6533b830fe1ef96bd129678b

RESEARCH PRODUCT

Ventricular Fibrillation and Tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning

subject

description

Parameter-less ventricular fibrillation detection with time-frequency representation.Time-frequency representations are treated as images for a classifier.A comparison for four classifiers demonstrates the validity of the proposed method.The proposed technique could be applied to any signal and research field.This is a novel approach to signal analysis. Background and objectiveTo safely select the proper therapy for Ventricullar Fibrillation (VF) is essential to distinct it correctly from Ventricular Tachycardia (VT) and other rhythms. Provided that the required therapy would not be the same, an erroneous detection might lead to serious injuries to the patient or even cause Ventricular Fibrillation (VF). The main novelty of this paper is the use of time-frequency (t-f) representation images as the direct input to the classifier. We hypothesize that this method allow to improve classification results as it allows to eliminate the typical feature selection and extraction stage, and its corresponding loss of information. MethodsThe standard AHA and MIT-BIH databases were used for evaluation and comparison with other authors. Previous to t-f Pseudo Wigner-Ville (PWV) calculation, only a basic preprocessing for denoising and signal alignment is necessary. In order to check the validity of the method independently of the classifier, four different classifiers are used: Logistic Regression with L2 Regularization (L2 RLR), Adaptive Neural Network Classifier (ANNC), Support Vector Machine (SSVM), and Bagging classifier (BAGG). ResultsThe main classification results for VF detection (including flutter episodes) are 95.56% sensitivity and 98.8% specificity, 88.80% sensitivity and 99.5% specificity for ventricular tachycardia (VT), 98.98% sensitivity and 97.7% specificity for normal sinus, and 96.87% sensitivity and 99.55% specificity for other rhythms. ConclusionResults shows that using t-f data representations to feed classifiers provide superior performance values than the feature selection strategies used in previous works. It opens the door to be used in any other detection applications.