Integrating Echocardiography Parameters With Explainable Artificial Intelligence for Data-Driven Clustering of Primary Mitral Regurgitation Phenotypes.

machine learning mitral valve intervention phenogrouping primary mitral regurgitation risk stratification

Journal

JACC. Cardiovascular imaging
ISSN: 1876-7591
Titre abrégé: JACC Cardiovasc Imaging
Pays: United States
ID NLM: 101467978

Informations de publication

Date de publication:
Oct 2023
Historique:
received: 01 11 2022
revised: 20 01 2023
accepted: 09 02 2023
pubmed: 14 5 2023
medline: 14 5 2023
entrez: 13 5 2023
Statut: ppublish

Résumé

Primary mitral regurgitation (MR) is a heterogeneous clinical disease requiring integration of echocardiographic parameters using guideline-driven recommendations to identify severe disease. The purpose of this preliminary study was to explore novel data-driven approaches to delineate phenotypes of MR severity that benefit from surgery. The authors used unsupervised and supervised machine learning and explainable artificial intelligence (AI) to integrate 24 echocardiographic parameters in 400 primary MR subjects from France (n = 243; development cohort) and Canada (n = 157; validation cohort) followed up during a median time of 3.2 years (IQR: 1.3-5.3 years) and 6.8 (IQR: 4.0-8.5 years), respectively. The authors compared the phenogroups' incremental prognostic value over conventional MR profiles and for the primary endpoint of all-cause mortality incorporating time-to-mitral valve repair/replacement surgery as a covariate for survival analysis (time-dependent exposure). High-severity (HS) phenogroups from the French cohort (HS: n = 117; low-severity [LS]: n = 126) and the Canadian cohort (HS: n = 87; LS: n = 70) showed improved event-free survival in surgical HS subjects over nonsurgical subjects (P = 0.047 and P = 0.020, respectively). A similar benefit of surgery was not seen in the LS phenogroup in both cohorts (P = 0.70 and P = 0.50, respectively). Phenogrouping showed incremental prognostic value in conventionally severe or moderate-severe MR subjects (Harrell C statistic improvement; P = 0.480; and categorical net reclassification improvement; P = 0.002). Explainable AI specified how each echocardiographic parameter contributed to phenogroup distribution. Novel data-driven phenogrouping and explainable AI aided in improved integration of echocardiographic data to identify patients with primary MR and improved event-free survival after mitral valve repair/replacement surgery.

Sections du résumé

BACKGROUND BACKGROUND
Primary mitral regurgitation (MR) is a heterogeneous clinical disease requiring integration of echocardiographic parameters using guideline-driven recommendations to identify severe disease.
OBJECTIVES OBJECTIVE
The purpose of this preliminary study was to explore novel data-driven approaches to delineate phenotypes of MR severity that benefit from surgery.
METHODS METHODS
The authors used unsupervised and supervised machine learning and explainable artificial intelligence (AI) to integrate 24 echocardiographic parameters in 400 primary MR subjects from France (n = 243; development cohort) and Canada (n = 157; validation cohort) followed up during a median time of 3.2 years (IQR: 1.3-5.3 years) and 6.8 (IQR: 4.0-8.5 years), respectively. The authors compared the phenogroups' incremental prognostic value over conventional MR profiles and for the primary endpoint of all-cause mortality incorporating time-to-mitral valve repair/replacement surgery as a covariate for survival analysis (time-dependent exposure).
RESULTS RESULTS
High-severity (HS) phenogroups from the French cohort (HS: n = 117; low-severity [LS]: n = 126) and the Canadian cohort (HS: n = 87; LS: n = 70) showed improved event-free survival in surgical HS subjects over nonsurgical subjects (P = 0.047 and P = 0.020, respectively). A similar benefit of surgery was not seen in the LS phenogroup in both cohorts (P = 0.70 and P = 0.50, respectively). Phenogrouping showed incremental prognostic value in conventionally severe or moderate-severe MR subjects (Harrell C statistic improvement; P = 0.480; and categorical net reclassification improvement; P = 0.002). Explainable AI specified how each echocardiographic parameter contributed to phenogroup distribution.
CONCLUSIONS CONCLUSIONS
Novel data-driven phenogrouping and explainable AI aided in improved integration of echocardiographic data to identify patients with primary MR and improved event-free survival after mitral valve repair/replacement surgery.

Identifiants

pubmed: 37178071
pii: S1936-878X(23)00113-4
doi: 10.1016/j.jcmg.2023.02.016
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

1253-1267

Informations de copyright

Copyright © 2023. Published by Elsevier Inc.

Déclaration de conflit d'intérêts

Funding Support and Author Disclosures This work was supported by funds from the National Science Foundation (#1920920) and National Institute of General Medical Sciences of the National Institutes of Health (#5U54GM104942-04) and by a research grant (FDN-143225) from the Canadian Institutes of Health Research (CIHR), Ottawa, Ontario, Canada. Mr Bernard is supported by a doctoral scholarship from CIHR. Dr Pibarot holds the Canada Research Chair in Valvular Heart Diseases from CIHR, Ottawa, Ontario, Canada. Dr Pibarot has received funding from Edwards Lifesciences, Medtronic, and Phoenix Cardiac Devices for echocardiography core laboratory analyses with no direct personal compensation. Dr Sengupta is a consultant for Kencor Health, RCE Technologies, and Ultromics. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.

Auteurs

Jérémy Bernard (J)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

Naveena Yanamala (N)

Robert Wood Johnson University Hospital, Rutgers Robert Wood Johnson Medical School, New Brunswick, New Jersey, USA.

Rohan Shah (R)

Robert Wood Johnson University Hospital, Rutgers Robert Wood Johnson Medical School, New Brunswick, New Jersey, USA.

Karthik Seetharam (K)

Robert Wood Johnson University Hospital, Rutgers Robert Wood Johnson Medical School, New Brunswick, New Jersey, USA.

Alexandre Altes (A)

Department of Cardiology, GCS-Groupement des Hôpitaux de l'Institut Catholique de Lille, Université Catholique de Lille, Lille, France.

Marlène Dupuis (M)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

Oumhani Toubal (O)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

Haïfa Mahjoub (H)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

Hélène Dumortier (H)

Department of Cardiology, GCS-Groupement des Hôpitaux de l'Institut Catholique de Lille, Université Catholique de Lille, Lille, France.

Jean Tartar (J)

Department of Cardiology, GCS-Groupement des Hôpitaux de l'Institut Catholique de Lille, Université Catholique de Lille, Lille, France.

Erwan Salaun (E)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

Kim O'Connor (K)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

Mathieu Bernier (M)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

Jonathan Beaudoin (J)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

Nancy Côté (N)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada.

André Vincentelli (A)

Cardiac Surgery Department, Centre Hospitalier Régional et Universitaire de Lille, Lille, France.

Florent LeVen (F)

Department of Cardiology, Hôpital La Cavale Blanche-Centre Hospitalier Regional Universitaire de Brest, Brest, France.

Sylvestre Maréchaux (S)

Department of Cardiology, GCS-Groupement des Hôpitaux de l'Institut Catholique de Lille, Université Catholique de Lille, Lille, France.

Philippe Pibarot (P)

Institut Universitaire de Cardiologie et de Pneumologie de Québec-Université Laval/Québec Heart and Lung Institute, Laval University, Québec City, Québec, Canada. Electronic address: philippe.pibarot@med.ulaval.ca.

Partho P Sengupta (PP)

Robert Wood Johnson University Hospital, Rutgers Robert Wood Johnson Medical School, New Brunswick, New Jersey, USA. Electronic address: partho.sengupta@rutgers.edu.

Classifications MeSH