Method for predicting bleeding events in patients with ischemic heart diseases based on lifting-resampling and feature correlation analysis

An ischemic heart disease and feature correlation technology, applied in the field of data processing, can solve the problems of less consideration of sample similarity, ignoring the potential correlation of IHD patient features, and failing to fully reflect the distribution of electronic health records, so as to improve prognosis, The effect of reducing medical expenses

Active Publication Date: 2018-05-29
ZHEJIANG UNIV
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional feature selection techniques seldom consider the similarity between samples, ignore the potential correlation between IHD patient characteristics, and treat intrinsically related patient characteristics as independent factors, so they cannot fully reflect the characteristics of electronic health records. distributed

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
  • Method for predicting bleeding events in patients with ischemic heart diseases based on lifting-resampling and feature correlation analysis
  • Method for predicting bleeding events in patients with ischemic heart diseases based on lifting-resampling and feature correlation analysis
  • Method for predicting bleeding events in patients with ischemic heart diseases based on lifting-resampling and feature correlation analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0099] This example uses a total of 2,930 case data of patients with ischemic heart disease, provided by the General Hospital of the Chinese People's Liberation Army, excluding private information such as names. In the entire dataset, a total of 230 patient characteristics were collected from patient electronic health records, and the analysis results of the dataset samples are shown in Table 3.

[0100] Table 3 Sample analysis results

[0101]

[0102] Then, follow the implementation step-by-step process for training.

[0103] In order to better compare the superiority of the model proposed by the present invention, a comparative test is carried out in three aspects. The first aspect reflects the superiority of lifting-resampling in dealing with unbalanced data. It is compared with three benchmark algorithms, namely logistic regression LR, random forest RF, and AdaBoost; in the second aspect, it is compared with the model BM based on the lifting-resampling framework that...

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 bleeding events in patients with ischemic heart diseases based on lifting-resampling and feature correlation analysis. The method includes the steps of(1) constructing training samples; (2) introducing a lifting-resampling framework for resampling of the training samples based on a logistic regression model, constructing a loss function of the logistic regression model based on patient sample-sample correlations and patient feature-feature correlations, and constructing a pre-training model; (3) using the training samples and true value labels corresponding to the training samples for training the pre-training model, using an equalized subsample set obtained by resampling for training the logistic regression model in each iteration to obtaina weak classifier corresponding to the equalized subsample set, and using multiple weak classifiers obtained after multiple iterations to constitute a predictive model of the bleeding events in the patients with the ischemic heart diseases; (4) using the predictive model of the bleeding events in the patients with the ischemic heart diseases to predict the probability of occurrence of bleeding events in samples to be tested.

Description

technical field [0001] The invention belongs to the field of data processing, and in particular relates to a bleeding event prediction method for patients with ischemic heart disease based on lifting-resampling and feature correlation analysis. Background technique [0002] Ischemic Heart Disease (IHD), also known as Coronary Artery Disease (CAD), is currently the number one killer of humans. It is estimated that by 2030, about 9,100,000 people worldwide will die from the disease, accounting for 14.2% of the total global death toll, and it will continue to be the leading cause of death in the world in the next few decades. [0003] IHD patients may experience ischemic events such as myocardial infarction, worsening angina, and revascularization during hospitalization. Ischemic events are related to bleeding complications. IHD patients undergoing coronary angiography have a risk of massive bleeding, and taking cardiovascular disease drugs such as prasugrel will increase the ...

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): G16H50/30G06Q10/04G06K9/62
CPCG06Q10/04G06F18/2148
Inventor 黄正行
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap