Predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementCentral MessagePerspective

Objective: After transcatheter aortic valve replacement, the mean transvalvular pressure gradient indicates the effectiveness of the therapy. The objective is to develop artificial intelligence to predict the post–transcatheter aortic valve replacement aortic valve pressure gradient and aortic valve...

Full description

Saved in:
Bibliographic Details
Main Authors: Anoushka Dasi, BS, Beom Lee, MS, Venkateshwar Polsani, MD, FACC, FASE, Pradeep Yadav, MD, FACC, Lakshmi Prasad Dasi, PhD, FACC, FAIMBE, Vinod H. Thourani, MD, FACS, FACC
Format: Article
Language:English
Published: Elsevier 2024-02-01
Series:JTCVS Techniques
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666250723004625
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849398947883253760
author Anoushka Dasi, BS
Beom Lee, MS
Venkateshwar Polsani, MD, FACC, FASE
Pradeep Yadav, MD, FACC
Lakshmi Prasad Dasi, PhD, FACC, FAIMBE
Vinod H. Thourani, MD, FACS, FACC
author_facet Anoushka Dasi, BS
Beom Lee, MS
Venkateshwar Polsani, MD, FACC, FASE
Pradeep Yadav, MD, FACC
Lakshmi Prasad Dasi, PhD, FACC, FAIMBE
Vinod H. Thourani, MD, FACS, FACC
author_sort Anoushka Dasi, BS
collection DOAJ
description Objective: After transcatheter aortic valve replacement, the mean transvalvular pressure gradient indicates the effectiveness of the therapy. The objective is to develop artificial intelligence to predict the post–transcatheter aortic valve replacement aortic valve pressure gradient and aortic valve area from preprocedural echocardiography and computed tomography data. Methods: A retrospective study was conducted on patients who underwent transcatheter aortic valve replacement due to aortic valve stenosis. A total of 1091 patients were analyzed for pressure gradient predictions (mean age 76.8 ± 9.2 years, 57.8% male), and 1063 patients were analyzed for aortic valve area predictions (mean age 76.7 ± 9.3 years, 57.2% male). An artificial intelligence learning model was trained (training: n = 663 patients, validation: n = 206 patients) and tested (testing: n = 222 patients) to predict pressure gradient, and a separate artificial intelligence learning model was trained (training: n = 640 patients, validation: n = 218 patients) and tested (testing: n = 205 patients) for predicting aortic valve area. Results: The mean absolute error for pressure gradient and aortic valve area predictions was 3.0 mm Hg and 0.45 cm2, respectively. Valve sheath size, body surface area, and age were determined to be the top 3 predictors for pressure gradient, and valve sheath size, left ventricular ejection fraction, and aortic annulus mean diameter were identified to be the top 3 predictors of post–transcatheter aortic valve replacement aortic valve area. A training dataset size of more than 500 patients demonstrated good robustness of the artificial intelligence models for pressure gradient and aortic valve area. Conclusions: The artificial intelligence–based algorithm has demonstrated potential in predicting post–transcatheter aortic valve replacement transvalvular pressure gradient predictions for patients with aortic valve stenosis. Further studies are necessary to differentiate pressure gradient between valve types.
format Article
id doaj-art-0744ee7223ba4d70897a0bd2cb4db982
institution Kabale University
issn 2666-2507
language English
publishDate 2024-02-01
publisher Elsevier
record_format Article
series JTCVS Techniques
spelling doaj-art-0744ee7223ba4d70897a0bd2cb4db9822025-08-20T03:38:27ZengElsevierJTCVS Techniques2666-25072024-02-012351710.1016/j.xjtc.2023.11.011Predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementCentral MessagePerspectiveAnoushka Dasi, BS0Beom Lee, MS1Venkateshwar Polsani, MD, FACC, FASE2Pradeep Yadav, MD, FACC3Lakshmi Prasad Dasi, PhD, FACC, FAIMBE4Vinod H. Thourani, MD, FACS, FACC5Department of Biomedical Engineering, Ohio State University, Columbus, OhioDepartment of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GaDepartment of Cardiac Surgery, Piedmont Heart Institute, Atlanta, GaDepartment of Cardiac Surgery, Piedmont Heart Institute, Atlanta, GaDepartment of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GaDepartment of Cardiac Surgery, Piedmont Heart Institute, Atlanta, Ga; Address for reprints: Vinod H. Thourani, MD, FACS, FACC, Department of Cardiovascular Surgery, Piedmont Heart Institute, 95 Collier Rd Suite 5015, Atlanta, GA 30309.Objective: After transcatheter aortic valve replacement, the mean transvalvular pressure gradient indicates the effectiveness of the therapy. The objective is to develop artificial intelligence to predict the post–transcatheter aortic valve replacement aortic valve pressure gradient and aortic valve area from preprocedural echocardiography and computed tomography data. Methods: A retrospective study was conducted on patients who underwent transcatheter aortic valve replacement due to aortic valve stenosis. A total of 1091 patients were analyzed for pressure gradient predictions (mean age 76.8 ± 9.2 years, 57.8% male), and 1063 patients were analyzed for aortic valve area predictions (mean age 76.7 ± 9.3 years, 57.2% male). An artificial intelligence learning model was trained (training: n = 663 patients, validation: n = 206 patients) and tested (testing: n = 222 patients) to predict pressure gradient, and a separate artificial intelligence learning model was trained (training: n = 640 patients, validation: n = 218 patients) and tested (testing: n = 205 patients) for predicting aortic valve area. Results: The mean absolute error for pressure gradient and aortic valve area predictions was 3.0 mm Hg and 0.45 cm2, respectively. Valve sheath size, body surface area, and age were determined to be the top 3 predictors for pressure gradient, and valve sheath size, left ventricular ejection fraction, and aortic annulus mean diameter were identified to be the top 3 predictors of post–transcatheter aortic valve replacement aortic valve area. A training dataset size of more than 500 patients demonstrated good robustness of the artificial intelligence models for pressure gradient and aortic valve area. Conclusions: The artificial intelligence–based algorithm has demonstrated potential in predicting post–transcatheter aortic valve replacement transvalvular pressure gradient predictions for patients with aortic valve stenosis. Further studies are necessary to differentiate pressure gradient between valve types.http://www.sciencedirect.com/science/article/pii/S2666250723004625AIaortic stenosisaortic valveTAVR
spellingShingle Anoushka Dasi, BS
Beom Lee, MS
Venkateshwar Polsani, MD, FACC, FASE
Pradeep Yadav, MD, FACC
Lakshmi Prasad Dasi, PhD, FACC, FAIMBE
Vinod H. Thourani, MD, FACS, FACC
Predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementCentral MessagePerspective
JTCVS Techniques
AI
aortic stenosis
aortic valve
TAVR
title Predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementCentral MessagePerspective
title_full Predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementCentral MessagePerspective
title_fullStr Predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementCentral MessagePerspective
title_full_unstemmed Predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementCentral MessagePerspective
title_short Predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementCentral MessagePerspective
title_sort predicting pressure gradient using artificial intelligence for transcatheter aortic valve replacementcentral messageperspective
topic AI
aortic stenosis
aortic valve
TAVR
url http://www.sciencedirect.com/science/article/pii/S2666250723004625
work_keys_str_mv AT anoushkadasibs predictingpressuregradientusingartificialintelligencefortranscatheteraorticvalvereplacementcentralmessageperspective
AT beomleems predictingpressuregradientusingartificialintelligencefortranscatheteraorticvalvereplacementcentralmessageperspective
AT venkateshwarpolsanimdfaccfase predictingpressuregradientusingartificialintelligencefortranscatheteraorticvalvereplacementcentralmessageperspective
AT pradeepyadavmdfacc predictingpressuregradientusingartificialintelligencefortranscatheteraorticvalvereplacementcentralmessageperspective
AT lakshmiprasaddasiphdfaccfaimbe predictingpressuregradientusingartificialintelligencefortranscatheteraorticvalvereplacementcentralmessageperspective
AT vinodhthouranimdfacsfacc predictingpressuregradientusingartificialintelligencefortranscatheteraorticvalvereplacementcentralmessageperspective