Electrocardiogram data classification method based on 12 leads and convolution neural network

Abstract

The invention relates to an electrocardiogram data classification method based on 12 leads and a convolution neural network. The method comprises the following steps: acquiring 12-lead electrocardiogram data signals from a PTB diagnostic electrocardiogram database; performing noise reduction processing on the signals acquired in the step 1 by using a wavelet transform denoising algorithm; processing the signals subjected to the noise reduction processing in the step 2 by using a wavelet modulus maximum value and variable threshold method; decomposing periods of a 12-lead electrocardiogram by using R wave peak position information acquired in the step 3, and then extracting a P-QRS-T characteristic segment of each period; selecting appropriate electrocardiosignals and sampling electrocardiosignals according to set sampling points; and constructing a one-dimensional convolution neural network, setting the number of nodes of an input layer, an implicit layer and an output layer of the one-dimensional convolution neural network, training the one-dimensional convolution neural network, and building a 12-lead electrocardiogram classification model. The method can quickly identify electrocardiosignals of a patient suffering from cardiovascular diseases.

Description

technical field [0001] The invention provides a method for classifying electrocardiographic data based on 12 leads and a convolutional neural network. Background technique [0002] The 12-lead ECG is a typical diagnostic tool to reflect the physiological status of various parts of the heart, including 12 leads (I, II, III, aVR, aVL, aVF, V1-V6), which detect different parts of the heart respectively. Since the detection of different types of cardiovascular diseases requires the evaluation of complex changes in different leads, it is time-consuming and laborious to manually analyze the ECG to assist in the diagnosis of cardiovascular diseases, and the diagnostic results are not ideal. Therefore, in order to effectively and reliably analyze 12-lead ECG, existing researchers have proposed a variety of automatic cardiovascular disease detection algorithms to solve the limitations of manual analysis of 12-lead ECG. [0003] However, in the existing scientific research work, most...

AI Technical Summary

Problems solved by technology

These studies have achieved certain results on a certain cardiovascular disease problem, but they are very limited. There are few studies on how to detect multiple cardiovascular diseases, and it is difficult to effectively assist the clinical diagnosis of cardiovascular diseases.

Images