{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:38:33Z","timestamp":1768343913470,"version":"3.49.0"},"reference-count":52,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"custo med GmbH"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate detection of premature atrial contractions (PACs) and premature ventricular contractions (PVCs) in single-lead electrocardiograms (ECGs) is crucial for early identification of patients at risk for atrial fibrillation, cardiomyopathy, and other adverse outcomes. In this work, we present a fully convolutional one-dimensional U-Net that reframes beat classification as a segmentation task and directly detects normal beats, PACs, and PVCs from raw ECG signals. The architecture employs a ConvNeXt V2 encoder with simple decoder blocks and does not rely on explicit R-peak detection, handcrafted features, or fixed-length input windows. The model is trained on the Icentia11k database and an in-house single-lead ECG dataset that emphasizes challenging, noisy recordings, and is validated on the CPSC2020 database. Generalization is assessed across several benchmark and clinical datasets, including MIT-BIH Arrhythmia (ADB), MIT 11, AHA, NST, SVDB, CST STRIPS, and CPSC2020. The proposed method achieves near-perfect QRS detection (sensitivity and precision up to 0.999) and competitive PVC performance, with sensitivity ranging from 0.820 (AHA) to 0.986 (MIT 11) and precision up to 0.993 (MIT 11). PAC detection is more variable, with sensitivities between 0.539 and 0.797 and precisions between 0.751 and 0.910, yet the resulting F1-score of 0.72 on SVDB exceeds that of previously published approaches. Model interpretability is addressed using Layer-wise Gradient-weighted Class Activation Mapping (LayerGradCAM), which confirms physiologically plausible attention to QRS complexes for PVCs and to P-waves for PACs. Overall, the proposed framework provides a robust, interpretable, and hardware-efficient solution for joint PAC and PVC detection in noisy, single-lead ECG recordings, suitable for integration into Holter and wearable monitoring systems.<\/jats:p>","DOI":"10.3390\/s26020513","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:17:32Z","timestamp":1768292252000},"page":"513","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Detection of Normal, Atrial, and Ventricular Premature Beats from Single-Lead ECG Using Convolutional Neural Networks"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0604-5854","authenticated-orcid":false,"given":"Dimitri","family":"Kraft","sequence":"first","affiliation":[{"name":"MedTec & Science GmbH, Maria-Merian-Stra\u00dfe 6, 85521 Ottobrunn, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Rumm","sequence":"additional","affiliation":[{"name":"custo med, GmbH, Maria-Merian-Stra\u00dfe 6, 85521 Ottobrunn, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1093\/cvr\/cvac054","article-title":"Frequent premature atrial contractions as a signalling marker of atrial cardiomyopathy, incident atrial fibrillation, and stroke","volume":"119","author":"Farinha","year":"2023","journal-title":"Cardiovasc. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1161\/CIRCULATIONAHA.119.040015","article-title":"Premature ventricular contractions: Not always innocent bystanders","volume":"140","author":"Gerstenfeld","year":"2019","journal-title":"Circulation"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Parreira, L., Marinheiro, R., Amador, P., Mesquita, D., Farinha, J., Lopes, A., Fonseca, M., Chambel, D., Venancio, J., and Lopes, C. (2021). Frequent premature ventricular contractions. Association of burden and complexity with prognosis according to the presence of structural heart disease. Ann. Noninvasive Electrocardiol., 26.","DOI":"10.1111\/anec.12800"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Navab, N., Hornegger, J., Wells, W.M., and Frangi, A.F. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI, Munich, Germany.","DOI":"10.1007\/978-3-319-24553-9"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TBME.2015.2468589","article-title":"Real-time patient-specific ECG classification by 1-D convolutional neural networks","volume":"63","author":"Kiranyaz","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1007\/s10586-019-02953-x","article-title":"Detection of premature ventricular contraction (PVC) using linear and nonlinear techniques: An experimental study","volume":"23","author":"Mazidi","year":"2020","journal-title":"Clust. Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1450723","DOI":"10.1155\/2022\/1450723","article-title":"Premature ventricular contraction recognition based on a deep learning approach","volume":"2022","author":"Sarshar","year":"2022","journal-title":"J. Healthc. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Kraft, D., Bieber, G., Jokisch, P., and Rumm, P. (2023). End-to-end premature ventricular contraction detection using deep neural networks. Sensors, 23.","DOI":"10.20944\/preprints202309.1588.v2"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"106006","DOI":"10.1016\/j.cmpb.2021.106006","article-title":"Automated ECG classification using a non-local convolutional block attention module","volume":"203","author":"Wang","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"102236","DOI":"10.1016\/j.artmed.2022.102236","article-title":"Enhancing dynamic ECG heartbeat classification with lightweight transformer model","volume":"124","author":"Meng","year":"2022","journal-title":"Artif. Intell. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"075003","DOI":"10.1088\/1361-6579\/ac0e82","article-title":"Premature beats detection based on a novel convolutional neural network","volume":"42","author":"Yang","year":"2021","journal-title":"Physiol. Meas."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-Isla, G., Mainardi, L., and Corino, V.D. (2021). A detector for premature atrial and ventricular complexes. Front. Physiol., 12.","DOI":"10.3389\/fphys.2021.678558"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1016\/j.jelectrocard.2014.07.022","article-title":"Normal values of the electrocardiogram for ages 16\u201390 years","volume":"47","author":"Rijnbeek","year":"2014","journal-title":"J. Electrocardiol."},{"key":"ref_14","first-page":"1565","article-title":"Sex differences in cardiac arrhythmia: A consensus document of the European Heart Rhythm Association, endorsed by the Heart Rhythm Society and Asia Pacific Heart Rhythm Society","volume":"20","author":"Linde","year":"2018","journal-title":"Ep Eur."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.artmed.2017.06.004","article-title":"Premature ventricular contraction detection combining deep neural networks and rules inference","volume":"79","author":"Zhou","year":"2017","journal-title":"Artif. Intell. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1016\/j.hrthm.2020.02.015","article-title":"Deep learning for comprehensive ECG annotation","volume":"17","author":"Teplitzky","year":"2020","journal-title":"Heart Rhythm"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/TBME.1985.325532","article-title":"A real-time QRS detection algorithm","volume":"32","author":"Pan","year":"1985","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/1475-925X-3-28","article-title":"Real time electrocardiogram QRS detection using combined adaptive threshold","volume":"3","author":"Christov","year":"2004","journal-title":"Biomed. Eng. Online"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chiarugi, F., Sakkalis, V., Emmanouilidou, D., Krontiris, T., Varanini, M., and Tollis, I. (October, January 30). Adaptive threshold QRS detector with best channel selection based on a noise rating system. Proceedings of the 2007 Computers in Cardiology, Durham, NC, USA.","DOI":"10.1109\/CIC.2007.4745445"},{"key":"ref_20","first-page":"9508","article-title":"QRS complex detection based on multi wavelet packet decomposition","volume":"217","author":"Chouakri","year":"2011","journal-title":"Appl. Math. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Elgendi, M. (2013). Fast QRS detection with an optimized knowledge-based method: Evaluation on 11 standard ECG databases. PloS ONE, 8.","DOI":"10.1371\/journal.pone.0073557"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Q., He, R., Wang, K., Liu, J., Yuan, Y., Xia, Y., and Zhang, H. (2022). Generalizable beat-by-beat arrhythmia detection by using weakly supervised deep learning. Front. Physiol., 13.","DOI":"10.3389\/fphys.2022.850951"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1109\/JBHI.2020.3018563","article-title":"Automatic Detection of QRS Complexes Using Dual Channels Based on U-Net and Bidirectional Long Short-Term Memory","volume":"25","author":"He","year":"2021","journal-title":"IEEE J. Biomed. Health Inform. s"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1109\/TBME.2003.821031","article-title":"A wavelet-based ECG delineator: Evaluation on standard databases","volume":"51","author":"Almeida","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TBME.2007.912658","article-title":"Analysis of First-Derivative Based QRS Detection Algorithms","volume":"55","author":"Arzeno","year":"2008","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.cmpb.2011.12.004","article-title":"QRS detection based on wavelet coefficients","volume":"107","author":"Zidelmal","year":"2012","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1109\/TBME.2004.827359","article-title":"Automatic classification of heartbeats using ECG morphology and heartbeat interval features","volume":"51","author":"Reilly","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1750","DOI":"10.1109\/TNN.2007.900239","article-title":"Block-based neural networks for personalized ECG signal classification","volume":"18","author":"Jiang","year":"2007","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1109\/TBME.2009.2013934","article-title":"A generic and robust system for automated patient-specific classification of ECG signals","volume":"56","author":"Ince","year":"2009","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, C., Wang, G., Zhao, J., Gao, P., Lin, J., and Yang, H. (2017, January 20\u201321). Patient-specific ECG classification based on recurrent neural networks and clustering technique. Proceedings of the 2017 13th IASTED International Conference on Biomedical Engineering (BioMed), Innsbruck, Austria.","DOI":"10.2316\/P.2017.852-029"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Cai, Z., Wang, T., Shen, Y., Xing, Y., Yan, R., Li, J., and Liu, C. (2022). Robust PVC identification by fusing expert system and deep learning. Biosensors, 12.","DOI":"10.20944\/preprints202203.0054.v1"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1109\/TBME.2010.2068048","article-title":"Heartbeat classification using feature selection driven by database generalization criteria","volume":"58","author":"Llamedo","year":"2010","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2312","DOI":"10.1109\/TBME.2012.2202662","article-title":"An automatic patient-adapted ECG heartbeat classifier allowing expert assistance","volume":"59","author":"Llamedo","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., and Xie, S. (2023, January 18\u201322). Convnext v2: Co-designing and scaling convnets with masked autoencoders. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref_35","unstructured":"Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer normalization. arXiv."},{"key":"ref_36","unstructured":"Maas, A.L., Hannun, A.Y., and Ng, A.Y. (2013, January 16\u201321). Rectifier nonlinearities improve neural network acoustic models. Proceedings of the 30th International Conference on Machine Learning, Atlanta, GA, USA."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"101788","DOI":"10.1016\/j.artmed.2019.101788","article-title":"An intelligent learning approach for improving ECG signal classification and arrhythmia analysis","volume":"103","author":"Sangaiah","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., and Ahmadi, S.A. (2016, January 25\u201328). V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"ref_39","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv.","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (2019, January 27\u201328). Cutmix: Regularization strategy to train strong classifiers with localizable features. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref_42","unstructured":"Raghu, A., Shanmugam, D., Pomerantsev, E., Guttag, J., and Stultz, C.M. (2022, January 7\u20138). Data augmentation for electrocardiograms. Proceedings of the Conference on Health, Inference, and Learning, PMLR, Virtual."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Rivolta, M.W., Badilini, F., and Sassi, R. (2023). A Systematic Survey of Data Augmentation of ECG Signals for AI Applications. Sensors, 23.","DOI":"10.3390\/s23115237"},{"key":"ref_44","unstructured":"Tan, S., Androz, G., Chamseddine, A., Fecteau, P., Courville, A., Bengio, Y., and Cohen, J.P. (2019). Icentia11k: An unsupervised representation learning dataset for arrhythmia subtype discovery. arXiv."},{"key":"ref_45","first-page":"2663","article-title":"An open-access long-term wearable ECG database for premature ventricular contractions and supraventricular premature beat detection","volume":"10","author":"Cai","year":"2020","journal-title":"J. Med. Imaging Health Inform."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/51.932724","article-title":"The impact of the MIT-BIH Arrhythmia Database","volume":"20","author":"Moody","year":"2001","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"ref_47","first-page":"381","article-title":"A noise stress test for arrhythmia detectors","volume":"11","author":"Moody","year":"1984","journal-title":"Comput. Cardiol."},{"key":"ref_48","unstructured":"(1998). Ambulatory Electrocardiographs (Standard No. ANSI\/AAMI EC38:1998)."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization","volume":"128","author":"Selvaraju","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"ref_50","unstructured":"Sundararajan, M., Taly, A., and Yan, Q. (2017, January 6\u201311). Axiomatic attribution for deep networks. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, Australia."},{"key":"ref_51","unstructured":"Shrikumar, A., Greenside, P., and Kundaje, A. (2017, January 6\u201311). Learning important features through propagating activation differences. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, Australia."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"106211","DOI":"10.1016\/j.bspc.2024.106211","article-title":"CAT-Net: Convolution, attention, and transformer based network for single-lead ECG arrhythmia classification","volume":"93","author":"Islam","year":"2024","journal-title":"Biomed. Signal Process. Control"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/513\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:54:56Z","timestamp":1768319696000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":52,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26020513"],"URL":"https:\/\/doi.org\/10.3390\/s26020513","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]}}}