Machine learning identifies pathophysiologically and prognostically informative phenotypes among patients with mitral regurgitation undergoing transcatheter edge-to-edge repair. (3rd February 2023)

• Record Type: Journal Article
• Authors: Trenkwalder, Teresa; Lachmann, Mark; Stolz, Lukas; Fortmeier, Vera; Covarrubias, Héctor Alfonso Alvarez; Rippen, Elena; Schürmann, Friederike; Presch, Antonia; von Scheidt, Moritz; Ruff, Celine; Hesse, Amelie; Gerçek, Muhammed; Mayr, N Patrick; Ott, Ilka; Schuster, Tibor; Harmsen, Gerhard; Yuasa, Shinsuke; Kufner, Sebastian; Hoppmann, Petra; Kupatt, Christian; Schunkert, Heribert; Kastrati, Adnan; Laugwitz, Karl-Ludwig; Rudolph, Volker; Joner, Michael; Hausleiter, Jörg; Xhepa, Erion
• Is Part Of: European heart journal. Volume 24:Number 5(2023)
• Page Start: 574
• Page End: 587
• Publication Date: 2023-02-03
• Subjects: mitral regurgitation -- transcatheter edge-to-edge repair -- cardiac damage -- machine learning -- unsupervised agglomerative clustering -- artificial neural network; Cardiovascular system -- Imaging -- Periodicals; Heart -- Imaging -- Periodicals; 616.10754
• DOI: 10.1093/ehjci/jead013
• Languages: English
• ISSNs: 2047-2404

Abstract

Abstract: Aims: Patients with mitral regurgitation (MR) present with considerable heterogeneity in cardiac damage depending on underlying aetiology, disease progression, and comorbidities. This study aims to capture their cardiopulmonary complexity by employing a machine-learning (ML)-based phenotyping approach. Methods and results: Data were obtained from 1426 patients undergoing mitral valve transcatheter edge-to-edge repair (MV TEER) for MR. The ML model was developed using 609 patients (derivation cohort) and validated on 817 patients from two external institutions. Phenotyping was based on echocardiographic data, and ML-derived phenotypes were correlated with 5-year outcomes. Unsupervised agglomerative clustering revealed four phenotypes among the derivation cohort: Cluster 1 showed preserved left ventricular ejection fraction (LVEF; 56.5 ± 7.79%) and regular left ventricular end-systolic diameter (LVESD; 35.2 ± 7.52 mm); 5-year survival in Cluster 1, hereinafter serving as a reference, was 60.9%. Cluster 2 presented with preserved LVEF (55.7 ± 7.82%) but showed the largest mitral valve effective regurgitant orifice area (0.623 ± 0.360 cm 2 ) and highest systolic pulmonary artery pressures (68.4 ± 16.2 mmHg); 5-year survival ranged at 43.7% ( P -value: 0.032). Cluster 3 was characterized by impaired LVEF (31.0 ± 10.4%) and enlarged LVESD (53.2 ± 10.9 mm); 5-year survival was reduced to 38.3% ( P -value: <0.001). The poorest 5-year survival (23.8%; P -value: <0.001) was observed in Cluster 4 with biatrial dilatation (left atrial volume: 312 ± 113 mL; right atrial area: 46.0 ± 8.83 cm 2 ) although LVEF was only slightly reduced (51.5 ± 11.0%). Importantly, the prognostic significance of ML-derived phenotypes was externally confirmed. Conclusion: ML-enabled phenotyping captures the complexity of extra-mitral valve cardiac damage, which does not necessarily occur in a sequential fashion. This novel phenotyping approach can refine risk stratification in patients undergoing MV TEER in the future. Graphical Abstract: Graphical Abstract A machine-learning-based phenotyping approach facilitates to capture the complexity of cardiac damage as commonly encountered in patients presenting with mitral regurgitation. Patients with mitral regurgitation typically present with considerable heterogeneity, depending on the underlying aetiology, disease progression, and comorbidities. We hereby demonstrate that a combination of unsupervised and supervised machine-learning techniques aids in capturing the complexity of cardiac morphology and function. Unsupervised agglomerative clustering unravelled four novel pathophysiologically and prognostically informative phenotypes among patients with symptomatic mitral regurgitation undergoing mitral valve transcatheter edge-to-edge repair. Pre-procedural assignment of patients to clusters by employing an artificial neural network can thus refine prognostic assessment in future clinical practice and possibly identify additional therapeutic targets to improve survival in high-risk clusters. LA volume, left atrial volume; LVEF, left ventricular ejection fraction; LVESD, left ventricular end-systolic diameter; MV EROA, mitral valve effective regurgitant orifice area; RA area, right atrial area; sPAP, systolic pulmonary artery pressure; TAPSE, tricuspid annular plane systolic excursion.