transformer architecture for power system short-term voltage stability assessment with class imbalance","volume":"189","author":"Li","year":"2024","journal-title":"Renew Sustain Energy Rev"},{"key":"B23","doi-asserted-by":"publisher","first-page":"105130","DOI":"10.1016\/j.bspc.2023.105130","article-title":"Classification of EEG signals using transformer based deep learning and ensemble models","volume":"86","author":"Zeynali","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3193169","article-title":"A hybrid transformer model for obstructive sleep apnea detection based on self-attention mechanism using single-lead ECG","volume":"71","author":"Hu","year":"2022","journal-title":"IEEE Trans Instrum Meas"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.1109\/TNSRE.2023.3244045","article-title":"Exploring the applicability of transfer learning and feature engineering in epilepsy prediction using hybrid transformer model","volume":"31","author":"Hu","year":"2023","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"B26","first-page":"1","article-title":"Personalized transfer learning for single-lead ECG-based sleep apnea detection: exploring the label mapping length and transfer strategy using hybrid transformer model","volume":"72","author":"Hu","year":"2023","journal-title":"IEEE Trans Instrum Meas"},{"key":"B27","doi-asserted-by":"publisher","first-page":"5281","DOI":"10.1109\/JBHI.2023.3304299","article-title":"Semi-supervised learning for low-cost personalized obstructive sleep apnea detection using unsupervised deep learning and single-lead electrocardiogram","volume":"27","author":"Hu","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"key":"B28","doi-asserted-by":"publisher","first-page":"106836","DOI":"10.1016\/j.neunet.2024.106836","article-title":"IPCT-Net: parallel information bottleneck modality fusion network for obstructive sleep apnea diagnosis","volume":"181","author":"Hu","year":"2025","journal-title":"Neural Netw"},{"key":"B29","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1016\/j.future.2019.03.025","article-title":"A novel electrocardiogram feature extraction approach for cardiac arrhythmia classification","volume":"97","author":"Marinho","year":"2019","journal-title":"Future Gener Comput Syst"},{"key":"B30","doi-asserted-by":"publisher","first-page":"8361","DOI":"10.1016\/j.eswa.2015.06.046","article-title":"A novel technique for cardiac arrhythmia classification using spectral correlation and support vector machines","volume":"42","author":"Khalaf","year":"2015","journal-title":"Expert Syst Appl"},{"key":"B31","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1016\/j.aeue.2014.12.013","article-title":"Automatic ECG arrhythmia classification using dual tree complex wavelet-based features","volume":"69","author":"Thomas","year":"2015","journal-title":"AEU Int J Electron Commun"},{"key":"B32","first-page":"7594","article-title":"Effective ECG beat classification using higher order statistic features and genetic feature selection","volume":"28","author":"Kaya","year":"2017","journal-title":"Biomed Res"},{"key":"B33","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1109\/JBHI.2014.2332001","article-title":"Electrocardiogram classification using reservoir computing with logistic regression","volume":"19","author":"Escalona-Mor\u00e1n","year":"2015","journal-title":"IEEE J Biomed Health Inform"},{"key":"B34","doi-asserted-by":"crossref","DOI":"10.22489\/CinC.2017.175-021","article-title":"Multi-parametric analysis for atrial fibrillation classification in the ECG","author":"Christov","year":""},{"key":"B35","doi-asserted-by":"publisher","first-page":"118","DOI":"10.3390\/a12060118","article-title":"Deep learning with a recurrent network structure in the sequence modeling of imbalanced data for ECG-rhythm classifier","volume":"12","author":"Darmawahyuni","year":"2019","journal-title":"Algorithms"},{"key":"B36","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.compbiomed.2018.06.002","article-title":"Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats","volume":"102","author":"Oh","year":"2018","journal-title":"Comput Biol Med"},{"key":"B37","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-0716-1006-0_496","article-title":"PhysioNet","author":"Moody","year":"2022"},{"key":"B38","doi-asserted-by":"publisher","first-page":"2243","DOI":"10.1098\/rspa.1998.0257","article-title":"The phase\u2013corrected undecimated discrete wavelet packet transform and its application to interpreting the timing of events","volume":"454","author":"Walden","year":"1998","journal-title":"Proc R Soc London Ser A"},{"key":"B39","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1016\/j.patrec.2010.03.014","article-title":"Variable selection using random forests","volume":"31","author":"Genuer","year":"2010","journal-title":"Pattern Recognit Lett"},{"key":"B40","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B41","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1080\/10255842.2020.1821192","article-title":"Classification of normal sinus rhythm, abnormal arrhythmia and congestive heart failure ECG signals using LSTM and hybrid CNN-SVM deep neural networks","volume":"24","author":"\u00c7\u0131nar","year":"2021","journal-title":"Comput Methods Biomech Biomed Engin"},{"key":"B42","doi-asserted-by":"publisher","first-page":"77849","DOI":"10.1109\/ACCESS.2019.2920900","article-title":"Classification of atrial fibrillation recurrence based on a convolution neural network with SVM architecture","volume":"7","author":"Li","year":"2019","journal-title":"IEEE Access"},{"key":"B43","doi-asserted-by":"crossref","DOI":"10.1109\/IECBES.2018.8626624","article-title":"Classification of atrial fibrillation with pre-trained convolutional neural network models","author":"Qayyum","year":""},{"key":"B44","first-page":"13176","article-title":"A novel application for autonomous detection of cardiac ailments using ECG scalograms with Alex net convolution neural network","volume":"18","author":"Alekhya","year":"2021","journal-title":"Des Eng"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1548448\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T05:24:35Z","timestamp":1745904275000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1548448\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,29]]},"references-count":44,"alternative-id":["10.3389\/fdgth.2025.1548448"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2025.1548448","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,29]]},"article-number":"1548448"}}