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

Deep cascade framework for ICU death rate prediction and ICU death rate prediction method

A mortality and cascading technology, applied in medical informatics, medical simulation, computer-aided medical procedures, etc., can solve problems such as relying on the validity of pre-trained features, manually defining risk factors, and difficult to obtain inference paths for neural network structures.

Active Publication Date: 2021-02-26
哈尔滨工业大学人工智能研究院有限公司
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, current methods not only require experts to manually define risk factors but also rely heavily on the effectiveness of pre-trained features
From the perspective of the model, the end-to-end prediction model lacks interpretability, and the black-box neural network structure is difficult to obtain the reasoning path

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
  • Deep cascade framework for ICU death rate prediction and ICU death rate prediction method
  • Deep cascade framework for ICU death rate prediction and ICU death rate prediction method
  • Deep cascade framework for ICU death rate prediction and ICU death rate prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to make the above objects, features and advantages of the present invention more comprehensible, specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0044] It should be noted that the terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein.

[0045] refer to figure 1As shown, a deep cascade framework for ICU mortality prediction includes a sign subnetwork and a disease subnetwork, the sign subnetwork includes multiple nodes corresponding to sign types, and the disease subnetwork includes multiple nod...

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 a deep cascade framework for ICU death rate prediction and an ICU death rate prediction method, the deep cascade framework for ICU death rate prediction comprises a sign sub-network and a disease sub-network, the sign sub-network comprises a plurality of nodes corresponding to sign types, and the disease sub-network comprises a plurality of nodes corresponding to a disease type, the sign sub-network and the disease sub-network have interaction edges, and the interaction edges are connecting edges of the nodes corresponding to the disease type and the nodes correspondingto the sign type; the sign sub-network and the disease sub-network are cascaded according to node failure conditions, and the sign sub-network and the disease sub-network are both used for outputtingfailure distribution so as to predict the ICU death rate through the failure distribution. The deep cascade framework has the advantages that the death rate of the ICU patient can be conveniently predicted, and prediction has interpretability.

Description

[0001] technology neighbor [0002] The present invention relates to the field of ICU mortality prediction, in particular, to a deep cascade framework for ICU mortality prediction and an ICU mortality prediction method. Background technique [0003] Medical risk detection is an important topic to improve the ability of ICU clinical practice. Many scale and feature-based biostatistical learning methods and deep learning methods have been able to predict the mortality of specific patients and assist physicians to make corresponding clinical decisions. . However, current methods not only require experts to manually define risk factors but also rely heavily on the effectiveness of pre-trained features. From the perspective of the model, the end-to-end prediction model lacks interpretability, and the black-box neural network structure is difficult to obtain the reasoning path. Contents of the invention [0004] The problem solved by the invention is how to conveniently predict ...

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): G16H50/50
CPCG16H50/50
Inventor 姜京池王勃然马林江李雪
Owner 哈尔滨工业大学人工智能研究院有限公司
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