Prediction of Ventricular Fibrillation by Machine Learning Based on QRS Complex Shape Features

摘要

The present invention relates to a method for predicting ventricular fibrillation through machine learning based on the form of a QRS complex. More specifically, a feature extracted from the QRS complex is used for early prediction of ventricular fibrillation compared to the existing heart rate variability characteristics, but the QRS complex The present invention relates to a method for predicting ventricular fibrillation through machine learning based on the QRS complex form in which the accuracy of prediction of ventricular fibrillation is significantly improved using four morphological features and 11 heart rate variability features. To this end, the present invention provides a method for predicting ventricular fibrillation using artificial neural network learning, wherein the method for predicting ventricular fibrillation comprises: selecting a database of a subject for learning with the artificial neural network; Specifying an electrocardiogram signal in the database; Extracting data according to a ventricular fibrillation prediction parameter from the ECG signal; And training the extracted data data using an artificial neural network (ANN), wherein the ventricular fibrillation prediction parameter is a characteristic of a plurality of QRS complexes.