Electrocardiography comprehensive sorting method based on deep learning algorithm

Abstract

The invention discloses an electrocardiography comprehensive sorting method based on deep learning algorithm. The method comprises the following steps of acquiring original electrocardiography waveform data and electrocardiography additional information as well as electrocardiography rhythm information, representative PQRST waveform data, conducting waveform classification to the related information via trained first deep learning algorithm to achieve a first sorting result, conducting trained second deep learning algorithm to related information to achieve P wave, QRS wave and T wave data and calculating representative PQRST wave featured data and inputting the above into a traditional electrocardiography computer for automatic sorting algorithm to achieve a second sorting result, and adding weight to adjust the sorting results and designating a sorting result having the maximum grade value as a final sorting result. Characteristics of electrocardiography classification are rationally combined; the deep learning method is trained via the above steps and waveform classification is conducted via the deep learning method, so accuracy of sorting result of the electrocardiography explanation can be improved.

Description

technical field [0001] The invention relates to an electrocardiogram classification method, in particular to an electrocardiogram comprehensive classification method based on a deep learning algorithm. Background technique [0002] ECG waveform data acquisition and ECG classification results are important auxiliary means and reference information for doctors to diagnose heart disease. Usually, ECG waveform data acquisition and classification are carried out in hospitals or physical examination centers, which have disadvantages such as inconvenient detection and low detection frequency, and cannot It is difficult to effectively prevent and timely treat heart disease if the ECG classification information is provided to doctors for real-time diagnosis. In recent years, with the popularity of the Internet and mobile smart phones, it has become possible to launch portable ECG monitors and family personal ECG monitors. The monitors currently on the market are based on the traditi...

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the traditional electrocardiogram measurement classification method existing in the prior art, which is prone to misclassification when the single waveform measurement feature is not obvious, its clinical reliability and accuracy are low, and it cannot meet the actual classification needs, etc., and provides A Novel Comprehensive Classification Method of ECG Based on Deep Learning Algorithm

Images