Static electrocardiogram analysis method and device based on artificial intelligence self-learning

Abstract

The embodiment of the invention relates to a static electrocardiogram analysis method and device based on artificial intelligence self-learning. The static electrocardiogram analysis method comprisesthe steps of data preprocessing, heart beat detection, heart beat classification based on a deep learning method, heart beat checking, heart beat waveform characteristic detection, electrocardiogram event measurement and analysis and final automatic report data outputting and achieve a complete and quick static electrocardiogram process. By adopting the static electrocardiogram analysis method, modification information of automatic analysis results can be also recorded, modified data is collected and fed back to a deep learning model for continuous training, and the accuracy rate of an automatic analysis method is constantly improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence data analysis, in particular to a static electrocardiogram analysis method and device based on artificial intelligence self-learning. Background technique [0002] In 1908, Einthoven began to use electrocardiography (ECG) to monitor the electrophysiological activity of the heart. At present, non-invasive electrocardiography has become one of the important methods for the diagnosis and screening of heart diseases in the clinical cardiovascular field. According to the clinical usage, electrocardiogram can be divided into several categories: resting electrocardiogram, dynamic electrocardiogram, and exercise electrocardiogram. The static electrocardiogram adopts the 12-lead system (standard lead system) invented by Einthoven-Wilson-Goldberger, and records the ECG signals for 8-30 seconds for analysis. It has positive value for the diagnosis and analysis of various arrhythmias a...

AI Technical Summary

Problems solved by technology

[0007] Although the patient is assisted by doctors and nurses during the static ECG examination process, it can effectively reduce the influence of signal interference and ensure that the quality of the static ECG signal output is relatively stable and reliable, but the current computer analysis methods for static ECG are generally as follows: Some problems: First, in the heartbeat feature extraction, it is impossible to accurately identify P waves and T waves

Second, the classification of heartbeats basically stays in the three types of sinus, supraventricular and ventricular, which are far from meeting the complex and comprehensive analysis requirements of clinical electrocardiography doctors

Third, atrial flutter and atrial fibrillation and ST-T changes cannot be accurately identified, and the help of ST segment and T wave changes to myocardial ischemia analysis cannot be accurately analyzed

Fourth, the recognition of heartbeat and ECG events is not accurate and comprehensive enough. Due to the influence of many factors above, it is easy to miss, which will also affect the interpretation of doctors.

Fifth, due to the above-mentioned problems, automatic analysis and automatic reporting cannot be achieved

Doctors still need to spend a lot of precious time carefully reading static ECG data, which cannot fundamentally help doctors improve their analysis and analysis capabilities, both in terms of quality and efficiency

Images