Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement

Abstract Cerebrovascular events (CVE) are among the most feared complications of transcatheter aortic valve replacement (TAVR). CVE appear difficult to predict due to their multifactorial origin incompletely explained by clinical predictors. We aimed to build a deep learning-based predictive tool fo...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Taishi Okuno, Pavel Overtchouk, Masahiko Asami, Daijiro Tomii, Stefan Stortecky, Fabien Praz, Jonas Lanz, George C. M. Siontis, Christoph Gräni, Stephan Windecker, Thomas Pilgrim
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/58810c58ee17474f9308606b1ebbbfdf
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:58810c58ee17474f9308606b1ebbbfdf
record_format dspace
spelling oai:doaj.org-article:58810c58ee17474f9308606b1ebbbfdf2021-12-02T18:48:09ZDeep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement10.1038/s41598-021-98265-52045-2322https://doaj.org/article/58810c58ee17474f9308606b1ebbbfdf2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98265-5https://doaj.org/toc/2045-2322Abstract Cerebrovascular events (CVE) are among the most feared complications of transcatheter aortic valve replacement (TAVR). CVE appear difficult to predict due to their multifactorial origin incompletely explained by clinical predictors. We aimed to build a deep learning-based predictive tool for TAVR-related CVE. Integrated clinical and imaging characteristics from consecutive patients enrolled into a prospective TAVR registry were analysed. CVE comprised any strokes and transient ischemic attacks. Predictive variables were selected by recursive feature reduction to train an autoencoder predictive model. Area under the curve (AUC) represented the model’s performance to predict 30-day CVE. Among 2279 patients included between 2007 and 2019, both clinical and imaging data were available in 1492 patients. Median age was 83 years and STS score was 4.6%. Acute (< 24 h) and subacute (day 2–30) CVE occurred in 19 (1.3%) and 36 (2.4%) patients, respectively. The occurrence of CVE was associated with an increased risk of death (HR [95% CI] 2.62 [1.82–3.78]). The constructed predictive model uses less than 107 clinical and imaging variables and has an AUC of 0.79 (0.65–0.93). TAVR-related CVE can be predicted using a deep learning-based predictive algorithm. The model is implemented online for broad usage.Taishi OkunoPavel OvertchoukMasahiko AsamiDaijiro TomiiStefan StorteckyFabien PrazJonas LanzGeorge C. M. SiontisChristoph GräniStephan WindeckerThomas PilgrimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Taishi Okuno
Pavel Overtchouk
Masahiko Asami
Daijiro Tomii
Stefan Stortecky
Fabien Praz
Jonas Lanz
George C. M. Siontis
Christoph Gräni
Stephan Windecker
Thomas Pilgrim
Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement
description Abstract Cerebrovascular events (CVE) are among the most feared complications of transcatheter aortic valve replacement (TAVR). CVE appear difficult to predict due to their multifactorial origin incompletely explained by clinical predictors. We aimed to build a deep learning-based predictive tool for TAVR-related CVE. Integrated clinical and imaging characteristics from consecutive patients enrolled into a prospective TAVR registry were analysed. CVE comprised any strokes and transient ischemic attacks. Predictive variables were selected by recursive feature reduction to train an autoencoder predictive model. Area under the curve (AUC) represented the model’s performance to predict 30-day CVE. Among 2279 patients included between 2007 and 2019, both clinical and imaging data were available in 1492 patients. Median age was 83 years and STS score was 4.6%. Acute (< 24 h) and subacute (day 2–30) CVE occurred in 19 (1.3%) and 36 (2.4%) patients, respectively. The occurrence of CVE was associated with an increased risk of death (HR [95% CI] 2.62 [1.82–3.78]). The constructed predictive model uses less than 107 clinical and imaging variables and has an AUC of 0.79 (0.65–0.93). TAVR-related CVE can be predicted using a deep learning-based predictive algorithm. The model is implemented online for broad usage.
format article
author Taishi Okuno
Pavel Overtchouk
Masahiko Asami
Daijiro Tomii
Stefan Stortecky
Fabien Praz
Jonas Lanz
George C. M. Siontis
Christoph Gräni
Stephan Windecker
Thomas Pilgrim
author_facet Taishi Okuno
Pavel Overtchouk
Masahiko Asami
Daijiro Tomii
Stefan Stortecky
Fabien Praz
Jonas Lanz
George C. M. Siontis
Christoph Gräni
Stephan Windecker
Thomas Pilgrim
author_sort Taishi Okuno
title Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement
title_short Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement
title_full Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement
title_fullStr Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement
title_full_unstemmed Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement
title_sort deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/58810c58ee17474f9308606b1ebbbfdf
work_keys_str_mv AT taishiokuno deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT pavelovertchouk deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT masahikoasami deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT daijirotomii deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT stefanstortecky deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT fabienpraz deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT jonaslanz deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT georgecmsiontis deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT christophgrani deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT stephanwindecker deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
AT thomaspilgrim deeplearningbasedpredictionofearlycerebrovasculareventsaftertranscatheteraorticvalvereplacement
_version_ 1718377623813357568