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

Electrocardiogram ST segment abnormity discrimination system based on causal analysis

A causal analysis and electrocardiogram technology, applied in character and pattern recognition, instruments, applications, etc., can solve problems such as misjudgment and low accuracy of electrocardiogram machine diagnosis results, and achieve good scalability, improved interpretability, and simple methods Effect

Pending Publication Date: 2022-03-15
SHANGHAI JIAO TONG UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in underdeveloped areas, limited to medical level, misjudgment or missed judgment may occur
The electrocardiogram machine will also give the electrocardiogram diagnosis result, but limited by the complexity of the electrocardiogram data, the accuracy of the diagnosis result of the electrocardiogram machine is low

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 ST segment abnormity discrimination system based on causal analysis
  • Electrocardiogram ST segment abnormity discrimination system based on causal analysis
  • Electrocardiogram ST segment abnormity discrimination system based on causal analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] According to a kind of electrocardiogram ST segment abnormal discrimination system based on causal analysis provided by the present invention, such as Figures 1 to 3 shown, including:

[0045] Bayesian network generation module: extract and preprocess the extracardiac factor data, obtain the preprocessed extracardiac factor data, generate a weighted adjacency matrix between data variables based on the preprocessed extracardiac factor data, and weighted adjacency Extracting non-zero weights from matrix to generate Bayesian network G 0 , to establish a causal connection mechanism between ECG ST-segment abnormalities and extracardiac sign factor data; wherein, the present invention uses a large amount of clinical ECG data including original xml files, doctors' clinical diagnosis results of ECG, and other sign data of interviewees, based on prior Based on empirical knowledge, ten variables were screened out from the original sign data. After preparing the data, the NOTEAR...

Embodiment 2

[0094] Embodiment 2 is a preferred example of embodiment 1

[0095] The extracardiac variable data used in the present invention is a data set based on the survey of the health status of the elderly population in Shanghai. Health survey, the total number of surveys is 12098 people. The original data set contains 55 variables, and ten variables are screened from the original data based on prior knowledge.

[0096] The invention provides a method for discriminating abnormal ST segment of electrocardiogram based on causal analysis, such as figure 1 shown, including:

[0097] Step 1: Use the NOTEARS structure learning algorithm and the K2 score search structure learning algorithm to generate a weighted adjacency matrix between data variables. The weighted adjacency matrix performs secondary processing on the matrix weights through the hard threshold rule, extracts non-zero weights, and generates Bay Yes Network G 0 ;Based on the trace index and the non-combined structure learn...

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 provides an electrocardiogram ST segment anomaly discrimination system based on causal analysis, which comprises the following steps: extracting extracardiac sign factor data and preprocessing, generating a weighted adjacency matrix among data variables based on the preprocessed extracardiac sign factor data, and extracting a non-zero weight by the weighted adjacency matrix to generate a Bayesian network G0; calculating a causal effect estimator of each path of the Bayesian network G0, and adjusting a network structure based on the causal effect estimator to generate a causal network G1; the method comprises the following steps: extracting 12-lead data from an electrocardiogram, and preprocessing the 12-lead data to obtain preprocessed 12-lead data; 10-dimensional electrocardiogram characteristics are obtained based on the 12-lead data; preprocessing the preprocessed 12-lead data and 10-dimensional electrocardiogram features, and extracting depth features through a convolutional residual neural network; and combining the depth features with the causal mechanism variable data, and inputting a decision tree to obtain the prediction probability of the abnormality of the st segment of the electrocardiogram feature in the electrocardiogram.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular, to a causal analysis-based electrocardiogram ST-segment abnormality discrimination system, and more specifically, to a method for judging whether an electrocardiogram has ST-segment abnormality and the abnormal type through causal analysis + tree classifier discriminant system. Background technique [0002] Coronary atherosclerotic heart disease, referred to as coronary heart disease for short, refers to ischemic and hypoxic heart disease caused by coronary atherosclerosis and coronary artery stenosis, and arrhythmia is its common complication. Coronary heart disease is one of the important causes of death in the elderly, and the incidence rate is proportional to age. Clinically, it often manifests as angina pectoris, myocardial infarction and other conditions, and even death due to arrhythmia and heart failure. At present, the gold standard for diagnosing...

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
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/318A61B5/346A61B5/358A61B5/00A61B5/352G06K9/62G06N3/04G06N3/08G06N20/20
CPCA61B5/318A61B5/346A61B5/358A61B5/7235A61B5/7203A61B5/352G06N3/08G06N20/20G06N3/045G06F18/24323
Inventor 骆源曾婉玉
Owner SHANGHAI JIAO TONG UNIV
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