Title :
A novel method for beat-to-beat detection of ventricular late potentials
Author :
Wu, Shuicai ; Qian, Yongxian ; Gao, Zhiyong ; Lin, Jiarui
Author_Institution :
Inst. of Biomed. Eng., Huazhong Univ. of Sci. & Technol., Wuhan, China
Abstract :
A novel method for beat-to-beat detection of ventricular late potentials (VLP) from high-resolution electrocardiograms (ECGs) is presented. ECG signals from the X lead are first filtered using a bandpass filter, and then a time-sequence adaptive filter, to improve its signal-to-noise ratio. Eight features are extracted using the wavelet transform, from the VLP time-frequency distribution of the filtered ECG signals, and used as inputs of specially designed artificial neural network for VLP recognition. The artificial neural network was trained and tested using clinical data, respectively. The results show that the presented method can detect beat-to-beat-based VLP with sensitivity of 80% and specificity of 77%, and the detection accuracy is 78%.
Keywords :
adaptive filters; band-pass filters; electrocardiography; medical signal detection; neural nets; wavelet transforms; artificial neural network; beat-to-beat detection method; clinical data; detection accuracy; electrodiagnostics; filtered ECG signals; high-resolution electrocardiograms; time-frequency distribution; time-sequence adaptive filter; ventricular late potentials; Adaptive filters; Artificial neural networks; Band pass filters; Data mining; Electrocardiography; Feature extraction; Signal design; Signal to noise ratio; Time frequency analysis; Wavelet transforms; Action Potentials; Algorithms; Electrocardiography; Humans; Neural Networks (Computer); Sensitivity and Specificity; Signal Processing, Computer-Assisted; Ventricular Dysfunction;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
