A method for automatic identification and classification of shockable cardioverter rhythms combined with time-frequency domain characteristic analysis of ECG

Abstract

The invention provides an automatic shockable rhythm identification and classification method combined with electrocardio time-frequency domain feature analysis. The method comprises specific steps as follows: S1, pretreating electrocardio signals; S2, automatically identifying cardiac arrest rhythms, and if discrimination conditions are not met, implementing S3; S3, on the basis of an integral coefficient band-pass filter, calculating the maximum amplitude proportion value (Pa), the average amplitude proportion value (Pb) and the average deviation proportion value (Pc) of output signals; S4, S5, S6 and S7, discriminating shockable rhythms and non-shockable rhythms according to frequency domain feature values such as the Pa, the Pb, the Pc and the like, and implementing S8 in case of failure; S8, calculating an electrocardio standard grid bar projection standard deviation; S9, discriminating the shockable rhythms and the non-shockable rhythms according to the standard deviation. The method can be applied to instruments and equipment which automatically identify and classify the shockable rhythms according to body surface electrocardiograms, the shockable rhythm identification sensitivity and the non-shockable rhythm specificity are improved, and the algorithm operating efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of medical electronics, and in particular relates to an automatic identification and classification method of electrocardiographic signals (ECG), in particular to an electric shock recovery device which can be used for ECG monitors and automatic external defibrillators (AED). Automatic recognition and classification method and algorithm of heart rhythm. Background technique [0002] According to the epidemiological research results of the Center for Health Statistics in the United States, more than 50% of the total number of deaths from cardiovascular diseases are caused by sudden cardiac death (Sudden Cardiac Death, SCD). Clinical epidemiological studies have shown that in the past fifty years, the incidence of SCD has been on the rise, and 80% of SCD is caused by ventricular fibrillation (Ventricular Fibrillation-VF, referred to as ventricular fibrillation) or sustained ventricular tachycardia. It is caus...

AI Technical Summary

Problems solved by technology

However, when the shape of the ECG signal changes greatly, the algorithm based on the ECG R wave recognition cannot adapt to the recognition of the shockable rhythm, which leads to the disadvantage of low sensitivity and specificity of the recognition

In 1994 and 1997, "IEEE Transactions on Biomedical Engineering" successively published "Multiway sequential hypothesis testing for tachyarrhythmia discrimination" and "Detecting ventricular tachycardia and fibrillation by complexity measure", reporting algorithms based on various transformations and complexity analysis. However, such algorithms have disadvantages such as complex calculations and high requirements for hardware calculation loads, and cannot be used in portable devices such as AEDs.

Recently, "Computers in Cardiology" (2005) and "IEEE Transactions on Biomedical Engineering" (2007) successively reported "A new ventricular fibrillation detection algorithm for automated external defibrillators" and "Detecting Ventricular Fibrillation by Time-Delay Methods" two articles on HILB The new algorithm of this kind of method and algorithm is based on the algorithm of phase space reconstruction, although the specificity has been greatly improved, but the recognition sensitivity is low

To sum up, although a variety of methods and algorithms for the recognition and classification of shockable cardiac rhythms have been publicly reported so far, there is still a lack of consideration of both the sensitivity and specificity of the recognition, and its computational complexity is far from sufficient. Exceeds the computational load of devices such as portable AEDs

Images