Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 13;6(3):340-349.
doi: 10.1093/ehjdh/ztaf006. eCollection 2025 May.

Machine-learning phenotyping of patients with functional mitral regurgitation undergoing transcatheter edge-to-edge repair: the MITRA-AI study

Fabrizio D'Ascenzo  1   2 , Filippo Angelini  1   2 , Corrado Pancotti  3 , Pier Paolo Bocchino  1   2 , Cristina Giannini  4 , Filippo Finizio  5 , Marianna Adamo  6 , Victoria Camman  7 , Nuccia Morici  8 , Leor Perl  9 , Saverio Muscoli  6   10 , Gabriele Crimi  11   12 , Paolo Boretto  1   2 , Ovidio de Filippo  1   2 , Luca Baldetti  13 , Giuseppe Biondi-Zoccai  14   15 , Federico Conrotto  1   2 , Sonia Petronio  1   2 , Arturo Giordano  11 , Rodrigo Estévez-Loureiro  16 , Davide Stolfo  17   18 , Christian Templin  6 , Mauro Chiarito  19   20 , Elena Cavallone  1   2 , Veronica Dusi  1   2 , Gianluca Alunni  1   2 , Jacopo Oreglia  21 , Mario Iannaccone  22 , Marco Pocar  7   23 , Matteo Pagnesi  24 , Stefano Pidello  1   2   4 , Ran Kornowski  8 , Piero Fariselli  3 , Simone Frea  1   2 , Michele La Torre  24 , Claudia Raineri  1   2 , Giuseppe Patti  11 , Italo Porto  11 , Antonio Montefusco  1   2 , Sergio Raposeiras Roubin  15 , Gaetano Maria De Ferrari  1   2
Affiliations

Machine-learning phenotyping of patients with functional mitral regurgitation undergoing transcatheter edge-to-edge repair: the MITRA-AI study

Fabrizio D'Ascenzo et al. Eur Heart J Digit Health. .

Abstract

Aims: Severe functional mitral regurgitation (FMR) may benefit from mitral transcatheter edge-to-edge repair (TEER), but selection of patients remains to be optimized.

Objectives: The aim of this study was to use machine-learning (ML) approaches to uncover concealed connections between clinical, echocardiographic, and haemodynamic data associated with patients' outcomes.

Methods and results: Consecutive patients undergoing TEER from 2009 to 2020 were included in the MITRA-AI registry. The primary endpoint was a composite of cardiovascular death or heart failure (HF) hospitalization at 1 year. External validation was performed on the Mitrascore cohort. 822 patients were included. The composite primary endpoint occurred in 250 (30%) patients. Four clusters with decreasing risk of the primary endpoint were identified (42, 37, 25, and 20% from Cluster 1 to Cluster 4, respectively). Clusters were combined into a high-risk (Clusters 1 and 2) and a low-risk phenotype (Clusters 3 and 4). High-risk phenotype patients had larger left ventriculars (LVs) (>107 mL/m2), lower left ventricular ejection fraction (<35%), and more prevalent ischaemic aetiology compared with low-risk phenotype patients. Within low-risk groups, permanent atrial fibrillation amplified that of HF hospitalizations. In the Mitrascore cohort, the incidence of the primary endpoint was 48, 52, 35, and 42% across clusters.

Conclusion: A ML analysis identified meaningful clinical phenotypic presentations in FMR undergoing TEER, with significant differences in terms of cardiovascular death and HF hospitalizations, confirmed in an external validation cohort.

Keywords: Artificial intelligence; Machine-learning; MitraClip; Mitral regurgitation; Transcatheter mitral valve repair.

PubMed Disclaimer

Conflict of interest statement

Conflict of interest: none declared.

Figures

Graphical Abstract
Graphical Abstract
Figure 1
Figure 1
Distribution of dichotomic a priori variables according to clusters. AF, atrial fibrillation; MI, myocardial infarction.
Figure 2
Figure 2
Distribution of continuous variables according to clusters (violin plot). BMI, body mass index; LVEDVi, left ventricle end-diastolic volume index; LVEF, left ventricle ejection fraction; sPAP, systolic pulmonary artery pressure; TAPSE, tricuspid annular plane excursion.
Figure 3
Figure 3
Incidence of primary and secondary endpoint according to clustering. CV, cardiovascular; HF, heart failure.
Figure 4
Figure 4
Incidence of events according to clustering in Mitrascore dataset. CV, cardiovascular; HF, heart failure.
Figure 5
Figure 5
Net reclassification index on the derivation cohort on the left and on the validation on the right (green means improvement in classification, yellow no difference, red worsening with AI model set as reference). NRI, net reclassification index.
Figure 6
Figure 6
Incidence of events according to clustering in optimal medical therapy dataset. CV, cardiovascular; HF, heart failure.
See this image and copyright information in PMC

References

    1. d’Arcy JL, Coffey S, Loudon MA, Kennedy A, Pearson-Stuttard J, Birks J, et al. Large-scale community echocardiographic screening reveals a major burden of undiagnosed valvular heart disease in older people: the OxVALVE population cohort study. Eur Heart J 2016;37:3515–3512. - PMC - PubMed
    1. Asgar AW, Mack MJ, Stone GW. Secondary mitral regurgitation in heart failure: pathophysiology, prognosis, and therapeutic considerations. J Am Coll Cardiol 2015;65:1231–1248. - PubMed
    1. Mesi O, Gad MM, Crane AD, Ramchand J, Puri R, Layoun H, et al. Severe atrial functional mitral regurgitation: clinical and echocardiographic characteristics, management and outcomes. JACC Cardiovasc Imaging 2021;14:797–808. - PubMed
    1. Packer M, Grayburn PA. New evidence supporting a novel conceptual framework for distinguishing proportionate and disproportionate functional mitral regurgitation. JAMA Cardiol 2020;5:469–475. - PubMed
    1. Ooms JF, Bouwmeester S, Debonnaire P, Nasser R, Voigt J-U, Schotborgh MA, et al. Transcatheter edge-to-edge repair in proportionate versus disproportionate functional mitral regurgitation. J Am Soc Echocardiogr 2022;35:105–115.e. - PubMed