Harnessing feature extraction capacities from a pre-trained convolutional neural network (VGG-16) for the unsupervised distinction of aortic outflow velocity profiles in patients with severe aortic stenosis
-
- Mark Lachmann
- First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Straße 22 , 81675 Munich, Germany
-
- Elena Rippen
- First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Straße 22 , 81675 Munich, Germany
-
- Daniel Rueckert
- Institute for AI and Informatics in Medicine, Faculty of Informatics and Medicine, Klinikum rechts der Isar, Technical University of Munich , Munich , Germany
-
- Tibor Schuster
- Department of Family Medicine, McGill University , Montreal, Quebec , Canada
-
- Erion Xhepa
- Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany
-
- Moritz von Scheidt
- Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany
-
- Costanza Pellegrini
- Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany
-
- Teresa Trenkwalder
- Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany
-
- Tobias Rheude
- Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany
-
- Anja Stundl
- First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Straße 22 , 81675 Munich, Germany
-
- Ruth Thalmann
- First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Straße 22 , 81675 Munich, Germany
-
- Gerhard Harmsen
- Department of Physics, University of Johannesburg , Auckland Park , South Africa
-
- Shinsuke Yuasa
- Department of Cardiology, Keio University School of Medicine , Minato, Tokyo , Japan
-
- Heribert Schunkert
- Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany
-
- Adnan Kastrati
- Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany
-
- Michael Joner
- Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany
-
- Christian Kupatt
- First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Straße 22 , 81675 Munich, Germany
-
- Karl Ludwig Laugwitz
- First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Straße 22 , 81675 Munich, Germany
抄録
<jats:title>Abstract</jats:title> <jats:sec> <jats:title>Aims</jats:title> <jats:p>Hypothesizing that aortic outflow velocity profiles contain more valuable information about aortic valve obstruction and left ventricular contractility than can be captured by the human eye, features of the complex geometry of Doppler tracings from patients with severe aortic stenosis (AS) were extracted by a convolutional neural network (CNN).</jats:p> </jats:sec> <jats:sec> <jats:title>Methods and results</jats:title> <jats:p>After pre-training a CNN (VGG-16) on a large data set (ImageNet data set; 14 million images belonging to 1000 classes), the convolutional part was employed to transform Doppler tracings to 1D arrays. Among 366 eligible patients [age: 79.8 ± 6.77 years; 146 (39.9%) women] with pre-procedural echocardiography and right heart catheterization prior to transcatheter aortic valve replacement (TAVR), good quality Doppler tracings from 101 patients were analysed. The convolutional part of the pre-trained VGG-16 model in conjunction with principal component analysis and k-means clustering distinguished two shapes of aortic outflow velocity profiles. Kaplan–Meier analysis revealed that mortality in patients from Cluster 2 (n = 40, 39.6%) was significantly increased [hazard ratio (HR) for 2-year mortality: 3; 95% confidence interval (CI): 1–8.9]. Apart from reduced cardiac output and mean aortic valve gradient, patients from Cluster 2 were also characterized by signs of pulmonary hypertension, impaired right ventricular function, and right atrial enlargement. After training an extreme gradient boosting algorithm on these 101 patients, validation on the remaining 265 patients confirmed that patients assigned to Cluster 2 show increased mortality (HR for 2-year mortality: 2.6; 95% CI: 1.4–5.1, P-value: 0.004).</jats:p> </jats:sec> <jats:sec> <jats:title>Conclusion</jats:title> <jats:p>Transfer learning enables sophisticated pattern recognition even in clinical data sets of limited size. Importantly, it is the left ventricular compensation capacity in the face of increased afterload, and not so much the actual obstruction of the aortic valve, that determines fate after TAVR.</jats:p> </jats:sec>
収録刊行物
-
- European Heart Journal - Digital Health
-
European Heart Journal - Digital Health 3 (2), 153-168, 2022-04-22
Oxford University Press (OUP)