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

Electrocardiogram analysis method based on comparative learning, terminal equipment and storage medium

An analysis method and electrocardiogram technology, applied in terminal equipment and storage media, in the field of electrocardiogram analysis methods based on comparative learning, can solve the problems of large heartbeat base and lower model accuracy, and achieve the effect of accurate analysis

Pending Publication Date: 2022-01-14
厦门纳龙健康科技股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When this method is applied to the dynamic electrocardiogram, because of the large number of heartbeats, it is inevi

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 analysis method based on comparative learning, terminal equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] The accuracy of ECG automatic analysis plays a vital role in the doctor's report quality and diagnosis efficiency. Some manufacturers have gradually proposed some methods based on deep learning, which have improved the accuracy of automatic diagnosis of QRS waves and P waves to a certain extent. The general practice of these methods is to establish a corresponding deep neural network model, and then use the collected big data for corresponding training, so as to obtain more accurate recognition and classification results than traditional methods. In fact, there are no identical ECGs in the world. Even for the same person, ECGs collected at different times may have relatively large differences and changes. This is why no matter how ingenious the model is, there will always be more misjudgments in some dynamic ECGs. At this time, if we can make full use of the doctor's supervisory opinion on the current ECG, the accuracy of the global automatic ECG analysis will be great...

Embodiment 2

[0040] The present invention also provides an electrocardiogram analysis terminal device based on contrastive learning, including a memory, a processor, and a computer program stored in the memory and operable on the processor, when the processor executes the computer program The steps in the above method embodiment of Embodiment 1 of the present invention are implemented.

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 relates to an electrocardiogram analysis method based on comparative learning, terminal equipment and a storage medium. The method comprises the steps of S1, collecting electrocardiogram data to form a training set; s2, constructing a deep neural network model based on comparative learning, setting the input of the model as a positive reference sample set and a target sample in a triple, setting the output of the model as a category label of the target sample, training the model through a training set, and taking the trained model as a sample category classification model; s3, pre-classifying heart beats to be classified in the electrocardiogram data to be classified; s4, correcting the classification result through an artificial part, and extracting positive samples in the corrected classification result to form a positive reference sample set; and S5, for an uncorrected classification result, jointly inputting the uncorrected classification result and the positive reference sample set into a sample category classification model for classification, and judging whether the sample is a positive sample or not according to a category label. According to the method, the accurate analysis target of all data can be quickly achieved.

Description

technical field [0001] The invention relates to the field of electrocardiogram analysis, in particular to an electrocardiogram analysis method based on contrastive learning, a terminal device and a storage medium. Background technique [0002] Electrocardiogram is of great significance to the rapid diagnosis of coronary insufficiency, variant angina, acute myocardial infarction and other dangerous cardiovascular diseases. Among them, the dynamic electrocardiogram examination is generally recorded continuously for 24 hours. Due to its long-term monitoring characteristics, the detection rate of these cardiovascular diseases is higher. [0003] With the current commercial dynamic ECG analysis system, it takes as long as 15-30 minutes for doctors to analyze a dynamic ECG, which seriously restricts the development of dynamic ECG examination. However, due to the huge amount of dynamic ECG data, more than 100,000 heartbeats can be collected in 24 hours, and the total print length ...

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): G06K9/00A61B5/00A61B5/346G06N3/04G06N3/08
CPCA61B5/346A61B5/7267G06N3/08G06N3/045G06F2218/12
Inventor 徐拥军李熙钟玉秋
Owner 厦门纳龙健康科技股份有限公司