Dr. Jan Eckstein (Bad Oeynhausen / DE), Negin Moghadasi (Charlottesville, VA / US), Dr. Hermann Körperich (Bad Oeynhausen / DE), Elena Weise Valdés (Bad Oeynhausen / DE), Dr. Vanessa Sciacca (Bad Oeynhausen / DE), Dr. Lech Paluszkiewicz (Bad Oeynhausen / DE), Prof. Dr. Wolfgang Burchert (Bad Oeynhausen / DE), Dr. Misagh Piran (Bad Oeynhausen / DE)
Abstract-Text (inkl. Referenzen und Bildunterschriften)
Background: This study challenges state-of-the-art cardiac amyloidosis (CA) diagnostics by feeding multi-chamber strain and cardiac function into supervised machine (SVM) learning algorithms.Methods: Forty-three CA (32 males; 79 years (IQR 71; 85)), 20 patients with hypertrophic cardiomyopathy (HCM, 10 males; 63.9 years (±7.4)) and 44 healthy controls (CTRL, 23 males; 56.3 years (IQR 52.5; 62.9)) received cardiovascular magnetic resonance imaging. Left atrial, right atrial and right ventricular strain parameters and cardiac function generated a 41-feature matrix for decision tree (DT), k-nearest neighbor (KNN), SVM linear and SVM radial basis function (RBF) kernel algorithm processing. A 10-feature principal component analysis (PCA) was conducted using SVM linear and RBF.Results: Forty-one features resulted in diagnostic accuracies of 87.9% (AUC = 0.960) for SVM linear, 90.9% (0.996; Precision = 94%; Sensitivity = 100%; F1-Score = 97%) using RBF kernel, 84.9% (0.970) for KNN, and 78.8% (0.787) for DT. The 10-feature PCA achieved 78.9% (0.962) via linear SVM and 81.8% (0.996) via RBF SVM. Explained variance presented bi-atrial longitudinal strain and left and right atrial ejection fraction as valuable CA predictors.Conclusion: SVM RBF kernel achieved competitive diagnostic accuracies under supervised conditions. Machine learning of multi-chamber cardiac strain and function may offer novel perspectives for non-contrast clinical decision-support systems in CA diagnostics.
Fig. 1 Flow diagram representing the methodology of machine learning and classifier algorithms used.
Fig. 2. Diagnostic accuracies achieved by the various classifier algorithms.
Fig. 3. The confusion matrices for 41-feature k-nearest neighbor (KNN), decision tree (DT), SVM radial basis function (RBF) kernel and for 10-feature principal component analysis (PCA + SVM RBF kernel) are presented with corresponding performance statistics.