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

A screening system for aortic dissection based on stochastic subspace ensemble learning

A technology of aortic dissection and random subspace, applied in the fields of informatics, medical simulation, medical informatics, etc., can solve the problems of low efficiency of aortic dissection diagnosis, complex process, low missed diagnosis rate, etc., to overcome other injuries and side effects , Improve the accuracy and reduce the cost of inspection

Active Publication Date: 2021-10-12
XIANGYA HOSPITAL CENT SOUTH UNIV +2
View PDF1 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 to provide a method based on stochastic subspace integration learning in view of the shortcomings of the existing traditional diagnostic methods for the diagnosis of aortic dissection, such as low efficiency, high misdiagnosis rate, low missed diagnosis rate, high cost, and complicated process. Aortic Dissection Screening Methods

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
  • A screening system for aortic dissection based on stochastic subspace ensemble learning
  • A screening system for aortic dissection based on stochastic subspace ensemble learning
  • A screening system for aortic dissection based on stochastic subspace ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0098] In order to further illustrate the implementation of the present invention, the following experiment is used to verify the beneficial effects of the present invention:

[0099] The data sets used in this experiment came from Xiangya, which includes information collected by 53,213 patients as a sample. The total number of patients with aorta is 802 people, 5,2411 non-patients, namely 802 samples, reverse sample 5,2411, the ratio of the atrial and the antique sample is 1: 65, and 85 indicators are extracted as the sample feature.

[0100] 1) The data set is divided into 7 sizes similar mutual exclusive, each subset ensures distribution consistency, that is, the layered sampling from the data concentration, each time the panel of six subset is used as a training set, rest That subset was used as a test set for 7 training and testing;

[0101] 2) In the training concentration, set a small number of patient samples to p, most types of non-patient samples are n, | P | << | N |, s...

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 aortic dissection screening model based on random subspace integration learning and a method, system and model for establishing the same. The present invention aims at the disadvantages of low efficiency, high misdiagnosis rate, low missed diagnosis rate, high cost and complicated process of existing traditional diagnostic methods for aortic dissection diagnosis, and provides a screening method for aortic dissection based on stochastic subspace ensemble learning. This method uses the RS-Ensemble algorithm of machine learning to establish the RS model, and uses the RS model to screen and diagnose aortic dissection, which greatly improves the diagnostic accuracy, while greatly reducing the misdiagnosis rate and missed diagnosis rate, and realizes efficient and low-cost diagnosis. .

Description

Technical field [0001] The present invention relates to the field of medical and artificial intelligence, especially a aortic interlayer screening model based on random sub-space integration learning and its establishment method, system and model. Background technique [0002] The aortatic clamp is a relatively rare emergency, and its incidence is that blood in the aortic cavity is broken into the aortic wall from the aortic pressure under aortic pressure, and then forms a sandwich in the aortic wall. Hematoma, and the main artery longitudinal axis extension forms "double chamber aorta". This is a very dangerous cardiovascular disease that the disease is 1% ~ 2% per hour in the initial 24 hours, and the mortality rate is as high as 60% ~ 70% in one week, most patients who have no treatment Will die within one year. [0003] The diagnostic method of the current aortic clamp is mainly an imaging method and an ultrasonic method. Including CT scan, CT angiography, ultrasonic electroc...

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 Patents(China)
IPC IPC(8): G16H50/70G16H50/50
CPCG16H50/50G16H50/70
Inventor 张国刚刘丽珏柏勇平谭世洋罗靖旻穆阳张伟
Owner XIANGYA HOSPITAL CENT SOUTH 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