26 November 2019 in IEEE Access
Electrocardiogram (ECG) is an efficient and commonly used tool for detecting arrhythmias. With the development of dynamic ECG monitoring, an effective and simple algorithm is needed to deal with large quantities of ECG data. In this study, we proposed a method to detect multiple arrhythmias based on time-frequency analysis and convolutional neural networks. For a short-time (10 s) single-lead ECG signal, the time-frequency distribution matrix of the signal was first obtained using a time-frequency transform method, and then a convolutional neural network was used to discriminate the rhythm of the signal. ECG data in multiple databases were used and were divided into 12 classes. Finally, the performance of three kinds of time-frequency transform methods are evaluated, including short-time Fourier transform (STFT), continuous wavelet transform (CWT), and pseudo Wigner-Ville distribution (PWVD). The best result was obtained by STFT, with an accuracy of 96.65%, an average sensitivity of 96.47%, an average specificity of 99.68%, and an average F1 score of 96.27%, respectively. Especially, the area under curve (AUC) value is 0.9987. The proposed method in this work may be efficient and valuable to detect multiple arrhythmias for dynamic ECG monitoring.
1 January 2016 in International Heart Journal
A rapid pacing-induced heart failure model is commonly used in developing dilated cardiomyopathy (DCM). Traditionally, the right ventricular lead was connected with a single chamber pacemaker specific for animals that had a high frequency. However, the pacemaker used in this model is commercially unavailable. We developed a "pacing bigeminal" method using a commercially available dual-chamber (DDD) pacemaker to achieve high-frequency pacing. Twenty beagles were assigned to group A (n = 10) (pacing bigeminal method) and group B (n = 10) (traditional method). Echocardiographic measurements and electrocardiograms were obtained at baseline, at two weeks of pacing, and at 4 weeks of end pacing. LV anterior wall cardiac samples were obtained at 2 weeks of pacing and 4 weeks of end pacing for myocardial microscopic evaluation. Clinical manifestation and exposure time were also observed. After pacing for 10.5 ± 2.3 (714) days, the beagles in group B experienced heart failure, whereas in group A, only 7.9 ± 2.5 (5-12) days (P < 0.05) were needed to reach heart failure. Both methods could induce wide QRS duration, heart rate elevation, and myocardial microscopic changes (P > 0.05). In conclusion, this pacing bigeminal-induced heart failure method is feasible and can induce heart failure faster than the traditional method, which makes it a promising alternative method.