Electrocardiogram diagnosis method and system based on deep convolution neural network

Abstract

The invention discloses an electrocardiogram diagnosis method and system based on a deep convolution neural network. The diagnosis method comprises the steps that a collected original electrocardiogram of the human body is preprocessed to obtain a plurality of heartbeat fragments with a preset length; the heartbeat fragments are input into a trained deep convolution neural network model, and a prediction value of each category is obtained; the category of a single heartbeat corresponding to the maximum prediction value and the time interval of the heartbeat and a previous heartbeat are recorded, and a time series is formed; on the basis of a preset mapping relation between a clinical diagnosis criterion and the time series, the time series is matched with the diagnosis criterion, and a corresponding diagnosis result is obtained. Any feature in the electrocardiogram is not required to be extracted, so that valid information loss, noise data introduction and other problems caused by manual screening and processing are avoided to the largest extent, and the influence of manual characteristic extraction on the diagnosis accuracy is reduced.

Description

technical field [0001] The invention belongs to the technical field of electrocardiographic monitoring and diagnosis, and in particular relates to a method and system for featureless extraction of electrocardiograms based on a deep convolutional neural network. Background technique [0002] Electrocardiogram examination is one of the most commonly used electrophysiological examination methods in clinical practice. It is of great significance for the diagnosis of cardiovascular diseases such as arrhythmia, myocardial ischemia, and myocardial hypertrophy. At the same time, due to its simplicity, convenience, and non-invasive characteristics, it has also been widely used in clinical practice, especially for the diagnosis and analysis of arrhythmia, which has extremely important and irreplaceable value. [0003] The computer processing and analysis technology of electrocardiogram has been developed for decades. The main purpose of this technology is to automatically analyze and ...

AI Technical Summary

Problems solved by technology

[0012] Therefore, under the framework of the prior art, the accuracy rate of electrocardiogram automatic analysis is still difficult to reach a high level, for example, the sensitivity and positive predictive value for the detection of ventricular premature beats (VEB) in arrhythmia are basically 90%, while Sensitivity for detection of supraventricular premature beats (SVEBs) is only about 80%

In the case of such accuracy, the automatic analysis results of ECG data still need to rely on a lot of manpower for screening and interpretation, which cannot actually solve the problem of large-scale application

Images