External validation of artificial intelligence for detection of heart failure with preserved ejection fraction

Abstract Artificial intelligence (AI) models to identify heart failure (HF) with preserved ejection fraction (HFpEF) based on deep-learning of echocardiograms could help address under-recognition in clinical practice, but they require extensive validation, particularly in representative and complex...

Full description

Saved in:
Bibliographic Details
Main Authors: Ashley P. Akerman, Nora Al-Roub, Constance Angell-James, Madeline A. Cassidy, Rasheed Thompson, Lorenzo Bosque, Katharine Rainer, William Hawkes, Hania Piotrowska, Paul Leeson, Gary Woodward, Patricia A. Pellikka, Ross Upton, Jordan B. Strom
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-58283-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850145171996409856
author Ashley P. Akerman
Nora Al-Roub
Constance Angell-James
Madeline A. Cassidy
Rasheed Thompson
Lorenzo Bosque
Katharine Rainer
William Hawkes
Hania Piotrowska
Paul Leeson
Gary Woodward
Patricia A. Pellikka
Ross Upton
Jordan B. Strom
author_facet Ashley P. Akerman
Nora Al-Roub
Constance Angell-James
Madeline A. Cassidy
Rasheed Thompson
Lorenzo Bosque
Katharine Rainer
William Hawkes
Hania Piotrowska
Paul Leeson
Gary Woodward
Patricia A. Pellikka
Ross Upton
Jordan B. Strom
author_sort Ashley P. Akerman
collection DOAJ
description Abstract Artificial intelligence (AI) models to identify heart failure (HF) with preserved ejection fraction (HFpEF) based on deep-learning of echocardiograms could help address under-recognition in clinical practice, but they require extensive validation, particularly in representative and complex clinical cohorts for which they could provide most value. In this study enrolling patients with HFpEF (cases; n = 240), and age, sex, and year of echocardiogram matched controls (n = 256), we compare the diagnostic performance (discrimination, calibration, classification, and clinical utility) and prognostic associations (mortality and HF hospitalization) between an updated AI HFpEF model (EchoGo Heart Failure v2) and existing clinical scores (H2FPEF and HFA-PEFF). The AI HFpEF model and H2FPEF score demonstrate similar discrimination and calibration, but classification is higher with AI than H2FPEF and HFA-PEFF, attributable to fewer intermediate scores, due to discordant multivariable inputs. The continuous AI HFpEF model output adds information beyond the H2FPEF, and integration with existing scores increases correct management decisions. Those with a diagnostic positive result from AI have a two-fold increased risk of the composite outcome. We conclude that integrating an AI HFpEF model into the existing clinical diagnostic pathway would improve identification of HFpEF in complex clinical cohorts, and patients at risk of adverse outcomes.
format Article
id doaj-art-13cb174a6eab41fea182964fe867d92d
institution OA Journals
issn 2041-1723
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-13cb174a6eab41fea182964fe867d92d2025-08-20T02:28:09ZengNature PortfolioNature Communications2041-17232025-03-0116111210.1038/s41467-025-58283-7External validation of artificial intelligence for detection of heart failure with preserved ejection fractionAshley P. Akerman0Nora Al-Roub1Constance Angell-James2Madeline A. Cassidy3Rasheed Thompson4Lorenzo Bosque5Katharine Rainer6William Hawkes7Hania Piotrowska8Paul Leeson9Gary Woodward10Patricia A. Pellikka11Ross Upton12Jordan B. Strom13Ultromics Ltd, 4630 Kingsgate, Cascade Way, Oxford Business Park SouthRichard A. and Susan F. Smith Center for Outcomes Research in Cardiology, Division of Cardiology, Beth Israel Deaconess Medical CenterRichard A. and Susan F. Smith Center for Outcomes Research in Cardiology, Division of Cardiology, Beth Israel Deaconess Medical CenterRichard A. and Susan F. Smith Center for Outcomes Research in Cardiology, Division of Cardiology, Beth Israel Deaconess Medical CenterHoward University College of MedicineDrexel University College of MedicineRichard A. and Susan F. Smith Center for Outcomes Research in Cardiology, Division of Cardiology, Beth Israel Deaconess Medical CenterUltromics Ltd, 4630 Kingsgate, Cascade Way, Oxford Business Park SouthUltromics Ltd, 4630 Kingsgate, Cascade Way, Oxford Business Park SouthUltromics Ltd, 4630 Kingsgate, Cascade Way, Oxford Business Park SouthUltromics Ltd, 4630 Kingsgate, Cascade Way, Oxford Business Park SouthDepartment of Cardiovascular Medicine, Mayo ClinicUltromics Ltd, 4630 Kingsgate, Cascade Way, Oxford Business Park SouthRichard A. and Susan F. Smith Center for Outcomes Research in Cardiology, Division of Cardiology, Beth Israel Deaconess Medical CenterAbstract Artificial intelligence (AI) models to identify heart failure (HF) with preserved ejection fraction (HFpEF) based on deep-learning of echocardiograms could help address under-recognition in clinical practice, but they require extensive validation, particularly in representative and complex clinical cohorts for which they could provide most value. In this study enrolling patients with HFpEF (cases; n = 240), and age, sex, and year of echocardiogram matched controls (n = 256), we compare the diagnostic performance (discrimination, calibration, classification, and clinical utility) and prognostic associations (mortality and HF hospitalization) between an updated AI HFpEF model (EchoGo Heart Failure v2) and existing clinical scores (H2FPEF and HFA-PEFF). The AI HFpEF model and H2FPEF score demonstrate similar discrimination and calibration, but classification is higher with AI than H2FPEF and HFA-PEFF, attributable to fewer intermediate scores, due to discordant multivariable inputs. The continuous AI HFpEF model output adds information beyond the H2FPEF, and integration with existing scores increases correct management decisions. Those with a diagnostic positive result from AI have a two-fold increased risk of the composite outcome. We conclude that integrating an AI HFpEF model into the existing clinical diagnostic pathway would improve identification of HFpEF in complex clinical cohorts, and patients at risk of adverse outcomes.https://doi.org/10.1038/s41467-025-58283-7
spellingShingle Ashley P. Akerman
Nora Al-Roub
Constance Angell-James
Madeline A. Cassidy
Rasheed Thompson
Lorenzo Bosque
Katharine Rainer
William Hawkes
Hania Piotrowska
Paul Leeson
Gary Woodward
Patricia A. Pellikka
Ross Upton
Jordan B. Strom
External validation of artificial intelligence for detection of heart failure with preserved ejection fraction
Nature Communications
title External validation of artificial intelligence for detection of heart failure with preserved ejection fraction
title_full External validation of artificial intelligence for detection of heart failure with preserved ejection fraction
title_fullStr External validation of artificial intelligence for detection of heart failure with preserved ejection fraction
title_full_unstemmed External validation of artificial intelligence for detection of heart failure with preserved ejection fraction
title_short External validation of artificial intelligence for detection of heart failure with preserved ejection fraction
title_sort external validation of artificial intelligence for detection of heart failure with preserved ejection fraction
url https://doi.org/10.1038/s41467-025-58283-7
work_keys_str_mv AT ashleypakerman externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT noraalroub externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT constanceangelljames externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT madelineacassidy externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT rasheedthompson externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT lorenzobosque externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT katharinerainer externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT williamhawkes externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT haniapiotrowska externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT paulleeson externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT garywoodward externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT patriciaapellikka externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT rossupton externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction
AT jordanbstrom externalvalidationofartificialintelligencefordetectionofheartfailurewithpreservedejectionfraction