Coronary heart disease electrocardiogram screening system and method based on residual neural network

Abstract

The invention provides a coronary heart disease electrocardiogram screening system based on a residual neural network, and the system comprises an electrocardiosignal processing module which is used for extracting electrocardiosignals generated by an electrocardiograph, carrying out the multi-layer decomposition and noise reduction of the electrocardiosignals through employing a symlets4 wavelet, searching the position of an R wave in electrocardiosignal sequence data converted from the electrocardiosignals, and carrying out the heart beat segmentation based on the position of the R wave; a depth feature extraction module which is used for performing translation and scaling on the data processed by the electrocardiosignal processing module to enhance the data, and extracting the depth features of the twelve-lead electrocardiogram by using a ResneXt50 network comprising an extrusion and excitation network module; and a tree model prediction module which is used for combining the depth features extracted by the depth feature extraction module with electrocardiograph data, and inputting the trained XGBoost model to obtain the prediction probability of the coronary heart disease electrocardio features in the electrocardiogram. The system is low in installation and use cost, can achieve automatic screening, is higher in accuracy compared with diagnosis of an electrocardiograph, can reduce misjudgment or missed judgment, and reduces the workload of doctors.

Description

technical field [0001] The invention relates to the technical field of cardiovascular disease diagnosis, in particular to a residual neural network-based ECG screening system and method for coronary heart disease. Background technique [0002] Coronary atherosclerotic heart disease, referred to as coronary heart disease, refers to ischemic and hypoxic heart disease caused by coronary atherosclerosis and coronary artery stenosis, and arrhythmia is a common complication. Coronary heart disease is one of the important causes of death in the elderly, and the incidence rate is proportional to age. Clinically, it manifests as angina pectoris, myocardial infarction and other conditions, and even death due to arrhythmia and heart failure. At present, the gold standard for diagnosing coronary heart disease is coronary angiography, but because of its high cost and certain risks, it cannot be popularized. At present, the use of 12-lead ECG to detect coronary heart disease is a very i...

AI Technical Summary

Problems solved by technology

Although the existing technology based on the ECG feature extraction based on the deep learning algorithm has improved the corresponding accuracy and diversity, the shortcomings of the existing technology are that it cannot handle structured data, the accuracy of the model is not enough, and the scalability and extension Insufficient performance

Images