A method and system for identifying p-waves in electrocardiographic signals

Abstract

The invention discloses a method and system for identifying P waves in electrocardiographic signals, comprising: acquiring original electrocardiographic signals and marking the position of P waves in the original electrocardiographic signals; adopting sliding segmentation to divide the original electrocardiographic signals into multiple small fragments of equal length, and mark the small fragments to set the value; construct the deep neural network model, and input the small fragments after the mark value is set to train the deep neural network model to obtain the target deep neural network model; test the The ECG signal is input into the target deep neural network model, and the position of the P wave in the test ECG signal is output. In this way, the artificial intelligence method is used for automatic identification, replacing the traditional pattern recognition-based method, which is more flexible and more accurate.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method and system for identifying P waves in electrocardiographic signals. Background technique [0002] The electrocardiographic signal records the electrophysiological signal of the beating heart, which is reflected in the image of each heartbeat, showing a series of characteristic wave bands, such as P wave, QRS wave, T wave, etc., corresponding to the atrial depolarization activity, ventricular depolarization polar atrial repolarization activity, ventricular repolarization activity. Among them, the P wave represents the beginning of a heart activity, and it is also the most obvious band of atrial electrophysiological activity. The accurate identification of the P wave plays a vital role in the analysis based on ECG signals. [0003] However, P waves have various shapes and are difficult to describe accurately. Words such as "tall", "inverted" and "not obvious" are ...

AI Technical Summary

Problems solved by technology

[0003] However, P waves have various shapes and are difficult to describe accurately. Words such as "tall", "inverted" and "not obvious" are usually used to describe P waves and other forms. How much mV is lower than it is regarded as inverted", "amplitude less than how much is regarded as insignificant", so it is difficult to quantify these descriptions in the pattern recognition method; secondly, the population is very different, and the position, direction, and activity intensity of each person's heart They are all different, resulting in a wide variety of P-wave shapes. In the pattern recognition method, the same pattern is used to identify P-waves for all people, and the accuracy is not high; P-waves are easily disturbed by noise, and various types of Noise, such as limb movement, other instrument interference, current interference, etc., will also cause changes in the shape of the P wave and reduce the accuracy of the pattern recognition method

Images