Machine-learning–based exploration to identify remodeling patterns associated with death or heart-transplant in pediatric-dilated cardiomyopathy

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Garcia Canadilla, Patricia
• dc.contributor.author Sanchez Martinez, Sergio
• dc.contributor.author Martí Castellote, Pablo Miki
• dc.contributor.author Slorach, Cameron
• dc.contributor.author Hui, Wei
• dc.contributor.author Piella Fenoy, Gemma
• dc.contributor.author Aguado, Ainhoa M.
• dc.contributor.author Nogueira, Mariana
• dc.contributor.author Mertens, Luc
• dc.contributor.author Bijnens, Bart
• dc.contributor.author Friedberg, Mark K.
• dc.date.accessioned 2023-03-06T07:30:26Z
• dc.date.available 2023-03-06T07:30:26Z
• dc.date.issued 2022
• dc.description.abstract AIMS: We investigated left ventricular (LV) remodeling, mechanics, systolic and diastolic function, combined with clinical characteristics and heart-failure treatment in association to death or heart-transplant (DoT) in pediatric idiopathic, genetic or familial dilated cardiomyopathy (DCM), using interpretable machine-learning. METHODS AND RESULTS: Echocardiographic and clinical data from pediatric DCM and healthy controls were retrospectively analyzed. Machine-learning included whole cardiac-cycle regional longitudinal strain, aortic, mitral and pulmonary vein Doppler velocity traces, age and body surface area. We used unsupervised multiple kernel learning for data dimensionality reduction, positioning patients based on complex conglomerate information similarity. Subsequently, k-means identified groups with similar phenotypes. The proportion experiencing DoT was evaluated. Pheno-grouping identified 5 clinically distinct groups that were associated with differing proportions of DoT. All healthy controls clustered in groups 1 to 2, while all, but one, DCM subjects, clustered in groups 3 to 5; internally validating the algorithm. Cluster-5 comprised the oldest, most medicated patients, with combined systolic and diastolic heart-failure and highest proportion of DoT. Cluster4 included the youngest patients characterized by severe LV remodeling and systolic dysfunction, but mild diastolic dysfunction and the second-highest proportion of DoT. Cluster-3 comprised young patients with moderate remodeling and systolic dysfunction, preserved apical strain, pronounced diastolic dysfunction and lowest proportion of DoT. CONCLUSIONS: Interpretable machine-learning, using full cardiac-cycle systolic and diastolic data, mechanics and clinical parameters, can potentially identify pediatric DCM patients at high-risk for DoT, and delineate mechanisms associated with risk. This may facilitate more precise prognostication and treatment of pediatric DCM.
• dc.description.sponsorship Patricia Garcia-Canadilla has received funding from the postdoctoral fellowships program Beatriu de Pinos (2018-BP-00201), funded by the Secretary of Universities and Research (Goverment of Catalonia) and by the Horizon 2020 programme of research and innovation of the European Union under the Marie Skłodowska-Curie grant agreement Nº 801370. Pablo Miki Martí-Castellote has received funding from the predoctoral fellowships program FI-SDUR (2020-FISDU-00169) from AGAUR.
• dc.format.mimetype application/pdf
• dc.identifier.citation Garcia-Canadilla P, Sanchez-Martinez S, Martí-Castellote PM, Slorach C, Hui W, Piella G, Aguado AM, Nogueira M, Mertens L, Bijnens BH, Friedberg MK. Machine-learning–based exploration to identify remodeling patterns associated with death or heart-transplant in pediatric-dilated cardiomyopathy. J Heart Lung Transplant. 2022;41(4):516-26. DOI: 10.1016/j.healun.2021.11.020
• dc.identifier.doi http://dx.doi.org/10.1016/j.healun.2021.11.020
• dc.identifier.issn 1053-2498
• dc.identifier.uri http://hdl.handle.net/10230/56051
• dc.language.iso eng
• dc.publisher Elsevier
• dc.relation.ispartof The Journal of Heart and Lung Transplantation. 2022;41(4):516-26.
• dc.relation.isreferencedby https://www.jhltonline.org/cms/10.1016/j.healun.2021.11.020/attachment/c3938e73-195d-40da-92d3-bb8ea510f1ee/mmc1.docx
• dc.relation.isreferencedby https://www.jhltonline.org/cms/10.1016/j.healun.2021.11.020/attachment/3cbd1387-4134-42ab-bef1-ca99b89361c2/mmc2.docx
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/801370
• dc.rights 2021 The Author(s). Published by Elsevier Inc. on behalf of International Society for Heart and Lung Transplantation. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/4.0/
• dc.subject.keyword dilated cardiomyopathy
• dc.subject.keyword pediatrics
• dc.subject.keyword heart failure
• dc.subject.keyword machine-learning
• dc.subject.keyword echocardiography
• dc.subject.keyword strain
• dc.subject.keyword death
• dc.subject.keyword heart transplantation
• dc.title Machine-learning–based exploration to identify remodeling patterns associated with death or heart-transplant in pediatric-dilated cardiomyopathy
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/publishedVersion