{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:57:02Z","timestamp":1777323422871,"version":"3.51.4"},"reference-count":50,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T00:00:00Z","timestamp":1777075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>The paper addresses ECG arrhythmia classification using a novel input fusion strategy that combines spatial representations of ECG time series recordings. Four distinct time series-to-image transformations are considered, namely classical spectrograms, Gramian Angular Field (GAF), Recursive Plot (RP), and the S-Transform (ST). Classification of combined 2 \u00d7 2 images generated from single-lead ECG recordings is performed using both custom and ResNet-50 deep learning architectures. Finally, several distinct explainability algorithms are used to identify the relevant regions in the input images that mainly influence the classification decisions. Experiments performed on the MIT-BIH and Chapman\u2013Shaoxing arrhythmia datasets revealed performance comparable to more sophisticated approaches in terms of accuracy (99%), F1-score (98.6%), and AUC (0.999) values.<\/jats:p>","DOI":"10.3390\/make8050114","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:24:51Z","timestamp":1777317891000},"page":"114","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Combined Spatial Representations for ECG Arrhythmia Classification"],"prefix":"10.3390","volume":"8","author":[{"given":"Iulia","family":"Onic\u0103","sequence":"first","affiliation":[{"name":"Faculty of Electronics, Telecommunications and Information Technology, Gheorghe Asachi Technical University of Iasi, Bd. Carol I, No. 11A, 700506 Iasi, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6935-3387","authenticated-orcid":false,"given":"Iulian B.","family":"Ciocoiu","sequence":"additional","affiliation":[{"name":"Faculty of Electronics, Telecommunications and Information Technology, Gheorghe Asachi Technical University of Iasi, Bd. Carol I, No. 11A, 700506 Iasi, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1811","DOI":"10.1016\/S0140-6736(25)01917-8","article-title":"Global burden of 292 causes of death in 204 countries and territories and 660 subnational locations, 1990\u20132023: A systematic analysis for the Global Burden of Disease Study 2023","volume":"406","author":"Naghavi","year":"2025","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2518512","DOI":"10.1109\/TIM.2022.3204316","article-title":"Interpretation and classification of arrhythmia using deep convolutional network","volume":"71","author":"Singh","year":"2022","journal-title":"IEEE Trans. Instr. Meas."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"39496","DOI":"10.1038\/s41598-025-22986-0","article-title":"An explainable deep learning framework for trustworthy arrhythmia detection from ECG signals","volume":"15","author":"Talukder","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ansari, Y., Mourad, O., Qaraqe, K., and Serpedin, E. (2023). Deep learning for ECG Arrhythmia detection and classification: An overview of progress for period 2017\u20132023. Front. Physiol., 14.","DOI":"10.3389\/fphys.2023.1246746"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"191921","DOI":"10.1109\/ACCESS.2024.3518776","article-title":"Classification algorithms in automatic diagnosis of ECG arrhythmias: A review","volume":"12","author":"Sun","year":"2024","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"111324","DOI":"10.1016\/j.compbiomed.2025.111324","article-title":"Explainable deep learning based techniques for ECG-Based heart disease classification: A systematic literature review and future direction","volume":"199","author":"Manimaran","year":"2025","journal-title":"Comp. Biol. Med."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Abdullah, T.A.A., Zahid, M.S.M., Ali, W., and Hassan, S.U. (2023). B-LIME: An improvement of LIME for interpretable deep learning classification of cardiac arrhythmia from ECG signals. Processes, 11.","DOI":"10.3390\/pr11020595"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Oporto, E., Mauricio, D., Maculan, N., and Uribe, G. (2026). Challenges in the classification of cardiac arrhythmias and ischemia using end-to-end deep learning and the electrocardiogram: A systematic review. Diagnostics, 16.","DOI":"10.3390\/diagnostics16010161"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1049\/iet-bmt.2016.0177","article-title":"Comparative analysis of bag-of-words models for ECG-based biometrics","volume":"6","author":"Ciocoiu","year":"2017","journal-title":"IET Biom."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"109496","DOI":"10.1016\/j.bspc.2026.109496","article-title":"Heartbeat classification for arrhythmia detection in ambulatory monitoring: A comprehensive systematic review","volume":"116","author":"Apandi","year":"2026","journal-title":"Biomed. Sig. Process. Control"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ahmed, A.A., Ali, W., Abdullah, T.A.A., and Malebary, S.J. (2023). Classifying cardiac arrhythmia from ECG signal using 1D CNN deep learning model. Mathematics, 11.","DOI":"10.3390\/math11030562"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Khan, F., Yu, X., Yuan, Z., and ur Rehman, A. (2023). ECG classification using 1-D convolutional deep residual neural network. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0284791"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Atwa, A.E.M., Atlam, E.S., Ahmed, A., Atwa, M.A., Abdelrahim, E.M., and Siam, A.I. (2025). Interpretable deep learning models for arrhythmia classification based on ECG signals using PTB-X dataset. Diagnostics, 15.","DOI":"10.3390\/diagnostics15151950"},{"key":"ref_14","unstructured":"Baig, Z., Nasir, S., Khan, R.A., and Haque, M.Z.U. (2025). ArrhythmiaVision: Resource-conscious deep learning models with visual explanations for ECG arrhythmia classification. arXiv."},{"key":"ref_15","unstructured":"Silva, G., Silva, P., Moreira, G., Freitas, V., Gertrudes, J., and Luz, E. (2025). A systematic review of ECG arrhythmia classification: Adherence to standards, fair evaluation, and embedded feasibility. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Imane, A., Abdelmajid, B., Hilal, D.L., Frederic, E.D.Y., and Hanaa, O.H. (2025, January 15\u201316). Artificial intelligence for atrial fibrillation detection: A systematic review of recent advances in ECG-based deep learning models. Proceedings of the 5th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Fez, Morocco.","DOI":"10.1109\/IRASET64571.2025.11008062"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.ins.2022.01.030","article-title":"A novel method for reducing arrhythmia classification from 12-lead ECG signals to single-lead ECG with minimal loss of accuracy through teacher-student knowledge distillation","volume":"593","author":"Sepahvand","year":"2022","journal-title":"Inf. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"9230","DOI":"10.1038\/s41598-025-93906-5","article-title":"Electrocardiogram analysis for cardiac arrhythmia classification and prediction through self attention based auto encoder","volume":"15","author":"Shah","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"113301","DOI":"10.1016\/j.knosys.2025.113301","article-title":"Advanced deep learning framework for ECG arrhythmia classification using 1D-CNN with attention mechanism","volume":"315","author":"Guhdar","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_20","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":"23","author":"Islam","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shah, H.A., Saeed, F., Diyan, M., Almujally, N., and Kang, J.-M. (2024). ECG-TransCovNet: A hybrid transformer model for accurate arrhythmia detection using electrocardiogram signals. CAAI Trans. Intell. Technol., 1\u201314.","DOI":"10.1049\/cit2.12293"},{"key":"ref_22","unstructured":"Wang, Z., and Oates, T. (2015, January 25\u201330). Encoding time series as images for visual inspection and classification using tiled convolutional neural networks. Proceedings of the 29th AAAI Conference on Artificial Intelligence, Austin, TX, USA."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1209\/0295-5075\/4\/9\/004","article-title":"Recurrence plots of dynamical systems","volume":"4","author":"Eckmann","year":"1987","journal-title":"Europhys. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1109\/78.492555","article-title":"Localization of the complex spectrum: The S-transform","volume":"44","author":"Stockwell","year":"1996","journal-title":"IEEE Trans. Sig. Process."},{"key":"ref_25","unstructured":"Moody, G., and Mark, R. (2025, August 04). MIT-BIH Arrhythmia Database. PhysioNet: MIT Laboratory for Computational Physiology, 2005. Available online: https:\/\/physionet.org\/content\/mitdb\/1.0.0\/mitdbdir\/#files-panel."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41597-020-0386-x","article-title":"A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients","volume":"7","author":"Zheng","year":"2020","journal-title":"Sci. Data"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"112056","DOI":"10.1016\/j.asoc.2024.112056","article-title":"Advancing cardiac diagnostics: Exceptional accuracy in abnormal ECG signal classification with cascading deep learning and explainability analysis","volume":"165","author":"Zeng","year":"2024","journal-title":"Appl. Soft Comp. J."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Benmessaoud, A.S., Medjani, F., Bousseloub, Y., Bouaita, K., Benrahem, D., and Kezai, T. (2023, January 23\u201325). High quality ECG dataset based on MIT-BIH recordings for improved heartbeats classification. Proceedings of the IEEE International Conference on Omni-Layer Intelligent Systems (COINS), Berlin, Germany.","DOI":"10.1109\/COINS57856.2023.10189299"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5718","DOI":"10.1016\/j.eswa.2008.06.108","article-title":"Cluster-based under-sampling approaches for imbalanced data distributions","volume":"36","author":"Yen","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.neucom.2021.01.033","article-title":"Relevant information undersampling to support imbalanced data classification","volume":"436","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bunkhumpornpat, C., Sinapiromsaran, K., and Lursinsap, C. (2009, January 27\u201330). Safe-level-SMOTE: Safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem. Proceedings of the 13th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Bangkok, Thailand.","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educat. Psych. Meas."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chattopadhyay, A., Sarkar, A., Howlader, P., and Balasubramanian, V.N. (2017). Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks. arXiv.","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, Z., Du, M., Yang, F., Zhang, Z., Ding, S., Mardziel, P., and Hu, X. (2020, January 14\u201319). Score-CAM: Score-weighted visual explanations for Convolutional Neural Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/s12530-023-09559-0","article-title":"An enhanced ResNet-50 deep learning model for arrhythmia detection using electrocardiogram biomedical indicators","volume":"15","author":"Anand","year":"2024","journal-title":"Evol. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e1774","DOI":"10.7717\/peerj-cs.1774","article-title":"Arrhythmia classification for non-experts using infinite impulse response (IIR)-filter-based machine learning and deep learning models of the electrocardiogram","volume":"10","author":"Mallikarjunamallu","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1007\/s44163-025-00290-0","article-title":"Fadlec: Feature extraction and arrhythmia classification using deep learning from electrocardiograph signals","volume":"5","author":"Lamba","year":"2025","journal-title":"Disc. Artif. Intell."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Eleyan, A., and Alboghbaish, E. (2024). Electrocardiogram signals classification using deep-learning-based incorporated convolutional neural network and long short-term memory framework. Computers, 13.","DOI":"10.3390\/computers13020055"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"105437","DOI":"10.1016\/j.bspc.2023.105437","article-title":"A novel imbalanced dataset mitigation method and ECG classification model based on combined 1D_CBAM-autoencoder and lightweight CNN model","volume":"87","author":"Chen","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e16182","DOI":"10.14814\/phy2.16182","article-title":"LDCNN: A new arrhythmia detection technique with ECG signals using a linear deep convolutional neural network","volume":"12","author":"Bayani","year":"2024","journal-title":"Physiol. Rep."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"87071","DOI":"10.1109\/ACCESS.2023.3305473","article-title":"Heartbeat dynamics: A novel efficient interpretable feature for arrhythmias classification","volume":"1","author":"Dong","year":"2023","journal-title":"IEEE Access"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"8804","DOI":"10.1038\/s41598-024-59311-0","article-title":"Multimodal ECG heartbeat classification method based on a convolutional neural network embedded with FCA","volume":"14","author":"Zhou","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Di Paolo, I.F., and Castro, A.R.G. (2024). Intra- and interpatient ECG heartbeat classification based on multimodal convolutional neural networks with an adaptive attention mechanism. Appl. Sci., 14.","DOI":"10.3390\/app14209307"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"105740","DOI":"10.1016\/j.cmpb.2020.105740","article-title":"Accurate deep neural network model to detect cardiac arrhythmia on more than 10,000 individual subject ECG records","volume":"197","author":"Yildirim","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Meqdad, M.N., Abdali-Mohammadi, F., and Kadry, S. (2022). A new 12-lead ECG signals fusion method using evolutionary CNN trees for arrhythmia detection. Mathematics, 10.","DOI":"10.3390\/math10111911"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2937","DOI":"10.1038\/s41598-023-30208-8","article-title":"Bimodal CNN for cardiovascular disease classification by co-training ECG grayscale images and scalograms","volume":"13","author":"Yoon","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"An, X., Shi, S., Wang, Q., Yu, Y., and Liu, Q. (2024). Research on a lightweight arrhythmia classification model based on knowledge distillation for wearable single-lead ECG monitoring systems. Sensors, 24.","DOI":"10.3390\/s24247896"},{"key":"ref_48","first-page":"971","article-title":"Automatic extraction of medical latent variables from ECG signals utilizing a mutual information-based technique and capsular neural networks for arrhythmia detection","volume":"81","author":"Hassan","year":"2024","journal-title":"Comp. Mat. Contin."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"105948","DOI":"10.1016\/j.cmpb.2021.105948","article-title":"Arrhythmia classification from single-lead ECG signals using the inter-patient paradigm","volume":"202","author":"Dias","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_50","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":"Chazal","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/5\/114\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:21:22Z","timestamp":1777321282000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/5\/114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,25]]},"references-count":50,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["make8050114"],"URL":"https:\/\/doi.org\/10.3390\/make8050114","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,25]]}}}