Electrocardio feature extraction method, system and device based on wavelet transform and medium

Abstract

The invention discloses an electrocardio feature extraction method, system and device based on wavelet transform and a medium. The method comprises the steps of: carrying out the wavelet filtering ofcollected electrocardio data, and determining a wavelet basis function; determining an oscillogram of the R wave position value according to the wavelet basis function and the electrocardio data; extracting r waves by setting a threshold value; enhancing Q-wave energy and S-wave energy in the oscillogram according to the wavelet basis function; taking the R wave position as a base point, and extracting a Q wave and an S wave through a set first finite region window; enhancing P-wave energy and T-wave energy in the oscillogram according to the wavelet basis function; taking the Q wave positionas a base point, and extracting a P wave through a set second finite region window; and taking the S wave position as a base point, and extracting the T wave through a set third finite region window.Key features in the electrocardiogram data can be accurately extracted, the false detection rate and the missing detection rate of feature waves are reduced, and the method can be widely applied to the technical field of electrocardiogram data processing.

Description

technical field [0001] The invention relates to the technical field of electrocardiographic data processing, in particular to a method, system, device and medium for extracting electrocardiographic features based on wavelet transform. Background technique [0002] Electrocardiogram (ECG) analysis is one of the most commonly used examinations in the prevention of heart disease, which can help doctors diagnose arrhythmia, myocardial ischemia, myocardial infarction and other cardiovascular diseases. There are many types of arrhythmia electrocardiograms and there are many differences. There are also large differences between the electrocardiograms of patients with the same arrhythmia. Accurate diagnosis requires rich theoretical knowledge and clinical experience; Monitoring generates a large amount of data, and manual identification of different arrhythmia ECGs will consume a lot of manpower and medical resources. And often there may be misjudgment in fatigue recognition. This...

AI Technical Summary

Problems solved by technology

These two methods are easy to cause false detection and missed detection of characteristic waves, which will affect the extraction of subsequent characteristic waves, time and amplitude features.

Images