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

A risk prediction method for aortic dissection surgery based on boosted tree model

A technology for aortic dissection and surgical risk, applied in the fields of medical data mining, character and pattern recognition, instruments, etc., can solve problems such as incompleteness, lack, and incomplete data, and achieve high accuracy.

Active Publication Date: 2022-04-22
THE SECOND XIANGYA HOSPITAL OF CENT SOUTH UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (2) Incomplete type; many data are incomplete or missing;

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 risk prediction method for aortic dissection surgery based on boosted tree model
  • A risk prediction method for aortic dissection surgery based on boosted tree model
  • A risk prediction method for aortic dissection surgery based on boosted tree model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Decision tree algorithm is a traditional machine learning algorithm.

[0047] The core idea of ​​the algorithm is to establish a set of trees to judge the judgment conditions based on the input features of the training set; each leaf node stores a category, and a set of multiple leafless nodes can contain multiple categories. The decision-making process is to classify samples into a category based on different feature values; the key point of building a decision tree is how to determine the direction of the next branch when it is at a certain node; the category of the split attribute is to divide all subsets as much as possible belong to the same category. Therefore, the core problem of the decision tree is how to choose the eigenvalue of the root node. Depending on the continuous or divisive nature of the output variable, decision trees can be classified as classification trees or regression trees.

[0048] The steps to build a decision tree are as follows:

[0049]...

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 a method for predicting the risk of aortic dissection surgery based on a lifting tree model, step 1: data preprocessing; completing the missing part of the data in the operation record to form a database containing the operation record; step 2: data Mining; process the data in the database based on the decision tree model; step 3: result analysis; analyze the processing results of data mining to evaluate the effectiveness of the data mining algorithm; step 4: knowledge application; apply the model to the current main Data corresponding to arterial dissection surgery to predict the risk of current surgery. The model of the present invention has 100% accuracy to the prediction of death risk after aortic dissection surgery, and is more accurate than other prediction methods, and the prediction result can provide the key factors of death after aortic dissection surgery, which can be In the future, doctors and patients will provide decision-making basis and help medical policy makers make full use of medical resources.

Description

technical field [0001] The invention relates to a method for predicting the risk of an aortic dissection operation based on a lifting tree model. Background technique [0002] With the development and progress of technology, various medical data are collected to form a database, and the records in the database have different formats and types. Therefore, it is more difficult to apply these data. To analyze this data, different algorithms are required. [0003] Most of the data comes from the patient's surgical plan, including conversations, test data, surgical results, medication information, etc., and has the following characteristics: [0004] (1) Diversity; including various data forms, such as data and images; [0005] (2) Incomplete type; many data are incomplete or missing; [0006] (3) Timing; almost all data are generated according to the timeline; [0007] (4) High-dimensionality; such as routine blood test and urine routine test often produce many sub-items; ...

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): G06K9/62G16H50/70
CPCG16H50/70G06F18/214G06F18/24323
Inventor 谭凌唐浩谭云秦姣华
Owner THE SECOND XIANGYA HOSPITAL OF 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