{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T11:59:57Z","timestamp":1793015997997,"version":"4.5.0"},"reference-count":90,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2021,5,7]],"date-time":"2021-05-07T00:00:00Z","timestamp":1620345600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002803","name":"Fondazione Cariplo","doi-asserted-by":"publisher","award":["2019\u20104608"],"award-info":[{"award-number":["2019\u20104608"]}],"id":[{"id":"10.13039\/501100002803","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["740132"],"award-info":[{"award-number":["740132"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Numer Methods Biomed Eng"],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We present a new, computationally efficient framework to perform forward uncertainty quantification (UQ) in cardiac electrophysiology. We consider the monodomain model to describe the electrical activity in the cardiac tissue, coupled with the Aliev\u2010Panfilov model to characterize the ionic activity through the cell membrane. We address a complete forward UQ pipeline, including both: <jats:italic>(i)<\/jats:italic> a variance\u2010based global sensitivity analysis for the selection of the most relevant input parameters, and <jats:italic>(ii)<\/jats:italic> a way to perform uncertainty propagation to investigate the impact of intra\u2010subject variability on outputs of interest depending on the cardiac potential. Both tasks exploit stochastic sampling techniques, thus implying overwhelming computational costs because of the huge amount of queries to the high\u2010fidelity, full\u2010order computational model obtained by approximating the coupled monodomain\/Aliev\u2010Panfilov system through the finite element method. To mitigate this computational burden, we replace the full\u2010order model with computationally inexpensive projection\u2010based reduced\u2010order models (ROMs) aimed at reducing the state\u2010space dimensionality. Resulting approximation errors on the outputs of interest are finally taken into account through artificial neural network (ANN)\u2010based models, enhancing the accuracy of the whole UQ pipeline. Numerical results show that the proposed physics\u2010based ROMs outperform regression\u2010based emulators relying on ANNs built with the same amount of training data, in terms of both numerical accuracy and overall computational efficiency.<\/jats:p>","DOI":"10.1002\/cnm.3450","type":"journal-article","created":{"date-parts":[[2021,2,18]],"date-time":"2021-02-18T05:35:32Z","timestamp":1613626532000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Enabling forward uncertainty quantification and sensitivity analysis in cardiac electrophysiology by reduced order modeling and machine learning"],"prefix":"10.1002","volume":"37","author":[{"given":"Stefano","family":"Pagani","sequence":"first","affiliation":[{"name":"MOX, Dipartimento di Matematica Politecnico di Milano  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-2802","authenticated-orcid":false,"given":"Andrea","family":"Manzoni","sequence":"additional","affiliation":[{"name":"MOX, Dipartimento di Matematica Politecnico di Milano  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,5,7]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1017\/9781108616096"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1113\/JP271671"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yjmcc.2015.11.018"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2019.00721"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-017-1714-y"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.05.007"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0558"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04801-7"},{"key":"e_1_2_9_10_1","series-title":"Monographs in Computational Science and Engineering","volume-title":"Computing the Electrical Activity in the Heart","author":"Sundnes J","year":"2007"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pbiomolbio.2010.05.008"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-012-0924-6"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-015-0033-5"},{"key":"e_1_2_9_14_1","volume-title":"Monte Carlo Statistical Methods","author":"Robert C","year":"2013"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jco.2010.04.001"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019129717644"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2013.12.025"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10237-014-0618-0"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1070.0496"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40072-015-0055-9"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2007.04.002"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/060663660"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492914000075"},{"key":"e_1_2_9_24_1","volume-title":"Neural Networks and Learning Machines","author":"Haykin S","year":"2009"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2008.10.008"},{"key":"e_1_2_9_26_1","volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen CE","year":"2006"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2017.06.020"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2010.2051156"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.1504242"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mbs.2005.04.003"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pbiomolbio.2004.01.016"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1114\/1.1289474"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1152\/ajpheart.00109.2006"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms11437"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0149342"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsfs.2010.0041"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0282-2"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101626"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2019.01.033"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492917000046"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/0960-0779(95)00089-5"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218202504003489"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2006.889181"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/nme.2571"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1137\/090766498"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2015.09.046"},{"key":"e_1_2_9_47_1","volume-title":"Reduced Basis Methods for Partial Differential Equations. An Introduction","author":"Quarteroni A","year":"2016"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2018.06.003"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2004.08.006"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.3934\/cpaa.2009.8.383"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.2465"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2017.06.011"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mbs.2015.12.005"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10444-014-9393-9"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96649-6_6"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1002\/nme.4371"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2015.06.032"},{"key":"e_1_2_9_58_1","volume-title":"Global Sensitivity Analysis: The Primer","author":"Saltelli A","year":"2008"},{"key":"e_1_2_9_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/0951-8320(96)00002-6"},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827501387826"},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.fluid.010908.165248"},{"key":"e_1_2_9_62_1","doi-asserted-by":"publisher","DOI":"10.1137\/050645142"},{"key":"e_1_2_9_63_1","volume-title":"Stochastic Finite Elements: A Spectral Approach","author":"Ghanem RG","year":"2003"},{"key":"e_1_2_9_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15337-2_3"},{"key":"e_1_2_9_65_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/57.1.97"},{"key":"e_1_2_9_66_1","doi-asserted-by":"publisher","DOI":"10.1137\/17M1151006"},{"key":"e_1_2_9_67_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0349"},{"key":"e_1_2_9_68_1","doi-asserted-by":"publisher","DOI":"10.1615\/Int.J.UncertaintyQuantification.2012004291"},{"key":"e_1_2_9_69_1","doi-asserted-by":"publisher","DOI":"10.1137\/140995817"},{"key":"e_1_2_9_70_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-conmatphys-020911-125112"},{"key":"e_1_2_9_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00419-009-0384-0"},{"key":"e_1_2_9_72_1","doi-asserted-by":"publisher","DOI":"10.1038\/415219a"},{"key":"e_1_2_9_73_1","volume-title":"Zygote Solid 3D Heart Generation II Developement Report","year":"2014"},{"key":"e_1_2_9_74_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199809033391003"},{"key":"e_1_2_9_75_1","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.102.21.2619"},{"key":"e_1_2_9_76_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mbs.2019.108228"},{"key":"e_1_2_9_77_1","first-page":"e3285","article-title":"Numerical evaluation of cardiac mechanical markers as estimators of the electrical activation time","author":"Colli Franzone P","year":"2019","journal-title":"Int J Numer Methods Biomed Eng"},{"key":"e_1_2_9_78_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0335"},{"key":"e_1_2_9_79_1","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.2985"},{"key":"e_1_2_9_80_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2011.01.008"},{"key":"e_1_2_9_81_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2011.05.003"},{"key":"e_1_2_9_82_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2018.01910"},{"key":"e_1_2_9_83_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0334"},{"key":"e_1_2_9_84_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0345"},{"key":"e_1_2_9_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2198473"},{"key":"e_1_2_9_86_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10237-019-01153-1"},{"key":"e_1_2_9_87_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2019.112762"},{"key":"e_1_2_9_88_1","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.2894"},{"key":"e_1_2_9_89_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-017-1696-9"},{"key":"e_1_2_9_90_1","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.3178"},{"key":"e_1_2_9_91_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0381"}],"container-title":["International Journal for Numerical Methods in Biomedical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cnm.3450","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cnm.3450","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cnm.3450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T19:42:08Z","timestamp":1693424528000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cnm.3450"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,7]]},"references-count":90,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["10.1002\/cnm.3450"],"URL":"https:\/\/doi.org\/10.1002\/cnm.3450","archive":["Portico"],"relation":{},"ISSN":["2040-7939","2040-7947"],"issn-type":[{"value":"2040-7939","type":"print"},{"value":"2040-7947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,7]]},"assertion":[{"value":"2021-02-07","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e3450"}}