Electrocardiosignal classification method and system based on multi-domain feature learning

Abstract

The invention discloses an electrocardiosignal classification method and system based on multi-domain feature learning, and the method comprises the steps: carrying out the preprocessing of an original electrocardiosignal, i.e., extracting an RR interval sequence and P-wave region data of the electrocardiosignal, and carrying out the time-frequency conversion of the P-wave region data, and obtaining a P-wave region time-frequency graph; performing multi-domain feature extraction on the electrocardiosignals to obtain heart rhythm feature representation, atrial activity feature representation and global spatial-temporal feature representation of the electrocardiosignals; and fusing the heart rhythm feature representation, the atrial activity feature representation and the global spatio-temporal feature representation to obtain fused features of the electrocardiosignals, and inputting the fused features into a classification layer to obtain a classification result of the electrocardiosignals. According to the method, collection and fusion of multi-domain features are achieved, local features and global features are combined, more complete patient representation is obtained, and then the precision of a model classification result is improved. Particularly, when the method is applied to atrial fibrillation classification, the classification result is of great significance for clinically assisting doctors to make decisions.

Description

technical field [0001] The invention belongs to the technical field of electrocardiographic signal classification and deep learning, and in particular relates to an electrocardiographic signal classification method and system based on multi-domain feature learning. Background technique [0002] With the development of my country's social economy, people's lifestyles have undergone profound changes. The excessively fast pace of life and heavy work pressure have led to increasingly prominent health problems and younger residents. According to the statistical results of the "Report on Nutrition and Chronic Diseases of Chinese Residents (2020)", cardiovascular disease has become the biggest threat to the health of residents. Arrhythmias are the most common group of diseases in cardiovascular diseases. Although most arrhythmias are not directly life-threatening, they may lead to other serious heart diseases and are one of the main causes of sudden cardiac death. For example, atr...

AI Technical Summary

Problems solved by technology

[0004] Although many scholars have developed many detection algorithms based on deep learning in the classification of ECG signals related to atrial fibrillation in recent years, the detection performance still cannot meet the needs of clinical applications.

Images