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

Artificial intelligence prediction method for hematogenous infection

A technology of artificial intelligence and prediction methods, applied in neural learning methods, artificial life, biological neural network models, etc., can solve the problem of low accuracy of bloodstream infection

Pending Publication Date: 2021-10-01
SHENZHEN PEOPLES HOSPITAL +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Clinical studies have shown that the correct rate of physicians in predicting bloodstream infections through clinical experience is very low. In addition, various biomarkers can effectively stop the treatment of antibiotics, rather than decide whether to start using antibiotics

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
  • Artificial intelligence prediction method for hematogenous infection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The above and other technical features and advantages of the present invention will be described in more detail below in conjunction with the accompanying drawings.

[0015] Such as figure 1 As shown, the present invention is mainly for individualized prediction of blood-borne infection in patients.

[0016] This method mainly incorporates the data of patients who have undergone blood culture in history from two aspects for model construction, including patient-related disease information, medical intervention-related information, and blood culture results of historical patients.

[0017] The random forest algorithm was used to construct the model and screen out the risk factors related to blood-borne infection.

[0018] Construct predictive models through different methodologies, including regularized logistic regression, K nearest neighbors, support vector machines, random forests, extreme gradient boosting, and deep neural network algorithms.

[0019] Different mod...

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 artificial intelligence prediction method for hematogenous infection. The method comprises the following steps: inputting historical data of a patient subjected to blood culture; screening risk factors of infection based on a random forest, and constructing a prediction model through regularization logistic regression, K nearest neighbor, a support vector machine, the random forest, limit gradient lifting and a deep neural network algorithm; and through prediction probabilities of different methods, carrying out secondary learning through a limit gradient lifting algorithm to finally predict whether the patient suffers from hematogenous infection, and further calculating the occurrence probability of the hematogenous infection. The method is used for early warning and advanced medical intervention of blood flow infection possibly existing in an early stage, an existing computer technology is combined and applied to intelligent diagnosis of blood flow infection, and meanwhile, individualized layering of patients with blood-borne infection is realized.

Description

technical field [0001] The invention belongs to the field of judging blood-borne infection, in particular to an artificial intelligence prediction method applied to auxiliary diagnosis of blood-borne infection. Background technique [0002] Bloodstream infections in hospitals are characterized by high morbidity and mortality, among which the mortality rate of bloodstream infections in critically ill patients can be as high as 30%. Numerous studies suggest that early identification and appropriate antibiotic treatment can significantly reduce the incidence and mortality of bloodstream infections. [0003] Clinical studies have shown that the correct rate of physicians in predicting bloodstream infections through clinical experience is very low. In addition, various biomarkers can effectively stop antibiotic treatment, rather than decide whether to start using antibiotics. [0004] In order to give early warning of possible bloodstream infection and advance medical interventi...

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): G16H50/80G16H50/20G06N3/00G06N3/08
CPCG16H50/80G16H50/20G06N3/006G06N3/08
Inventor 胡安民李惠萍马磊单智铭李镇
Owner SHENZHEN PEOPLES HOSPITAL
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