{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T19:01:53Z","timestamp":1791226913265,"version":"4.1.0"},"reference-count":19,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"40","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"the Key Program of Natural Science Research of Anhui Provincial Department of Education","award":["KJ2021A1564"],"award-info":[{"award-number":["KJ2021A1564"]}]},{"name":"the Domestic Visiting and Research Program for Excellent Young Teachers in Universities","award":["gxgnfx2022211"],"award-info":[{"award-number":["gxgnfx2022211"]}]},{"name":"the Key Project for the Cultivation of Excellent Young Teachers by Anhui Provincial Department of Education","award":["YQZD2024099"],"award-info":[{"award-number":["YQZD2024099"]}]}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,3]]},"abstract":"<jats:p>Accurate R-peak detection in electrocardiogram (ECG) signals represents a fundamental prerequisite for cardiac rhythm analysis and arrhythmia diagnosis. Traditional signal processing approaches demonstrate limited robustness when confronted with noise artifacts, baseline drift, and morphological variations commonly encountered in clinical recordings. This study introduces a novel deep residual U-Net (ResU-Net) architecture specifically designed for robust R-peak detection in noisy ECG signals, addressing the critical challenge of maintaining high detection accuracy across diverse noise conditions and patient populations. We developed an innovative deep learning framework combining the strengths of residual networks and U-Net architecture for precise R-peak localization. The proposed ResU-Net model incorporates skip connections, multi-scale feature extraction, and attention mechanisms to enhance feature representation. The architecture was trained and evaluated using the Massachusetts Institute of Technology\u2013Beth Israel Hospital (MIT\u2013BIH) arrhythmia database, INCART database, and QT database, with comprehensive noise stress testing performed using the MIT\u2013BIH noise stress test database. Data augmentation strategies including synthetic noise injection and morphological variations were employed to enhance model generalization. The ResU-Net architecture achieved superior performance compared to traditional signal processing methods (Pan\u2013Tompkins, Hamilton\u2013Tompkins algorithms) and state-of-the-art deep learning approaches (1D convolutional neural network (CNN), long short-term memory (LSTM)-CNN, ResNet-18) with sensitivity of 99.76%, positive predictive value of 99.82%, and F1-score of 99.79% on the MIT\u2013BIH arrhythmia database. Cross-database validation demonstrated exceptional generalization capabilities with sensitivity values of 99.45% (INCART) and 99.38% (QT database). Under severe noise conditions (\u22126 dB signal-to-noise ratio), the model maintained sensitivity above 98.2%, significantly outperforming conventional algorithms and state-of-the-art deep learning approaches. The proposed deep ResU-Net architecture establishes a new benchmark for robust R-peak detection in noisy ECG signals. The integration of residual connections with U-Net\u2019s encoder-decoder structure enables superior feature learning and noise resilience, providing a reliable foundation for automated cardiac rhythm analysis in clinical applications.<\/jats:p>","DOI":"10.1097\/md.0000000000044968","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T20:05:41Z","timestamp":1759781141000},"page":"e44968","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":6,"title":["Robust R-peak detection in noisy ECG using deep residual U-Net for enhanced cardiac rhythm analysis"],"prefix":"10.1097","volume":"104","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0251-2347","authenticated-orcid":false,"given":"Wang","family":"Chaoya","sequence":"first","affiliation":[{"name":"Experimental Training Center, Anhui Health College, Chizhou, Anhui Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8405-6100","authenticated-orcid":false,"given":"Pan","family":"Chun","sequence":"additional","affiliation":[{"name":"Department of Medicine, Anhui Health College, Chizhou, Anhui Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9070-9846","authenticated-orcid":false,"given":"Meng","family":"Chao","sequence":"additional","affiliation":[{"name":"Orthopedics Department, The Second People\u2019s Hospital of Anhui Province, Hefei, Anhui Province, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R2-20260526","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1038\/s41467-020-15432-4","article-title":"Automatic diagnosis of the 12-lead ECG using a deep neural network.","volume":"11","author":"Ribeiro","year":"2020","journal-title":"Nat Commun"},{"key":"R3-20260526","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":"R4-20260526","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/10.362922","article-title":"Detection of ECG characteristic points using wavelet transforms.","volume":"42","author":"Li","year":"1995","journal-title":"IEEE Trans Biomed Eng"},{"key":"R5-20260526","doi-asserted-by":"crossref","first-page":"2014","DOI":"10.1109\/TBME.2024.3359752","article-title":"The deep-match framework: R-peak detection in ear-ECG.","volume":"71","author":"Davies","year":"2024","journal-title":"IEEE Trans Biomed Eng"},{"key":"R6-20260526","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/0010-4809(77)90021-0","article-title":"Electrocardiogram baseline noise estimation and removal using cubic splines and state-space computation techniques.","volume":"10","author":"Meyer","year":"1977","journal-title":"Computers Biomed Res"},{"key":"R7-20260526","doi-asserted-by":"crossref","first-page":"2288","DOI":"10.3390\/s23042288","article-title":"A deep learning architecture using 3D vectorcardiogram to detect R-peaks in ECG with enhanced precision.","volume":"23","author":"Mehri","year":"2023","journal-title":"Sensors (Basel, Switzerland)"},{"key":"R8-20260526","doi-asserted-by":"crossref","first-page":"e38454","DOI":"10.2196\/38454","article-title":"State-of-the-art deep learning methods on electrocardiogram data: systematic review.","volume":"10","author":"Petmezas","year":"2022","journal-title":"JMIR Med Informatics"},{"key":"R11-20260526","doi-asserted-by":"crossref","first-page":"106262","DOI":"10.1016\/j.bspc.2024.106262","article-title":"A novel hybrid GRU-CNN and residual bias (RB) based RB-GRU-CNN models for prediction of PTB diagnostic ECG time series data.","volume":"94","author":"Khan","year":"2024","journal-title":"Biomed Signal Proc Control"},{"key":"R12-20260526","doi-asserted-by":"crossref","first-page":"1246746","DOI":"10.3389\/fphys.2023.1246746","article-title":"Deep learning for ECG arrhythmia detection and classification: an overview of progress for period 2017\u20132023.","volume":"14","author":"Ansari","year":"2023","journal-title":"Front Physiol"},{"key":"R13-20260526","doi-asserted-by":"crossref","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 Inform Decis Mak"},{"key":"R14-20260526","doi-asserted-by":"crossref","first-page":"19638","DOI":"10.1038\/s41598-022-19495-9","article-title":"Robust R-peak detection in an electrocardiogram with stationary wavelet transformation and separable convolution.","volume":"12","author":"Yun","year":"2022","journal-title":"Sci Rep"},{"key":"R15-20260526","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1109\/TBME.2021.3088218","article-title":"Robust R-peak detection in low-quality Holter ECGs using 1D convolutional neural network.","volume":"69","author":"Zahid","year":"2022","journal-title":"IEEE Trans Biomed Eng"},{"key":"R17-20260526","doi-asserted-by":"crossref","first-page":"1322334","DOI":"10.3389\/frsip.2024.1322334","article-title":"Comparative study of time-frequency transformation methods for ECG signal classification.","volume":"4","author":"Song","year":"2024","journal-title":"Front Signal Processing"},{"key":"R18-20260526","doi-asserted-by":"crossref","first-page":"106582","DOI":"10.1016\/j.cmpb.2021.106582","article-title":"Inter-patient arrhythmia classification with improved deep residual convolutional neural network.","volume":"214","author":"Li","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"R19-20260526","doi-asserted-by":"crossref","first-page":"87","DOI":"10.3109\/03091900903336886","article-title":"Noise and baseline wandering suppression of ECG signals by morphological filter.","volume":"34","author":"Taouli","year":"2010","journal-title":"J Med Engineering Technol"},{"key":"R20-20260526","doi-asserted-by":"crossref","first-page":"281","DOI":"10.3390\/electronics14020281","article-title":"Exercise ECG classification based on novel R-Peak detection using BILSTM-CNN and multi-feature fusion method.","volume":"14","author":"Su","year":"2025","journal-title":"Electronics"},{"key":"R21-20260526","doi-asserted-by":"crossref","first-page":"e143437","DOI":"10.5812\/intjcardiovascpract-143437","article-title":"Advancements in artificial intelligence for ECG signal analysis and arrhythmia detection: a review.","volume":"8","author":"Kazemi Lichaee","year":"2024","journal-title":"Int J Cardiovasc Pract"},{"key":"R23-20260526","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1080\/01969722.2025.2459959","article-title":"Heart disease detection and prognosis using IoT-based ECG sensor data with hybrid deep learning architecture.","volume":"56","author":"Lokhande","year":"2025","journal-title":"Cybern Syst"},{"key":"R24-20260526","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1038\/s41591-018-0240-2","article-title":"Screening for cardiac contractile dysfunction using an artificial intelligence\u2013enabled electrocardiogram.","volume":"25","author":"Attia","year":"2019","journal-title":"Nat Med"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000044968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T14:27:50Z","timestamp":1779805670000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000044968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":19,"journal-issue":{"issue":"40","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000044968","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"2025-07-03","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-12","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}