Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Automatic diagnosis method and system for electrocardiogram diagnosis conclusion

A diagnostic conclusion and automatic diagnosis technology, applied in the direction of diagnosis, diagnostic record/measurement, medical science, etc., can solve the problems of inability to judge which term to keep, ignore the relationship between ECG terms, and the conclusion does not conform to clinical habits, etc., to improve The effect of accuracy

Active Publication Date: 2020-12-04
SHANGHAI SID MEDICAL CO LTD
View PDF25 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is: in order to solve the problem that the traditional ECG diagnosis model in the prior art only proceeds from the ECG itself, ignoring the relationship between ECG terms, therefore, the conclusion obtained by the automatic diagnosis does not conform to the clinical practice , or there are contradictions between some terms but it is impossible to judge which term should be reserved, so as to provide an automatic diagnosis method and system for the diagnostic conclusion of the electrocardiogram

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
  • Automatic diagnosis method and system for electrocardiogram diagnosis conclusion
  • Automatic diagnosis method and system for electrocardiogram diagnosis conclusion
  • Automatic diagnosis method and system for electrocardiogram diagnosis conclusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] The present embodiment provides a method for automatic diagnosis of the diagnosis conclusion of electrocardiogram, such as figure 1 shown, including:

[0035] S1: collecting some standard 12-lead electrocardiographic signals and corresponding diagnostic conclusions with a sampling frequency of 500HZ through quality control, and counting all electrocardiographic terms occurring in the diagnostic conclusions;

[0036] S2: Preprocessing the standard 12-lead ECG signal and its corresponding diagnostic conclusion, constructing a training set for a data set composed of the preprocessed ECG signal and its corresponding diagnostic conclusion;

[0037] S3: the electrocardiographic signal in the training set is used as input, and the diagnosis conclusion is used as output to train the deep learning model;

[0038] S4: Input the ECG signal with a sampling frequency of 500HZ to be diagnosed into the trained deep learning model to obtain an output vector representing a diagnosis co...

Embodiment S7

[0057] Optionally, S7 in this embodiment specifically includes:

[0058] S71: If there are K elements in the output vector greater than the preset threshold, K≥2, then arrange the K elements greater than the preset threshold in descending order to obtain a sorted set Z={z 1 ,z 2 ,z 3 ,...,z K};

[0059] S72: Determine the m-th element z in the sorted set in descending order m Corresponding ECG term and z 1 ,z 2 ,z 3 ,…,z m-1 The probability that corresponding ECG terms can be combined with each other Among them, m≤K, the initial value of m is 2;

[0060] S73: if is greater than the preset probability value, add 1 to the value of m, and judge again until When it is less than the preset probability value, it is judged that the diagnostic conclusion of the current ECG signal to be diagnosed is z 1 ,z 2 ,z 3 ,…,z m-1 A combination of corresponding ECG terms.

[0061] In this embodiment, for the ECG signal to be diagnosed with a sampling frequency of 500HZ, it ...

Embodiment 2

[0068] The present embodiment provides a kind of diagnosis conclusion automatic diagnosis system of electrocardiogram, comprising:

[0069] The data collection module is used to collect some standard 12-lead electrocardiographic signals and corresponding diagnostic conclusions with a sampling frequency of 500HZ through quality control, and counts all electrocardiographic terms that appear in the diagnostic conclusions;

[0070] The preprocessing module is used to preprocess the standard 12-lead electrocardiographic signal and its corresponding diagnostic conclusion, and construct a training set for the data set composed of the preprocessed electrocardiographic signal and its corresponding diagnostic conclusion;

[0071] The deep learning module is used to use the ECG signal in the training set as input and the diagnosis conclusion as output to train the deep learning model;

[0072] The conclusion prediction module is used to input the ECG signal to be diagnosed with a samplin...

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 automatic diagnosis method and system for an electrocardiogram diagnosis conclusion. An electrocardiosignal is input into a trained deep learning model to obtain an outputvector representing the diagnosis conclusion, an element in the output vector represents the probability that a corresponding electrocardio term is contained in the diagnosis conclusion. According tothe method, the final diagnosis conclusion of the to-be-diagnosed electrocardiosignal is given in combination with the element values in the output vector and the probability that the electrocardio terms can be combined with one another. By means of the method, automatic diagnosis can be achieved, meanwhile, the situation that mutually exclusive electrocardio terms appear in a diagnosis conclusionis avoided, and the accuracy of electrocardio diagnosis is improved.

Description

technical field [0001] The application belongs to the technical field of electrocardiogram diagnosis, in particular to a quality control method for electrocardiogram diagnosis report. Background technique [0002] Along with people's rhythm of life and pressure gradually increase, heart disease has become one of major killers threatening people's life and health. Cardiovascular disease has become a frequently-occurring and common disease in my country. According to the survey data released by the Ministry of Health, the prevalence of heart disease in my country is very high, and it is increasing year by year, and the age of onset of coronary heart disease and myocardial infarction tends to Due to younger age, myocardial infarction and stroke are not uncommon around the age of 30. [0003] For early detection and treatment of heart disease, accurate analysis and diagnosis of electrocardiogram plays a key role in cardiovascular diseases. Electrocardiogram is a non-invasive, n...

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): A61B5/0402A61B5/04
CPCA61B5/7267
Inventor 朱俊江王雨轩黄浩李俊亮
Owner SHANGHAI SID MEDICAL CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com