Unlock instant, AI-driven research and patent intelligence for your innovation.

Electrocardiogram anomaly detection method, model training method, device and equipment and medium

An electrical anomaly detection and anomaly detection technology, applied in diagnostic recording/measurement, medical science, sensors, etc., can solve the problems of low labeling efficiency, time-consuming, time-wasting, etc., to improve annotation efficiency and save time and cost Effect

Pending Publication Date: 2020-09-08
GUANGZHOU SHIYUAN ELECTRONICS CO LTD
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the continuous ECG (Electrocardiogram, electrocardiogram) monitoring process, the ECG record is as long as 24-48h, and contains 100,000-200,000 heartbeats. Cardiologists must spend a lot of time on heartbeat annotations, wasting a lot of time, and Labeling efficiency is not high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Electrocardiogram anomaly detection method, model training method, device and equipment and medium
  • Electrocardiogram anomaly detection method, model training method, device and equipment and medium
  • Electrocardiogram anomaly detection method, model training method, device and equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Figure 1A It is a flowchart of a method for detecting abnormal ECG provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of determining the type of abnormal ECG recorded by ECG. This method can be detected by abnormal ECG provided by the embodiment of the present invention The device can be implemented by means of software and / or hardware, and is usually configured in a computer device. Such as Figure 1A As shown, the method specifically includes the following steps:

[0049] S101. Obtain an electrocardiographic record, where the electrocardiographic record includes a plurality of cardiac beat signals.

[0050] Before and after the heart beats, the heart muscle is excited. During the exciting process, a weak biological current will be generated. In this way, every cardiac cycle of the heart is accompanied by bioelectrical changes. This bioelectrical change can be transmitted to various parts of the body surface. Due to t...

Embodiment 2

[0069] Embodiment 2 of the present invention provides a method for detecting abnormal ECG, Figure 2A It is a flow chart of a method for abnormal ECG detection provided by Embodiment 2 of the present invention. This embodiment refines the above-mentioned Embodiment 1 and describes the processing process of the abnormality detection model in detail. For example, Figure 2A As shown, the method includes:

[0070] S201. Obtain an electrocardiographic record, where the electrocardiographic record includes a plurality of cardiac beat signals.

[0071] Exemplarily, in some embodiments of the present invention, step S201 may include the following steps:

[0072] Acquire an electrocardiogram (ECG) signal. The electrocardiogram signal can come from the results of physical examination. The electrical signals of different parts of the body surface are detected through electrodes, and the collected signals are processed by impedance matching, filtering, and amplification through analog ...

Embodiment 3

[0143] image 3 An ECG abnormality detection model training method provided by Embodiment 3 of the present invention, this embodiment can be used for the ECG abnormality detection model training provided by the above-mentioned embodiments of the present invention, and this method can be obtained by the ECG abnormality detection model provided by the embodiment of the present invention It can be implemented by a model training device, which can be implemented in software and / or hardware, and is usually configured in a computer device. Such as image 3 As shown, the method specifically includes the following steps:

[0144] S301. Obtain a plurality of ECG record samples, the ECG record samples include a plurality of cardiac beat signal samples, and the ECG record samples are associated with category tags, and the category tags are used to identify abnormal types of the ECG record samples.

[0145] Specifically, the ECG record sample is the ECG record used to train the abnormal...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an electrocardiogram anomaly detection method, a model training method, device and equipment and a medium. The electrocardiogram anomaly detection method comprises the steps that electrocardiogram records are acquired, wherein the electrocardiogram records comprise multiple heart beat signals; an anomaly detection model is determined; the electrocardiogram records are inputinto the anomaly detection model to be processed, and probability values of the heart beat signals of different anomaly types are obtained; the probability values corresponding to the heart beat signals are arranged in a descending order; and that the anomaly types of the electrocardiogram records are anomaly types corresponding to the first K target probability values is determined, wherein thefirst K target probability values represent the same anomaly type. By marking the electrocardiogram records comprising the heart beat signals as the anomaly types of the heart beat signals corresponding to the K target probability values, annotation of the record level is achieved instead of annotating each heart beat, the annotation efficiency is improved, and the time cost is saved.

Description

technical field [0001] Embodiments of the present invention relate to electrocardiographic detection technology, and in particular, to a method for detecting abnormal electrocardiogram, a model training method, a device, equipment, and a medium. Background technique [0002] A variety of diseases can cause ECG abnormalities, and the detection of ECG abnormalities is particularly important for the diagnosis of heart diseases. ECG diagnosis has become an indispensable part of clinical diagnosis. At present, many portable ECG detectors have been popularized and applied in people's daily life. Portable ECG detectors can regularly record ECG data anytime and anywhere and calculate and analyze whether the heart rate is normal, but they cannot diagnose complex ECGs. . [0003] Existing ECG abnormality detection techniques require trained cardiologists to label each beat signal with beat annotations. However, in the continuous ECG (Electrocardiogram, electrocardiogram) monitoring ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): A61B5/0402A61B5/00
CPCA61B5/7235A61B5/7267
Inventor 胡静
Owner GUANGZHOU SHIYUAN ELECTRONICS CO LTD