{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:23:27Z","timestamp":1777983807985,"version":"3.51.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:00:00Z","timestamp":1770336000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:00:00Z","timestamp":1774483200000},"content-version":"vor","delay-in-days":48,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004937","name":"Bundesministerium f\u00fcr Forschung und Technologie","doi-asserted-by":"publisher","award":["01KD2208A"],"award-info":[{"award-number":["01KD2208A"]}],"id":[{"id":"10.13039\/501100004937","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Bundesministerium f\u00fcr Forschung und Technologie, Germany","award":["01KD2414A"],"award-info":[{"award-number":["01KD2414A"]}]},{"name":"Bundesministerium f\u00fcr Forschung und Technologie, Germany","award":["01ZZ9603"],"award-info":[{"award-number":["01ZZ9603"]}]},{"DOI":"10.13039\/501100014840","name":"Gemeinsame Bundesausschuss","doi-asserted-by":"publisher","award":["01VSF20014"],"award-info":[{"award-number":["01VSF20014"]}],"id":[{"id":"10.13039\/501100014840","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011937","name":"Nieders\u00e4chsische Ministerium f\u00fcr Wissenschaft und Kultur","doi-asserted-by":"publisher","award":["76211-12-1\/21"],"award-info":[{"award-number":["76211-12-1\/21"]}],"id":[{"id":"10.13039\/100011937","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The clinical deployment of artificial intelligence (AI) solutions for assessing cardiovascular disease (CVD) risk in 12-lead electrocardiography (ECG) is hindered by limitations in interpretability and explainability. To address this, we present xGNN4MI, an open-source framework for graph neural networks (GNNs) in ECG modeling for interpretable CVD prediction. Our framework facilitates modeling clinically relevant spatial relationships between ECG leads and their temporal dynamics. We integrated explainable AI (XAI) and developed a task-specific XAI evaluation and visualization workflow to identify ECG leads crucial to the model\u2019s decision-making process, enabling a systematic comparison with established clinical knowledge. We evaluated xGNN4MI on two challenging tasks: diagnostic superclass classification and localization of myocardial infarction. Our findings show that the interpretable ECG-GNN models demonstrate good performance across the tasks. XAI analysis revealed clinically meaningful training effects, such as differentiating between anteroseptal and inferior myocardial infarction. Our work demonstrates the potential of ECG-GNNs for providing trustworthy and interpretable AI-based CVD diagnosis.<\/jats:p>","DOI":"10.1038\/s41746-026-02367-1","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T04:48:28Z","timestamp":1770353308000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["xGNN4MI: explainability of graph neural networks in 12-lead electrocardiography for cardiovascular disease classification"],"prefix":"10.1038","volume":"9","author":[{"given":"Miriam Cindy","family":"Maurer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Hempel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristin Elisabeth","family":"Steinhaus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hryhorii","family":"Chereda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Vollmer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dagmar","family":"Krefting","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolai","family":"Spicher","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne-Christin","family":"Hauschild","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,6]]},"reference":[{"key":"2367_CR1","unstructured":"WHO. World Health Organization https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds) (1948)."},{"key":"2367_CR2","doi-asserted-by":"publisher","first-page":"6318","DOI":"10.3390\/s20216318","volume":"20","author":"L Xie","year":"2020","unstructured":"Xie, L., Li, Z., Zhou, Y., He, Y. & Zhu, J. Computational diagnostic techniques for electrocardiogram signal analysis. Sensors 20, 6318 (2020).","journal-title":"Sensors"},{"key":"2367_CR3","doi-asserted-by":"crossref","unstructured":"de Jager, J., Wallis, L. & Maritz, D. ECG interpretation skills of South African emergency medicine residents. Int. J. Emerg. Med. 3, 309\u201314 (2010).","DOI":"10.1007\/s12245-010-0227-3"},{"key":"2367_CR4","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.1161\/CIR.0b013e31826e1058","volume":"126","author":"K Thygesen","year":"2012","unstructured":"Thygesen, K. et al. Third universal definition of myocardial infarction. Circulation 126, 2020\u20132035 (2012).","journal-title":"Circulation"},{"key":"2367_CR5","doi-asserted-by":"crossref","unstructured":"Sachdeva, P. et al. Advancements in myocardial infarction management: exploring novel approaches and strategies. Cureus 15, e45578 (2023).","DOI":"10.7759\/cureus.45578"},{"key":"2367_CR6","unstructured":"Mechanic, O. J., Gavin, M. & Grossman, S. A. Acute Myocardial Infarction (updated 2023 Sep 3) (StatPearls Publishing, 2023); https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK459269\/."},{"key":"2367_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15432-4","volume":"11","author":"AH Ribeiro","year":"2020","unstructured":"Ribeiro, A. H. et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat. Commun. 11, 1760 (2020).","journal-title":"Nat. Commun."},{"key":"2367_CR8","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1038\/s41591-020-0870-z","volume":"26","author":"S Raghunath","year":"2020","unstructured":"Raghunath, S. et al. Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network. Nat. Med. 26, 886\u2013891 (2020).","journal-title":"Nat. Med."},{"key":"2367_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25351-7","volume":"12","author":"EM Lima","year":"2021","unstructured":"Lima, E. M. et al. Deep neural network-estimated electrocardiographic age as a mortality predictor. Nat. Commun. 12, 5117 (2021).","journal-title":"Nat. Commun."},{"key":"2367_CR10","doi-asserted-by":"crossref","unstructured":"Maurer, M. C. et al. Explainable artificial intelligence on biosignals for clinical decision support. In KDD 24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 6597\u20136604 (KDD, 2024).","DOI":"10.1145\/3637528.3671459"},{"key":"2367_CR11","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T., Singh, S. & Guestrin, C. \u201cWhy should I trust you?\u201d Explaining the predictions of any classifier. In Proc. of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 1135\u20131144 (ACM, 2016).","DOI":"10.1145\/2939672.2939778"},{"key":"2367_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2019","unstructured":"Guidotti, R. et al. A survey of methods for explaining black box models. ACM Comput. Surv. 51, 1\u201342 (2019).","journal-title":"ACM Comput. Surv."},{"key":"2367_CR13","unstructured":"EU AI Act. European Union Artificial Intelligence Act https:\/\/artificialintelligenceact.eu\/ (2025)."},{"key":"2367_CR14","doi-asserted-by":"crossref","unstructured":"Goettling, M., Hammer, A., Malberg, H. & Schmidt, M. xECGArch: a trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features. Sci. Rep. 14, 13122 (2024).","DOI":"10.1038\/s41598-024-63656-x"},{"key":"2367_CR15","doi-asserted-by":"publisher","unstructured":"Bender, T. et al. Analysis of a deep learning model for 12-lead ECG classification reveals learned features similar to diagnostic criteria. IEEE J. Biomed. Health Inform. https:\/\/doi.org\/10.1109\/JBHI.2023.3271858 (2023).","DOI":"10.1109\/JBHI.2023.3271858"},{"key":"2367_CR16","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1038\/s42256-023-00620-w","volume":"5","author":"H Turb\u00e9","year":"2023","unstructured":"Turb\u00e9, H., Bjelogrlic, M., Lovis, C. & Mengaldo, G. Evaluation of post-hoc interpretability methods in time-series classification. Nat. Mach. Intell. 5, 250\u2013260 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"2367_CR17","doi-asserted-by":"publisher","first-page":"105420","DOI":"10.1016\/j.bspc.2023.105420","volume":"87","author":"G Kutluana","year":"2024","unstructured":"Kutluana, G. & T\u00fcrker, I. Classification of cardiac disorders using weighted visibility graph features from ECG signals. Biomed. Signal Process. Control 87, 105420 (2024).","journal-title":"Biomed. Signal Process. Control"},{"key":"2367_CR18","doi-asserted-by":"publisher","first-page":"105005","DOI":"10.1088\/1361-6579\/acf754","volume":"44","author":"H Dathe","year":"2023","unstructured":"Dathe, H., Krefting, D. & Spicher, N. Completing the cabrera circle: deriving adaptable leads from ecg limb leads by combining constraints with a correction factor. Physiol. Meas. 44, 105005 (2023).","journal-title":"Physiol. Meas."},{"key":"2367_CR19","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2009","unstructured":"Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M. & Monfardini, G. The graph neural network model. IEEE Trans. Neural Netw. 20, 61\u201380 (2009).","journal-title":"IEEE Trans. Neural Netw."},{"key":"2367_CR20","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2021","unstructured":"Wu, Z. et al. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32, 4\u201324 (2021).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2367_CR21","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/RBME.2021.3122522","volume":"16","author":"R Li","year":"2023","unstructured":"Li, R. et al. Graph signal processing, graph neural network and graph learning on biological data: a systematic review. IEEE Rev. Biomed. Eng. 16, 109\u2013135 (2023).","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"2367_CR22","doi-asserted-by":"publisher","first-page":"102840","DOI":"10.1016\/j.artmed.2024.102840","volume":"151","author":"H Chereda","year":"2024","unstructured":"Chereda, H., Leha, A. & Bei\u00dfbarth, T. Stable feature selection utilizing graph convolutional neural network and layer-wise relevance propagation for biomarker discovery in breast cancer. Artif. Intell. Med. 151, 102840 (2024).","journal-title":"Artif. Intell. Med."},{"key":"2367_CR23","unstructured":"Zhang, H. et al. ST-ReGE: a novel spatial-temporal residual graph convolutional network for CVD. IEEE J. Biomed. Health Inform. https:\/\/ieeexplore.ieee.org\/document\/10292830\/ (2023)."},{"key":"2367_CR24","doi-asserted-by":"publisher","first-page":"108406","DOI":"10.1016\/j.cmpb.2024.108406","volume":"257","author":"Y Qiang","year":"2024","unstructured":"Qiang, Y. et al. Conv-rgnn: an efficient convolutional residual graph neural network for ECG classification. Comput. Methods Prog. Biomed. 257, 108406 (2024).","journal-title":"Comput. Methods Prog. Biomed."},{"key":"2367_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, X., Liu, Z., Han, L. & Peng, S. ECGNN: enhancing abnormal recognition in 12-Lead ECG with graph neural network. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 1411\u20131416 (IEEE, 2022).","DOI":"10.1109\/BIBM55620.2022.9995419"},{"key":"2367_CR26","doi-asserted-by":"crossref","unstructured":"Guo, L., Wu, Y., Ma, N. & An, Y. KGD-GNN: a knowledge-guided graph neural network for myocardial infarction localization via 12-lead ECG. In: ICASSP 2025\u20142025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 1\u20135 (IEEE, 2025).","DOI":"10.1109\/ICASSP49660.2025.10887796"},{"key":"2367_CR27","doi-asserted-by":"publisher","first-page":"104388","DOI":"10.1016\/j.bspc.2022.104388","volume":"80","author":"C Kan","year":"2023","unstructured":"Kan, C., Ye, Z., Zhou, H. & Cheruku, S. R. DG-ECG: multi-stream deep graph learning for the recognition of disease-altered patterns in electrocardiogram. Biomed. Signal Process. Control 80, 104388 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"2367_CR28","doi-asserted-by":"publisher","first-page":"7308","DOI":"10.1109\/TPAMI.2022.3228315","volume":"45","author":"TT Mueller","year":"2023","unstructured":"Mueller, T. T. et al. Differentially private graph neural networks for whole-graph classification. IEEE Trans. Pattern Anal. Mach. Intell. 45, 7308\u20137318 (2023).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2367_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-0495-6","volume":"7","author":"P Wagner","year":"2020","unstructured":"Wagner, P. et al. PTB-XL, a large publicly available electrocardiography dataset. Sci. Data 7, 154 (2020).","journal-title":"Sci. Data"},{"key":"2367_CR30","doi-asserted-by":"publisher","first-page":"e372","DOI":"10.1093\/ije\/dyac034","volume":"51","author":"H V\u00f3lzke","year":"2022","unstructured":"V\u00f3lzke, H. et al. Cohort profile update: the study of health in pomerania (SHIP). Int. J. Epidemiol. 51, e372\u2013e383 (2022).","journal-title":"Int. J. Epidemiol."},{"key":"2367_CR31","unstructured":"Ying, Z., Bourgeois, D., You, J., Zitnik, M. & Leskovec, J. Gnnexplainer: Generating explanations for graph neural networks. In Advances in neural information processing systems, 9244\u22129255 (Curran Associates Inc., 2019)."},{"key":"2367_CR32","unstructured":"Ganschow, U. EKG-Kurs (KVM, Berlin, 2016)."},{"key":"2367_CR33","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.jelectrocard.2019.11.045","volume":"58","author":"B Ruiz-Mateos","year":"2020","unstructured":"Ruiz-Mateos, B. et al. Elevation of ST-segment in aVR is predictive of cardiogenic shock but not of multivessel disease in inferior myocardial infarction. J. Electrocardiol. 58, 63\u201367 (2020).","journal-title":"J. Electrocardiol."},{"key":"2367_CR34","unstructured":"Vu, M. & Thai, M.T. PGM-Explainer: Probabilistic graphical model explanations for graph neural networks, In Advances In Neural Information Processing Systems, Vol. 33, (eds Larochelle H., Ranzato M., Hadsell R., Balcan M., Lin H.) pp. 12225\u201312235 https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3495724.3496749 (Curran Associates, Inc., 2020)."},{"key":"2367_CR35","doi-asserted-by":"publisher","first-page":"e005114","DOI":"10.1161\/CIRCOUTCOMES.118.005114","volume":"12","author":"R Chen","year":"2019","unstructured":"Chen, R., Stewart, W. F., Sun, J., Ng, K. & Yan, X. Recurrent neural networks for early detection of heart failure from longitudinal electronic health record data: implications for temporal modeling with respect to time before diagnosis, data density, data quantity, and data type. Circ. Cardiovasc. Qual. Outcomes 12, e005114 (2019).","journal-title":"Circ. Cardiovasc. Qual. Outcomes"},{"key":"2367_CR36","doi-asserted-by":"publisher","first-page":"690049","DOI":"10.3389\/fgene.2021.690049","volume":"12","author":"X-M Zhang","year":"2021","unstructured":"Zhang, X.-M., Liang, L., Liu, L. & Tang, M.-J. Graph neural networks and their current applications in bioinformatics. Front. Genet. 12, 690049 (2021).","journal-title":"Front. Genet."},{"key":"2367_CR37","doi-asserted-by":"publisher","unstructured":"Kipf, T. N. & Welling, M., Semi-Supervised Classification with Graph Convolutional Networks, In 5th International Conference on Learning Representations, Toulon, France, Conference Track Proceedings', OpenReview.net, (ICLR, 2017) https:\/\/doi.org\/10.48550\/arXiv.1609.02907.","DOI":"10.48550\/arXiv.1609.02907"},{"key":"2367_CR38","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J., Deep Residual Learning for Image Recognition, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770\u2212778, (Las Vegas, NV, USA, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2367_CR39","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q., Densely Connected Convolutional Networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2261\u22122269, (Honolulu, HI, USA, 2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"2367_CR40","doi-asserted-by":"publisher","unstructured":"Yuan, H., Yu, H., Wang, J., Li, K. & Ji, S. On explainability of graph neural networks via subgraph explorations. In Proc. 38th International Conference on Machine Learning, Vol. 139, 12241\u221212252 https:\/\/doi.org\/10.48550\/arXiv.2102.05152 (2021).","DOI":"10.48550\/arXiv.2102.05152"},{"key":"2367_CR41","doi-asserted-by":"crossref","unstructured":"Longo, L. et al. Explainable artificial intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions. Inf. Fusion 106, 102301 (2024).","DOI":"10.1016\/j.inffus.2024.102301"},{"key":"2367_CR42","doi-asserted-by":"crossref","unstructured":"Metsch, J. M. & Hauschild, A.-C. Benchxai: comprehensive benchmarking of post-hoc explainable ai methods on multi-modal biomedical data. Comput. Biol. Med. 191, 110124 (2025).","DOI":"10.1016\/j.compbiomed.2025.110124"},{"key":"2367_CR43","doi-asserted-by":"crossref","unstructured":"Klein, L., L\u00fcth, C., Schlegel, U. & Bungert, T. El-Assady M., and J\u00e4ger P. Navigating the maze of explainable AI: a systematic approach to evaluating methods and metrics. In Proc. 38th International Conference on Neural Information Processing Systems (NIPS '24), Vol. 37, 67106\u201367146 (Curran Associates Inc., Red Hook, NY, USA, 2024).","DOI":"10.52202\/079017-2142"},{"key":"2367_CR44","doi-asserted-by":"crossref","unstructured":"Bender, T. et al. Analysis of a deep learning model for 12-Lead ECG classification reveals learned features similar to diagnostic criteria. IEEE J. Biomed. Health Inform. https:\/\/ieeexplore.ieee.org\/document\/10113187\/ (2023).","DOI":"10.1109\/JBHI.2023.3271858"},{"key":"2367_CR45","doi-asserted-by":"publisher","unstructured":"Fey, M. & Lenssen, J. E., Fast graph representation learning with pytorch geometric, In ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds. https:\/\/doi.org\/10.48550\/arXiv.1903.02428 (2019).","DOI":"10.48550\/arXiv.1903.02428"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02367-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02367-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02367-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T21:32:13Z","timestamp":1774560733000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02367-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,6]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2367"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02367-1","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7721630\/v1","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,6]]},"assertion":[{"value":"26 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"256"}}