BACKGROUND The correct interpretation of the ECG is pivotal for the accurate diagnosis of many cardiac abnormalities, and conventional computerized interpretation has not been able to reach physician‐level accuracy in detecting (acute) cardiac abnormalities. This study aims to develop and validate a deep neural network for comprehensive automated ECG triage in daily practice. METHODS AND RESULTS We developed a 37‐layer convolutional residual deep neural network on a data set of free‐text physician‐annotated 12‐lead ECG s. The deep neural network was trained on a data set with 336.835 recordings from 142.040 patients and validated on an independent validation data set (n=984), annotated by a panel of 5 cardiologists electrophysiologists. The 12‐lead ECG s were acquired in all noncardiology departments of the University Medical Center Utrecht. The algorithm learned to classify these ECG s into the following 4 triage categories: normal, abnormal not acute, subacute, and acute. Discriminative performance is presented with overall and category‐specific concordance statistics, polytomous discrimination indexes, sensitivities, specificities, and positive and negative predictive values. The patients in the validation data set had a mean age of 60.4 years and 54.3% were men. The deep neural network showed excellent overall discrimination with an overall concordance statistic of 0.93 (95% CI , 0.92–0.95) and a polytomous discriminatory index of 0.83 (95% CI , 0.79–0.87). CONCLUSIONS This study demonstrates that an end‐to‐end deep neural network can be accurately trained on unstructured free‐text physician annotations and used to consistently triage 12‐lead ECG s. When further fine‐tuned with other clinical outcomes and externally validated in clinical practice, the demonstrated deep learning–based ECG interpretation can potentially improve time to treatment and decrease healthcare burden.

The inherited mutation (R14del) in the calcium regulatory protein phospholamban (PLN) is linked to malignant ventricular arrhythmia with poor prognosis starting at adolescence. However, the underlying early mechanisms that may serve as prognostic factors remain elusive. This study generated humanized mice in which the endogenous gene was replaced with either human wild type or R14del-PLN and addressed the early molecular and cellular pathogenic mechanisms. R14del-PLN mice exhibited stress-induced impairment of atrioventricular conduction, and prolongation of both ventricular activation and repolarization times in association with ventricular tachyarrhythmia, originating from the right ventricle (RV). Most of these distinct electrocardiographic features were remarkably similar to those in R14del-PLN patients. Studies in isolated cardiomyocytes revealed RV-specific calcium defects, including prolonged action potential duration, depressed calcium kinetics and contractile parameters, and elevated diastolic Ca-levels. Ca-sparks were also higher although SR Ca-load was reduced. Accordingly, stress conditions induced after contractions, and inclusion of the CaMKII inhibitor KN93 reversed this proarrhythmic parameter. Compensatory responses included altered expression of key genes associated with Ca-cycling. These data suggest that R14del-PLN cardiomyopathy originates with RV-specific impairment of Ca-cycling and point to the urgent need to improve risk stratification in asymptomatic carriers to prevent fatal arrhythmias and delay cardiomyopathy onset.

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.

Aims Deep neural networks (DNNs) perform excellently in interpreting electrocardiograms (ECGs), both for conventional ECG interpretation and for novel applications such as detection of reduced ejection fraction (EF). Despite these promising developments, implementation is hampered by the lack of trustworthy techniques to explain the algorithms to clinicians. Especially, currently employed heatmap-based methods have shown to be inaccurate. Methods and results We present a novel pipeline consisting of a variational auto-encoder (VAE) to learn the underlying factors of variation of the median beat ECG morphology (the FactorECG), which are subsequently used in common and interpretable prediction models. As the ECG factors can be made explainable by generating and visualizing ECGs on both the model and individual level, the pipeline provides improved explainability over heatmap-based methods. By training on a database with 1.1 million ECGs, the VAE can compress the ECG into 21 generative ECG factors, most of which are associated with physiologically valid underlying processes. Performance of the explainable pipeline was similar to ‘black box’ DNNs in conventional ECG interpretation (AUROC 0.94 vs 0.96), detection of reduced EF (AUROC 0.90 vs 0.91) and prediction of one-year mortality (AUROC 0.76 vs 0.75). Contrary to the ‘black box’ DNNs, our pipeline provided explainability on which morphological ECG changes were important for prediction. Results were confirmed in a population-based external validation dataset. Conclusions Future studies on DNNs for ECGs should employ pipelines that are explainable to facilitate clinical implementation by gaining confidence in artificial intelligence and making it possible to identify biased models.