Electrocardio and heart sound signal combined analysis based coronary heart disease non-invasive screening system

Abstract

The invention discloses an electrocardio and heart sound signal combined analysis based coronary heart disease non-invasive screening system. The system comprises an electrocardiosignal preprocessingmodule used for filtering, denoising and normalizing an original electrocardiosignal, a heart sound signal preprocessing module used for filtering, denoising and normalizing an original heart sound signal, a characteristic extraction and selection module used for extracting and selecting multi-domain characteristics of the processed electrocardiosignal and heart sound signal, a five-channel cascade module used for performing wavelet transformation and reconstruction on the heart sound signal and connecting the reconstructed four-frequency-band heart sound signal and the electrocardiosignal into a five-channel group signal, and a double-input neural network classification module composed of a multi-layer perceptron, a deep learning model and an activation model and used for processing and analyzing electromechanical eigenvectors and the five-channel group signal. Therefore, the coronary heart diseases can be screened more accurately and non-invasively.

Description

technical field [0001] The invention relates to a system for screening coronary heart disease. The system is based on combined analysis of electrocardiogram and heart sound signals, and belongs to the technical field of non-invasive screening of human diseases in biomedical engineering. Background technique [0002] Coronary heart disease is the major type of cardiovascular disease and one of the leading causes of death worldwide. The buildup of plaque along the lining of the coronary arteries reduces blood flow to the heart muscle, leading to coronary heart disease. In severe cases, plaque rupture can completely block the lumen of the artery, triggering an acute myocardial infarction. [0003] Currently, coronary angiography is considered the gold standard for clinical diagnosis of coronary heart disease. Unfortunately, this is an invasive technique that requires specialized surgical procedures and considerable time and cost, making it unattractive as a screening method f...

AI Technical Summary

Problems solved by technology

[0007] The ECG features extracted in the above device only belong to the time domain level, without considering the information of the frequency domain and nonlinear level; the extracted heart sound signal features only belong to the information of the frequency domain level, without considering the time domain, entropy and kurtosis information; only a summary analysis at the feature level has been carried out, no deep learning of the complete ECG and heart sound signals has been carried out, and in-depth and effective information related to coronary heart disease has not been excavated from the overall situation to the details, making the screening of coronary heart disease difficult. Accuracy needs to be further improved

Images