Atrial fibrillation event detection method based on deep learning

Abstract

The invention provides an atrial fibrillation event detection method based on deep learning. The method can break through the constraint of insufficient features of a traditional atrial fibrillation detection algorithm and further improve the accuracy. The method comprises the following steps: S1, acquiring an electrocardiosignal for training an atrial fibrillation event detection deep learning model, and then performing preprocessing operation on the electrocardiosignal to remove interference and invalid data; S2, performing QRS detection processing on the preprocessed electrocardiosignal toextract heart beat information in the electrocardiosignal; S3, according to the QRS detection processing result, performing electrocardio dimension-increasing transformation processing; S4, building adeep learning model according to the data subjected to the dimension increasing transformation processing; and S5, carrying out training set and test set data division on the data set subjected to the dimension-increasing transformation processing through a five-fold cross validation method, and then carrying out training of the deep learning model through the training set data to finally obtainan atrial fibrillation detection model.

Description

technical field [0001] The invention relates to the technical field of atrial fibrillation detection, in particular to a method for detecting atrial fibrillation events based on deep learning. Background technique [0002] Atrial fibrillation is a common arrhythmia problem, which is a serious disorder of atrial electrical activity. With age, the incidence of atrial fibrillation is also increasing. Atrial fibrillation not only affects the quality of life of patients, but also may cause thromboembolism, Heart failure and stroke, and with the development of long-term ECG monitoring, the amount of ECG signal data that can be obtained is increasing, and the automatic detection algorithm for atrial fibrillation is also developed. However, the traditional automatic detection algorithm for atrial fibrillation Often limited by the feature acquisition process, it is difficult to break through the detection accuracy. Contents of the invention [0003] In view of the above problems, ...

AI Technical Summary

Problems solved by technology

[0002] Atrial fibrillation is a common arrhythmia problem, which is a serious disorder of atrial electrical activity. With age, the incidence of atrial fibrillation is also increasing. Atrial fibrillation not only affects the quality of life of patients, but also may cause thromboembolism, Heart failure and stroke, and with the development of long-term ECG monitoring, the amount of ECG signal data that can be obtained is increasing, and the automatic detection algorithm for atrial fibrillation is also developed. However, the traditional automatic detection algorithm for atrial fibrillation Often limited by the feature acquisition process, it is difficult to break through the detection accuracy

Images