Detection of Ventricular Fibrillation Using the Image from Time-Frequency Representation and Combined Classifiers without Feature Extraction

Abstract

Due the fact that the required therapy to treat Ventricular Fibrillation (V F) is aggressive (electric shock), the lack of a proper detection and recovering therapy could cause serious injuries to the patient or trigger a ventricular fibrillation, or even death. This work describes the development of an automatic diagnostic system for the detection of the occurrence of V F in real time by means of the time-frequency representation (T F R) image of the ECG. The main novelties are the use of the T F R image as input for a classification process, as well as the use of combined classifiers. The feature extraction stage is eliminated and, together with the use of specialized binary classifiers, this method improves the results of the classification. To verify the validity of the method, four different classifiers in different combinations are used: Regression Logistic with L2 Regularization (L 2 R L R), adaptive neural network (A N N C), Bagging (B A G G), and K-nearest neighbor (K N N). The Hierarchical Method (HM) and Voting Majority Method (VMM) combinations are used. ECG signals used for evaluation were obtained from the standard MIT-BIH and AHA databases. When the classifiers were combined, it was observed that the combination of B A G G , K N N , and A N N C using the Hierarchical Method (HM) gave the best results, with a sensitivity of 95.58 ± 0.41%, a 99.31 ± 0.08% specificity, a 98.6 ± 0.04% of overall accuracy, and a precision of 98.25 ± 0.29% for V F . Whereas a sensitivity of 94.02 ± 0.58%, a specificity of 99.31 ± 0.08%, an overall accuracy of 99.14 ± 0.43%, and a precision of 98.59 ± 0.09% was obtained for V T with a run time between 0.07 s and 0.12 s. Results show that the use of T F R image data to feed the combined classifiers yields a reduction in execution time with performance values above to those obtained by individual classifiers. This is of special utility for V F detection in real time.

Fusion of Multiple Univariate Data Analysis-based Detectors to Build a Specific Fingerprint of Atrial Fibrillation

“…Besides, instead of training the data with well-known machine learning classifiers [22,23], herein, we opted for voting majority approach using the selected features in order to reduce the computational complexity as much as possible. This approach has a rapid execution time since all univariate based classifiers must be executed to make the final decision which is well adapted for real time execution [24] and portable electronic devices. Although its simplicity, the proposed approach has attained satisfactory results in terms of sensitivity and specificity by reaching 98.50% and 95.1 % respectively.…”

A Novel Systolic Parallel Hardware Architecture for the FPGA Acceleration of Feedforward Neural Networks

“…• MIT-BIH & AHA. The MIT-BIH Malignant Ventricular Arrhythmia [41] and AHA (2000 series) [42] databases were processed as in [43], [44] to obtain 15 features. One output class identify two different types of rhythms (normal and abnormal).…”

“…The aim of this application is to discern between the normal function of the heart and several pathologies as Ventricular Tachycardia (VT) and Ventricular Fibrillation (VF), amongst others. To feed the classifier, the input data (ECG signal) were preprocessed in several stages [43], [44]. The first step consisted of a baseline wandering removal (denoising), Fig.…”

A novel approach to extracting useful information from noisy TFDs using 2D local entropy measures

“…The time-frequency distribution (TFD) of the signal, when the signal has time-varying frequency content and dynamical spectral behavior, allows us to represent the signal jointly in time and frequency domain and to detect frequency components at each time instant [1]. TFDs are used in various fields, such as nautical studies [2], medicine [3,4], electrical engineering [5,6], and image processing [7,8].…”