{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:17:52Z","timestamp":1785421072270,"version":"3.56.0"},"reference-count":49,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Deanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University","award":["KFU261516"],"award-info":[{"award-number":["KFU261516"]}]},{"award":["KFU261516"],"award-info":[{"award-number":["KFU261516"]}],"id":[{"id":"https:\/\/ror.org\/00dn43547","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Cardiovascular diseases (CVDs) are among the leading causes of death globally. In order to treat CVDs successfully in the early stages, it is crucial to diagnose them in time. The ECG is one of the most common and non-invasive methods to detect heart rhythms and to diagnose arrhythmias. However, the analysis of ECG recordings manually requires a lot of time and experience because the morphology of ECG signals and the characteristics of their waveforms are very complex and show large overlaps between different types of arrhythmias. So far, various approaches for automated analysis of ECG signals have been developed, mostly based on deep learning (DL). In general, these methods are able to analyze ECG signals automatically and to detect different types of arrhythmias. Most approaches, however, are based on a purely data-driven feature learning and do not pay attention to the morphology-sensitive temporal structure of ECG signals, which is important for a discriminative diagnosis of arrhythmias. Methods: In this paper, we propose an Attention-Based Morphology-Aware (ABMA) framework to leverage multilead ECG signals in conjunction with automatically computed physiological features using a hybrid deep learning architecture. ABMA leverages multi-scale convolutional neural networks to learn local morphology features, and bidirectional long short-term memory (BiLSTM) networks to model temporal rhythms in ECG signals. We designed an ABMA module that incorporates a morphology scoring network (MSN) in order to (1) estimate the morphology-aware importance of different ECG segments and (2) learn the temporal importance of ECG features. The learned attention weights enable learning to focus on key sections of ECG signals without predefined boundaries or manual annotation of fiducial points. To understand the contribution of each individual component of the framework, we performed an extensive ablation study, where we removed the handcrafted feature branch, the ABMA module, the MSN, and the multi-head attention mechanism, one at a time, and compared the results against a fixed set of experimental configurations. Results: To assess the performance of the proposed framework in three-class classification between sinus rhythm (SA), atrial fibrillation (AFIB), and ventricular tachycardia (VT), we employed a stratified 10-fold cross-validation protocol. Our approach achieved a mean accuracy of 95.18 \u00b1 1.18%, followed by a corresponding weighted F1-score of 95.19 \u00b1 1.18% and a macro F1-score of 94.66 \u00b1 1.35%. Notably, the performance of the proposed complete ABMA framework considerably outperformed the baseline CNN\u2013BiLSTM architecture. Furthermore, in the primary evaluation metrics (i.e., accuracy, F1-score), the complete framework showed statistically significant improvements against the baseline through paired two-sided t-tests (p &lt; 0.001). The ablation study indicated that each architectural component contributed positively to the overall classification performance, with the complete ABMA framework outperforming all reduced variants. Conclusions: The framework was evaluated by stratified cross-validation on a publicly available dataset. Our framework outperformed the baseline CNN\u2013BiLSTM model as well as the respective ablation models in terms of classification performance. The findings from the current study are based on a retrospective analysis and therefore future studies using an independent external dataset, from multiple centers, or as part of a prospective clinical study are necessary in order to establish the generalizability and clinical utility of the proposed framework. The ABMA framework is currently viewed as a very promising research framework for intelligent ECG analysis, but it is not yet a clinically validated diagnostic tool.<\/jats:p>","DOI":"10.3390\/diagnostics16142274","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T08:14:27Z","timestamp":1784621667000},"page":"2274","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ABMA: An Attention-Based Morphology-Aware Framework for Automated 12-Lead ECG Arrhythmia Classification"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9152-3242","authenticated-orcid":false,"given":"Manjur","family":"Kolhar","sequence":"first","affiliation":[{"name":"Department of Health Information Management and Technology, College of Applied Medical Sciences, King Faisal University, Al-Ahsa 31982, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raisa Nazir Ahmed","family":"Kazi","sequence":"additional","affiliation":[{"name":"Department of Respiratory Therapy, College of Applied Medical Sciences, King Faisal University, Al-Ahsa 31982, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Gaidai, O., Cao, Y., and Loginov, S. (2023). Global cardiovascular diseases death rate prediction. Curr. Probl. Cardiol., 48.","DOI":"10.1016\/j.cpcardiol.2023.101622"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1038\/s41582-023-00921-z","article-title":"Addressing disparities in the global epidemiology of stroke","volume":"20","author":"Prust","year":"2024","journal-title":"Nat. Rev. Neurol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1093\/eurheartj\/ehab892","article-title":"European Society of Cardiology: Cardiovascular disease statistics 2021","volume":"43","author":"Timmis","year":"2022","journal-title":"Eur. Hear. J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/S2213-8587(24)00271-7","article-title":"Effects of GLP-1 receptor agonists on kidney and cardiovascular disease outcomes: A meta-analysis of randomised controlled trials","volume":"13","author":"Badve","year":"2025","journal-title":"Lancet Diabetes Endocrinol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"He, Y., Zhou, Y., Qian, Y., Liu, J., Zhang, J., Liu, D., and Wu, Q. (2025). Cardioattentionnet: Advancing ECG beat characterization with a high-accuracy and portable deep learning model. Front. Cardiovasc. Med., 11.","DOI":"10.3389\/fcvm.2024.1473482"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.jelectrocard.2024.01.006","article-title":"Artificial intelligence-enhanced electrocardiography for accurate diagnosis and management of cardiovascular diseases","volume":"83","author":"Muzammil","year":"2024","journal-title":"J. Electrocardiol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Centeno-Bautista, M.A., Perez-Sanchez, A.V., Amezquita-Sanchez, J.P., and Valtierra-Rodriguez, M. (2024). Sudden cardiac death prediction based on the complete ensemble empirical mode decomposition method and a machine learning strategy by using ECG signals. Measurement, 236.","DOI":"10.1016\/j.measurement.2024.115052"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Haleem, M.S., Cisuelo, O., Andellini, M., Castaldo, R., Angelini, M., Ritrovato, M., Schiaffini, R., Franzese, M., and Pecchia, L. (2024). A Without the Morphology-Aware Attention Deep Neural Network Regressor for real time blood glucose estimation in paediatric population using physiological signals. Biomed. Signal Process. Control., 92.","DOI":"10.1016\/j.bspc.2024.106065"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zahra, F.A., and Kate, R.J. (2024). Obtaining clinical term embeddings from SNOMED CT ontology. J. Biomed. Inform., 149.","DOI":"10.1016\/j.jbi.2023.104560"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1080\/10255842.2024.2378105","article-title":"Arrhythmia detection in inter-patient ECG signals using entropy rate features and RR intervals with CNN architecture","volume":"29","author":"Berrahou","year":"2024","journal-title":"Comput. Methods Biomech. Biomed. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1093\/eurheartj\/ehz467","article-title":"2019 ESC guidelines for the management of patients with supraventricular tachycardia the task force for the management of patients with supraventricular tachycardia of the European Society of Cardiology (ESC) developed in collaboration with the Association for European Paediatric and Congenital Cardiology (AEPC)","volume":"41","author":"Brugada","year":"2020","journal-title":"Eur. Heart J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1002\/joa3.12599","article-title":"Differential diagnosis of wide QRS tachycardia: A review","volume":"37","author":"Abedin","year":"2021","journal-title":"J. Arrhythmia"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2214","DOI":"10.1016\/j.jacc.2024.03.416","article-title":"Arrhythmia-Induced Cardiomyopathy: JACC State-of-the-Art Review","volume":"83","author":"Shoureshi","year":"2024","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.jelectrocard.2024.05.099","article-title":"Aberrancy masquerading as ventricular tachycardia: Importance of invasive electrophysiology study for diagnosis of wide complex tachycardias","volume":"85","author":"William","year":"2024","journal-title":"J. Electrocardiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12938-023-01075-1","article-title":"ECG signal feature extraction trends in methods and applications","volume":"22","author":"Singh","year":"2023","journal-title":"Biomed. Eng. Online"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-024-02822-7","article-title":"An improved electrocardiogram arrhythmia classification performance with feature optimization","volume":"24","author":"Darmawahyuni","year":"2024","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TBME.2002.805486","article-title":"An improved morphological approach to background normalization of ECG signals","volume":"50","author":"Sun","year":"2003","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_18","first-page":"1","article-title":"Multilabel 12-lead ECG classification based on leadwise grouping multibranch network","volume":"71","author":"Xie","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Assegie, T.A., Sushma, S.J., and Mamanazarovna, S.S. (2023). Explainable heart disease diagnosis with supervised learning methods. ADCAIJ Adv. Distrib. Comput. Artif. Intell. J., 12.","DOI":"10.14201\/adcaij.31228"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1159\/000530376","article-title":"Heart rate variability for evaluating psychological stress changes in healthy adults: A scoping review","volume":"82","author":"Immanuel","year":"2023","journal-title":"Neuropsychobiology"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Castro, H., Garcia-Racines, J.D., and Bernal-Norena, A. (2021). Methodology for the prediction of paroxysmal atrial fibrillation based on heart rate variability feature analysis. Heliyon, 7.","DOI":"10.1016\/j.heliyon.2021.e08244"},{"key":"ref_22","first-page":"61","article-title":"Evolutionary and Design Perspectives on the Human Cardiac Conduction System: The cardiac conduction system is well designed","volume":"5","author":"Jung","year":"2025","journal-title":"Orig. Res. J."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Sayood, K. (2026). The Electrocardiogram. Biomedical Signal Processing: A One Semester Course, Springer Nature.","DOI":"10.1007\/978-3-032-08855-0"},{"key":"ref_24","first-page":"199","article-title":"The comparison of time-frequency analysis methods and their applications","volume":"24","author":"Liu","year":"2015","journal-title":"Comput. Tomogr. Theory Appl."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Pradhan, B.K., Neelappu, B.C., Sivaraman, J., Kim, D., and Pal, K. (2023). A Review on the Applications of Time-Frequency Methods in ECG Analysis. J. Heal. Eng., 2023.","DOI":"10.1155\/2023\/3145483"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1080\/02564602.2023.2265897","article-title":"Signal acquisition and time\u2013frequency perspective of EMG signal-based systems and applications","volume":"41","author":"Sharma","year":"2024","journal-title":"IETE Tech. Rev."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Tsalera, E., Papadakis, A., Samarakou, M., and Voyiatzis, I. (2022). Feature extraction with handcrafted methods and convolutional neural networks for facial emotion recognition. Appl. Sci., 12.","DOI":"10.3390\/app12178455"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Liu, G., Han, X., Tian, L., Zhou, W., and Liu, H. (2021). ECG quality assessment based on hand-crafted statistics and deep-learned S-transform spectrogram features. Comput. Methods Programs Biomed., 208.","DOI":"10.1016\/j.cmpb.2021.106269"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Prakash, A.J., Patro, K.K., Samantray, S., P\u0142awiak, P., and Hammad, M. (2023). A deep learning technique for biometric authentication using ECG beat template matching. Information, 14.","DOI":"10.3390\/info14020065"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"22823","DOI":"10.1007\/s00521-021-06693-1","article-title":"Hybrid feature fusion for classification optimization of short ECG segment in IoT based intelligent healthcare system","volume":"35","author":"Zhang","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Mathunjwa, B.M., Lin, Y.-T., Lin, C.-H., Abbod, M.F., and Shieh, J.-S. (2021). ECG arrhythmia classification by using a recurrence plot and convolutional neural network. Biomed. Signal Process. Control., 64.","DOI":"10.1016\/j.bspc.2020.102262"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"92871","DOI":"10.1109\/ACCESS.2019.2928017","article-title":"ECG arrhythmia classification using STFT-based spectrogram and convolutional neural network","volume":"7","author":"Huang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3561","DOI":"10.1016\/j.eswa.2012.12.063","article-title":"ECG arrhythmia classification based on optimum-path forest","volume":"40","author":"Luz","year":"2013","journal-title":"Expert Syst. Appl."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3802","DOI":"10.1109\/JBHI.2021.3138986","article-title":"Multi-scale convolutional neural network ensemble for multi-class arrhythmia classification","volume":"26","author":"Prabhakararao","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"8755","DOI":"10.1007\/s00521-022-06889-z","article-title":"Automated ECG multi-class classification system based on combining deep learning features with HRV and ECG measures","volume":"34","author":"Eltrass","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhang, J., Liu, A., Gao, M., Chen, X., Zhang, X., and Chen, X. (2020). ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network. Artif. Intell. Med., 106.","DOI":"10.1016\/j.artmed.2020.101856"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sattar, S., Mumtaz, R., Qadir, M., Mumtaz, S., Khan, M.A., De Waele, T., De Poorter, E., Moerman, I., and Shahid, A. (2024). Cardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets. Sensors, 24.","DOI":"10.3390\/s24082484"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"D, H., Anand, L.D.V., J, J., R, V., F, A.F., and S, R.I. (2024, January 20\u201322). Cardiac Arrhythmia Diagnosis Using Deep Learning: A 1D CNN-GRU Approach with Multiclass SVM and DWT Analysis. Proceedings of the 2024 Tenth International Conference on Bio Signals, Images, and Instrumentation (ICBSII), Chennai, India.","DOI":"10.1109\/ICBSII61384.2024.10564086"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.inffus.2019.06.024","article-title":"Multi-class arrhythmia detection from 12-lead varied-length ECG using attention-based time-incremental convolutional neural network","volume":"53","author":"Yao","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Pan, W., An, Y., Guan, Y., and Wang, J. (2022). MCA-net: A multi-task channel attention network for Myocardial infarction detection and location using 12-lead ECGs. Comput. Biol. Med., 150.","DOI":"10.1016\/j.compbiomed.2022.106199"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, X., Wang, J., Guang, Q., Ding, X., Liu, H., Xu, Y., Zhao, J., and Bai, M. (2026). Multimodal Transformer\u2013Based Electrocardiogram Analysis for Cardiovascular Comorbidity Detection: Model Development and Validation Study. JMIR Form. Res., 10.","DOI":"10.2196\/80815"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Feng, N., Chen, C., Du, P., Gong, C., Pei, J., and Huang, D. (2025). MS-LTCAF: A Multi-Scale Lead-Temporal Co-Attention Framework for ECG Arrhythmia Detection. Bioengineering, 12.","DOI":"10.3390\/bioengineering12091007"},{"key":"ref_44","first-page":"1","article-title":"Cardiac Abnormality Detection from 12-Lead ECG Using MultiBranch CNN and Attention-Based Feature Fusion","volume":"74","author":"Sharan","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ji, C., Wang, L., Qin, J., Liu, L., Han, Y., and Wang, Z. (2024). MSGformer: A multi-scale grid transformer network for 12-lead ECG arrhythmia detection. Biomed. Signal Process. Control., 87.","DOI":"10.1016\/j.bspc.2023.105499"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Kurniawan, A., Triwibowo, B.A., and Fandiantoro, D.H. (2024, January 6\u20137). Classification of arrhythmias 12-lead ECG signals based on 1 dimensional convolutional neural networks. Proceedings of the 2024 International Conference on Smart Computing, IoT and Machine Learning (SIML), Surakarta, Indonesia.","DOI":"10.1109\/SIML61815.2024.10578089"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1055","DOI":"10.1152\/physrev.00020.2025","article-title":"The Clinical Pathophysiology of Atrial Fibrillation: Outstanding Questions from Bedside to Bench and Back","volume":"106","author":"Boehmer","year":"2026","journal-title":"Physiol. Rev."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"27550834251342890","DOI":"10.1177\/27550834251342890","article-title":"Atrial fibrillation with slow-ventricular response (AF-SVR): A literature review","volume":"9","author":"Choi","year":"2025","journal-title":"J. Med. Access"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"2463","DOI":"10.1007\/s11517-022-02621-0","article-title":"Atrial conduction velocity mapping: Clinical tools, algorithms and approaches for understanding the arrhythmogenic substrate","volume":"60","author":"Coveney","year":"2022","journal-title":"Med. Biol. Eng. Comput."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/14\/2274\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T08:36:22Z","timestamp":1784622982000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/14\/2274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":49,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["diagnostics16142274"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16142274","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]}}}