An Artificial Intelligence Algorithm for Detection of Severe Aortic Stenosis: A Clinical Cohort Study.
aortic stenosis
artificial intelligence
decision-support
echocardiography
Journal
JACC. Advances
ISSN: 2772-963X
Titre abrégé: JACC Adv
Pays: United States
ID NLM: 9918419284106676
Informations de publication
Date de publication:
Sep 2024
Sep 2024
Historique:
received:
01
03
2024
revised:
10
05
2024
accepted:
18
06
2024
medline:
7
10
2024
pubmed:
7
10
2024
entrez:
7
10
2024
Statut:
epublish
Résumé
Identifying individuals with severe aortic stenosis (AS) at high risk of mortality remains challenging using current clinical imaging methods. The purpose of this study was to evaluate an artificial intelligence decision support algorithm (AI-DSA) to augment the detection of severe AS within a well-resourced health care setting. Agnostic to clinical information, an AI-DSA trained to identify echocardiographic phenotype associated with an aortic valve area (AVA)<1 cm Performance of AI-DSA to detect the phenotype associated with an AVA<1 cm Without relying on left ventricular outflow tract measurements, an AI-DSA used echocardiographic reports to reliably identify the phenotype of severe AS. These results suggest possible utility for this AI-DSA to enhance detection of severe AS individuals at risk for adverse outcomes.
Sections du résumé
Background
UNASSIGNED
Identifying individuals with severe aortic stenosis (AS) at high risk of mortality remains challenging using current clinical imaging methods.
Objectives
UNASSIGNED
The purpose of this study was to evaluate an artificial intelligence decision support algorithm (AI-DSA) to augment the detection of severe AS within a well-resourced health care setting.
Methods
UNASSIGNED
Agnostic to clinical information, an AI-DSA trained to identify echocardiographic phenotype associated with an aortic valve area (AVA)<1 cm
Results
UNASSIGNED
Performance of AI-DSA to detect the phenotype associated with an AVA<1 cm
Conclusions
UNASSIGNED
Without relying on left ventricular outflow tract measurements, an AI-DSA used echocardiographic reports to reliably identify the phenotype of severe AS. These results suggest possible utility for this AI-DSA to enhance detection of severe AS individuals at risk for adverse outcomes.
Identifiants
pubmed: 39372458
doi: 10.1016/j.jacadv.2024.101176
pii: S2772-963X(24)00407-1
pmc: PMC11450902
doi:
Types de publication
Journal Article
Langues
eng
Pagination
101176Informations de copyright
© 2024 The Authors.
Déclaration de conflit d'intérêts
This work was supported by Echo IQ Pty Ltd. Dr Stewart is supported by the 10.13039/501100000925National Health and Medical Research Council of Australia (GNT1135894). Dr Strom is supported by the 10.13039/100000002National Institutes of Health (1K23HL144907, R01AG063937), 10.13039/100006520Edwards Lifesciences, Ultromics, HeartSciences, Anumana, and EchoIQ. Unrelated to this work, Dr Strom has served on the Scientific Advisory Board for Edwards Lifesciences and EchoIQ and has received consulting fees from Bracco Diagnostics, General Electric Healthcare, and Lantheus Medical Imaging. Prof Strange has received consulting fees from Edwards, Medtronic, and Echo IQ and has received speaker fees from Edwards, Medtronic, Abbott, and Echo IQ. Prof Playford has received consulting fees from Edwards, Medtronic, and Echo IQ. Prof Stewart has received consulting fees from Echo IQ.