Electrocardiogram (ECG)-based intelligent screening for systolic heart failure (HF) is an emerging method that could become a low-cost and rapid screening tool for early diagnosis of the disease before the comprehensive echocardiographic procedure. We collected 12-lead ECG signals from 900 systolic HF patients (ejection fraction, EF < 50%) and 900 individuals with normal EF in the absence of HF symptoms. The 12-lead ECG signals were converted by continuous wavelet transform (CWT) to 2D spectra and classified using a 2D convolutional neural network (CNN). The 2D CWT spectra of 12-lead ECG signals were trained separately in 12 identical 2D-CNN models. The 12-lead classification results of the 2D-CNN model revealed that Lead V6 had the highest accuracy (0.93), sensitivity (0.97), specificity (0.89), and f1 scores (0.94) in the testing dataset. We designed four comprehensive scoring methods to integrate the 12-lead classification results into a key diagnostic index. The highest quality result among these four methods was obtained when Leads V5 and V6 of the 12-lead ECG signals were combined. Our new 12-lead ECG signal–based intelligent screening method using straightforward combination of ECG leads provides a fast and accurate approach for pre-screening for systolic HF.

Electrical defibrillation is a well-established treatment for cardiac dysrhythmias. Studies have suggested that shock-induced spatial sawtooth patterns and virtual electrodes are responsible for defibrillation efficacy. We hypothesize that high-frequency shocks enhance defibrillation efficacy by generating temporal sawtooth patterns and using rapid virtual electrodes synchronized with shock frequency. High-speed optical mapping was performed on isolated rat hearts at 2000 frames/s. Two defibrillation electrodes were placed on opposite sides of the ventricles. An S1-S2 pacing protocol was used to induce ventricular tachyarrhythmia (VTA). High-frequency shocks of equal energy but varying frequencies of 125-1000 Hz were used to evaluate VTA vulnerability and defibrillation success rate. The 1000-Hz shock had the highest VTA induction rate in the shorter S1-S2 intervals (50 and 100 ms) and the highest VTA defibrillation rate (70%) among all frequencies. Temporal sawtooth patterns and synchronous shock-induced virtual electrode responses could be observed with frequencies of up to 1000 Hz. The improved defibrillation outcome with high-frequency shocks suggests a lower energy requirement than that of low-frequency shocks for successful ventricular defibrillation.