In Circulation. Arrhythmia and electrophysiology
Background - Electrocardiogram (ECG) interpretation requires expertise and is mostly based on physician recognition of specific patterns, which may be challenging in rare cardiac diseases. Deep neural networks (DNN) can discover complex features in ECGs and may facilitate the detection of novel features which possibly play a pathophysiological role in relatively unknown diseases. Using a cohort of phospholamban (PLN) p.Arg14del mutation carriers, we aimed to investigate whether a novel DNN-based approach can identify established ECG features, but moreover we aimed to expand our knowledge on novel ECG features in these patients. Methods - A DNN was developed on 12-lead median beat ECGs of 69 patients and 1380 matched controls and independently evaluated on 17 patients and 340 controls. Differentiating features were visualized using Guided Grad-CAM++. Novel ECG features were tested for their diagnostic value by adding them to a logistic regression model including established ECG features. Results - The DNN showed excellent discriminatory performance with a c-statistic of 0.95 (95% confidence interval 0.91-0.99) and sensitivity and specificity of 0.82 and 0.93, respectively. Visualizations revealed established ECG features (low QRS voltages and T-wave inversions), specified these features (e.g. R and T-wave attenuation in V2/V3) and identified novel PLN-specific ECG features (e.g. increased PR-duration). The logistic regression baseline model improved significantly when augmented with the identified features (p<0.001). Conclusions - A DNN-based feature detection approach was able to discover and visualize disease-specific ECG features in PLN mutation carriers and revealed yet unidentified features. This novel approach may help advance diagnostic capabilities in daily practice.
van de Leur Rutger, Taha Karim, Bos Max N, van der Heijden Jeroen F, Gupta Deepak, Cramer Maarten J, Hassink Rutger J, van der Harst Pim, Doevendans Pieter A, Asselbergs Folkert W, van Es René
deep learning, deep neural network, electrocardiogram, feature detection, phospholamban mutation