Skin sympathetic nerve activity and ventricular arrhythmias in acute coronary syndrome.

BACKGROUND: Acute coronary syndrome (ACS) is major cause of ventricular arrhythmias (VAs) and sudden death. neuECG is a noninvasive method to simultaneously record skin sympathetic nerve activity (SKNA) and electrocardiogram. OBJECTIVE: The purpose of this study was to test the hypotheses that (1) ACS increases average SKNA (aSKNA), (2) the magnitude of aSKNA elevation is associated with VAs during ACS, and (3) there is a gender difference in aSKNA between patients without and with ACS. METHODS: We prospectively studied 128 ACS and 165 control participants. The neuECG was recorded with electrodes at Lead I configuration at baseline, during mental math stress, and during recovery (5 minutes for each phase). All recordings were done in the morning. RESULTS: In the control group, women have higher aSKNA than do men at baseline (0.82 ± 0.25 µV vs 0.73 ± 0.20 µV; P = .009) but not during mental stress (1.21 ± 0.36 µV vs 1.16 ± 0.36 µV; P = .394), suggesting women had lower sympathetic reserve. In comparison, ACS is associated with equally elevated aSKNA in women vs men at baseline (1.14 ± 0.33 µV vs 1.04 ± 0.35 µV; P = .531), during mental stress (1.46 ± 0.32 µV vs 1.33 ± 0.37 µV; P = .113), and during recovery (1.30 ± 0.33 µV vs 1.11 ± 0.30 µV; P = .075). After adjusting for age and gender, the adjusted odds ratio for VAs including ventricular tachycardia and ventricular fibrillation is 1.23 (95% confidence interval 1.05-1.44) for each 0.1 µV aSKNA elevation. aSKNA is positively correlated with plasma norepinephrine level. CONCLUSION: ACS is associated with elevated aSKNA, and the magnitude of aSKNA elevation is associated with the occurrence of VAs. Women have higher aSKNA and lower SKNA reserve than do men among controls but not among patients with ACS.

Automated ECG classification based on 1D deep learning network.

The standard 12-lead electrocardiogram (ECG) records the heart's electrical activity from electrodes on the skin, and is widely used in screening and diagnosis of the cardiac conditions due to its low price and non-invasive characteristics. Manual examination of ECGs requires professional medical skills, and is strenuous and time consuming. Recently, deep learning methodologies have been successfully applied in the analysis of medical images. In this paper, we present an automated system for the identification of normal and abnormal ECG signals. A multi-channel multi-scale deep neural network (DNN) model is proposed, which is an end-to-end structure to classify the ECG signals without any feature extraction. Convolutional layers are used to extract primary features, and long short-term memory (LSTM) and attention are incorporated to improve the performance of the DNN model. The system was developed with a 12-lead ECG dataset provided by the Kaohsiung Medical University Hospital (KMUH). Experimental results show that the proposed system can yield high recognition rates in classifying normal and abnormal ECG signals.