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
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
1253-1267Informations 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.