Improving Deep Learning-based Cardiac Abnormality Detection in 12-Lead ECG with Data Augmentation.

Automated Electrocardiogram (ECG) classification using deep neural networks requires large datasets annotated by medical professionals, which is time-consuming and expensive. This work examines ECG augmentation as a method for enriching existing datasets at low cost. First, we introduce three novel augmentations: Limb Electrode Move and Chest Electrode Move both simulate a minor electrode mislocation during signal measurement, and Heart Vector Transform generates an ECG by modeling a rotated main heart axis.

Estradiol regulates human QT-interval: acceleration of cardiac repolarization by enhanced KCNH2 membrane trafficking.

Background: Modulation of cardiac repolarization by sexual hormones is controversial and hormonal effects on ion channels remain largely unknown. In the present translational study, we therefore assessed the relationship between QTc duration and gonadal hormones and studied underlying mechanisms.

Methods And Results: We measured hormone levels and QTc intervals in women during clomiphene stimulation for infertility and women before, during, and after pregnancy.

Comparison of real-time classification systems for arrhythmia detection on Android-based mobile devices.

The electrocardiogram (ECG) is a key diagnostic tool in heart disease and may serve to detect ischemia, arrhythmias, and other conditions. Automatic, low cost monitoring of the ECG signal could be used to provide instantaneous analysis in case of symptoms and may trigger the presentation to the emergency department. Currently, since mobile devices (smartphones, tablets) are an integral part of daily life, they could form an ideal basis for automatic and low cost monitoring solution of the ECG signal.

Cellular properties of C-terminal KCNH2 long QT syndrome mutations: description and divergence from clinical phenotypes.

Background: C-terminal KCNH2 mutations are commonly associated with a more benign clinical presentation, but mutations localized in close proximity may exhibit different clinical and biophysical phenotypes. The value of detailed cellular characterization of such mutant channels in vitro has not been studied with respect to clinical risk stratification of affected patients.

Objective: The purpose of this study was to study the cellular properties and clinical presentation of C-terminal KCNH2 missense mutations localized in close proximity.

Biventricular pacing does not affect microvolt T-wave alternans in heart failure patients.

Background: Microvolt T-wave alternans (MTWA) is a valuable tool for stratification of patients at risk for sudden death and has recently been approved for this purpose by Medicare. Although right atrial (RA) pacing has been applied for MTWA testing, the effects of other pacing modalities on MTWA have not been systematically studied. Accordingly, it is unknown whether biventricular (BiV) pacing might influence MTWA test results.