Predicting mortality after transcatheter aortic valve replacement using preprocedural CT

Abstract Transcatheter aortic valve replacement (TAVR) is a widely used intervention for patients with severe aortic stenosis. Identifying high-risk patients is crucial due to potential postprocedural complications. Currently, this involves manual clinical assessment and time-consuming radiological...

Full description

Saved in:
Bibliographic Details
Main Authors: David Brüggemann, Denis Cener, Nazar Kuzo, Shehab Anwer, Julia Kebernik, Matthias Eberhard, Hatem Alkadhi, Felix C. Tanner, Ender Konukoglu
Format: Article
Language:English
Published: Nature Portfolio 2024-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-63022-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850208676361535488
author David Brüggemann
Denis Cener
Nazar Kuzo
Shehab Anwer
Julia Kebernik
Matthias Eberhard
Hatem Alkadhi
Felix C. Tanner
Ender Konukoglu
author_facet David Brüggemann
Denis Cener
Nazar Kuzo
Shehab Anwer
Julia Kebernik
Matthias Eberhard
Hatem Alkadhi
Felix C. Tanner
Ender Konukoglu
author_sort David Brüggemann
collection DOAJ
description Abstract Transcatheter aortic valve replacement (TAVR) is a widely used intervention for patients with severe aortic stenosis. Identifying high-risk patients is crucial due to potential postprocedural complications. Currently, this involves manual clinical assessment and time-consuming radiological assessment of preprocedural computed tomography (CT) images by an expert radiologist. In this study, we introduce a probabilistic model that predicts post-TAVR mortality automatically using unprocessed, preprocedural CT and 25 baseline patient characteristics. The model utilizes CT volumes by automatically localizing and extracting a region of interest around the aortic root and ascending aorta. It then extracts task-specific features with a 3D deep neural network and integrates them with patient characteristics to perform outcome prediction. As missing measurements or even missing CT images are common in TAVR planning, the proposed model is designed with a probabilistic structure to allow for marginalization over such missing information. Our model demonstrates an AUROC of 0.725 for predicting all-cause mortality during postprocedure follow-up on a cohort of 1449 TAVR patients. This performance is on par with what can be achieved with lengthy radiological assessments performed by experts. Thus, these findings underscore the potential of the proposed model in automatically analyzing CT volumes and integrating them with patient characteristics for predicting mortality after TAVR.
format Article
id doaj-art-eb877de8ad714cb1af1c4967d8b8aeac
institution OA Journals
issn 2045-2322
language English
publishDate 2024-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-eb877de8ad714cb1af1c4967d8b8aeac2025-08-20T02:10:12ZengNature PortfolioScientific Reports2045-23222024-05-0114111110.1038/s41598-024-63022-xPredicting mortality after transcatheter aortic valve replacement using preprocedural CTDavid Brüggemann0Denis Cener1Nazar Kuzo2Shehab Anwer3Julia Kebernik4Matthias Eberhard5Hatem Alkadhi6Felix C. Tanner7Ender Konukoglu8Computer Vision Laboratory, ETH ZurichComputer Vision Laboratory, ETH ZurichDepartment of Cardiology, University Heart Center, University Hospital ZurichDepartment of Cardiology, University Heart Center, University Hospital ZurichInstitute for Diagnostic and Interventional Radiology, University Hospital ZurichInstitute for Diagnostic and Interventional Radiology, University Hospital ZurichInstitute for Diagnostic and Interventional Radiology, University Hospital ZurichDepartment of Cardiology, University Heart Center, University Hospital ZurichComputer Vision Laboratory, ETH ZurichAbstract Transcatheter aortic valve replacement (TAVR) is a widely used intervention for patients with severe aortic stenosis. Identifying high-risk patients is crucial due to potential postprocedural complications. Currently, this involves manual clinical assessment and time-consuming radiological assessment of preprocedural computed tomography (CT) images by an expert radiologist. In this study, we introduce a probabilistic model that predicts post-TAVR mortality automatically using unprocessed, preprocedural CT and 25 baseline patient characteristics. The model utilizes CT volumes by automatically localizing and extracting a region of interest around the aortic root and ascending aorta. It then extracts task-specific features with a 3D deep neural network and integrates them with patient characteristics to perform outcome prediction. As missing measurements or even missing CT images are common in TAVR planning, the proposed model is designed with a probabilistic structure to allow for marginalization over such missing information. Our model demonstrates an AUROC of 0.725 for predicting all-cause mortality during postprocedure follow-up on a cohort of 1449 TAVR patients. This performance is on par with what can be achieved with lengthy radiological assessments performed by experts. Thus, these findings underscore the potential of the proposed model in automatically analyzing CT volumes and integrating them with patient characteristics for predicting mortality after TAVR.https://doi.org/10.1038/s41598-024-63022-x
spellingShingle David Brüggemann
Denis Cener
Nazar Kuzo
Shehab Anwer
Julia Kebernik
Matthias Eberhard
Hatem Alkadhi
Felix C. Tanner
Ender Konukoglu
Predicting mortality after transcatheter aortic valve replacement using preprocedural CT
Scientific Reports
title Predicting mortality after transcatheter aortic valve replacement using preprocedural CT
title_full Predicting mortality after transcatheter aortic valve replacement using preprocedural CT
title_fullStr Predicting mortality after transcatheter aortic valve replacement using preprocedural CT
title_full_unstemmed Predicting mortality after transcatheter aortic valve replacement using preprocedural CT
title_short Predicting mortality after transcatheter aortic valve replacement using preprocedural CT
title_sort predicting mortality after transcatheter aortic valve replacement using preprocedural ct
url https://doi.org/10.1038/s41598-024-63022-x
work_keys_str_mv AT davidbruggemann predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct
AT deniscener predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct
AT nazarkuzo predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct
AT shehabanwer predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct
AT juliakebernik predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct
AT matthiaseberhard predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct
AT hatemalkadhi predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct
AT felixctanner predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct
AT enderkonukoglu predictingmortalityaftertranscatheteraorticvalvereplacementusingpreproceduralct