Artificial Intelligence-Derived Computed Tomography Phenotyping for Cardiovascular Risk Stratification in Transcatheter Mitral Valve Replacement.
Authors
Affiliations (21)
Affiliations (21)
- Department of Cardiac and Thoracic Aortic Surgery, Medical University of Vienna, 1090 Vienna, Austria.
- Medizinische Klinik I, LMU University Hospital, 81377 Munich, Germany.
- Department of Cardiology, University Medical Center Mainz, 55131 Mainz, Germany.
- Department of Cardiothoracic Surgery, Heart Center, University Hospital Cologne, 50937 Cologne, Germany.
- Department of Cardiology, Heart and Diabetes Center North Rhine-Westphalia, Ruhr University Bochum, 44801 Bad Oeynhausen, Germany.
- Department of Cardiac Surgery, University Hospital Frankfurt, 60590 Frankfurt, Germany.
- Department of Cardiac Surgery, Heart Center, University Hospital Cologne, 50937 Cologne, Germany.
- Department for Cardiac, Vascular and Thoracic Surgery, Kepler University Hospital Linz, 4020 Linz, Austria.
- Valve Center, IRCCS Ospedale San Raffaele, University Vita-Salute San Raffaele, 20132 Milan, Italy.
- Department of Cardiac Surgery and Heart Transplantation, Azienda Ospedaliera San Camillo Forlanini, 00152 Rome, Italy.
- Division of Cardiac Surgery, Spedali Civili di Brescia, University of Brescia, 25121 Brescia, Italy.
- Department of Surgical, Medical and Molecular Pathology and Critical Care Medicine, University of Pisa, 56126 Pisa, Italy.
- Servicio Cirugía Cardíaca, Hospital Álvaro Cunqueiro, 36312 Vigo, Spain.
- Department of Cardiac Surgery, Inselspital University Hospital Bern, 3010 Bern, Switzerland.
- Department of Cardiovascular and Thoracic Surgery, Cliniques Universitaires Saint-Luc, 1200 Brussels, Belgium.
- Department of Cardiovascular Medicine, University Hospital Leuven, 3000 Leuven, Belgium.
- Department of Cardiovascular Sciences, KU Leuven, 3000 Leuven, Belgium.
- German Centre for Cardiovascular Research, Munich Heart Alliance, 80336 Munich, Germany.
- Division of Cardiovascular and Interventional Radiology, Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, 1090 Vienna, Austria.
- Institute of Clinical Biometrics, Center for Medical Data Science, Medical University of Vienna, 1090 Vienna, Austria.
- Division of Cardiac Surgery, Department of Surgery, Medical University Graz, 8010 Graz, Austria.
Abstract
<b>Background:</b> Despite high procedural success of transcatheter mitral valve replacement (TMVR), mortality remains substantial, and conventional risk scores inadequately reflect the specific risk profile of this high-risk population. Artificial intelligence (AI)-derived analysis may enable TMVR-specific risk assessment using routinely acquired computed tomography (CT). <b>Methods:</b> In a retrospective European multicenter registry, AI-based segmentation of harmonized real-world pre-procedural cardiac CT with variable thoracic and upper-abdominal coverage was applied in patients undergoing TMVR with the Tendyne<sup>TM</sup> system (134 patients; 346 CT-derived variables retained for high-dimensional screening). One-year cardiovascular mortality was assessed using Cox proportional hazards models with Benjamini-Hochberg false discovery rate correction. STS- and EuroSCORE II-adjusted analyses and a targeted coronary-ventricular coupling analysis were performed. <b>Results:</b> In the STS-adjusted Cox analysis, nine AI-derived CT parameters met the 10% FDR discovery threshold for cardiovascular mortality, spanning skeletal (n = 3), muscular (n = 1), and cardiopulmonary phenotypes (n = 5), whereas three parameters met this threshold in CT-only analyses. Coronary-ventricular coupling, defined as coronary artery volume relative to left ventricular end-diastolic volume, was significantly associated with lower 1-year cardiovascular mortality in the CT-only analysis (HR per IQR 0.47, 95% CI 0.22-1.00; <i>p</i> = 0.049) and after EuroSCORE II adjustment (HR 0.47, 95% CI 0.22-0.99; <i>p</i> = 0.046), while the STS-adjusted estimate remained directionally consistent but did not reach statistical significance (HR 0.49, 95% CI 0.23-1.05; <i>p</i> = 0.067). <b>Conclusions:</b> AI-based CT phenotyping identifies imaging-derived markers associated with cardiovascular mortality beyond information captured by conventional surgical risk scores in TMVR patients. Coronary-ventricular coupling emerges as a promising automated CT-derived imaging marker with a biologically plausible pathophysiological basis, linking coronary arterial volume to ventricular size in mitral valve disease.