Patient hospitalization duration early prediction method based on graph neural network and device thereof

A neural network and prediction method technology, applied in the field of early prediction of the length of hospitalization of patients based on graph neural network, can solve the problem of neglecting the length of hospitalization, and achieve the effect of good representation, improved prediction accuracy, and reduced feature dimension.

Active Publication Date: 2021-09-03
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current prediction of patient length of stay is based on data modeling such as clinical tests and demographics, which ignores the impact of patients' comorbidities on the length of hospital stay; Early prediction of length of hospital stay

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
  • Patient hospitalization duration early prediction method based on graph neural network and device thereof
  • Patient hospitalization duration early prediction method based on graph neural network and device thereof
  • Patient hospitalization duration early prediction method based on graph neural network and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.

[0068] Based on the above-mentioned background technology, it can be seen that the existing methods for predicting the length of hospital stay of patients mainly have the following problems: (1) In the research on the early prediction of the length of hospital stay at the admission point, the available data are very limited and these studies only extract some routine features, resulting in the prediction not effectively. (2...

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 patient hospitalization duration early prediction method based on graph neural network and a device thereof, and belongs to the technical field of data processing. The method comprises the following steps: obtaining a medical record home page data set and preprocessing; extracting basic features and historical features of the patient; according to the preprocessed medical record home page data set, extracting a disease vector; constructing a patient similarity network; based on the patient hospitalization duration label, the basic features, the historical features, the disease vectors and the patient similarity network, constructing a hospitalization duration early prediction model by using a GraphSAGE graph neural network; and predicting the hospitalization duration of the to-be-predicted sample by using the hospitalization duration early-stage prediction model to obtain a hospitalization duration early-stage prediction result of the patient. According to the method, the hospitalization duration of the patient is predicted at the hospitalization point in the early stage, and the method has higher application value.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a graph neural network-based early prediction method and device for a patient's length of stay in hospital. Background technique [0002] Accurately predicting the length of hospital stay of patients can help hospital managers effectively allocate limited medical resources, control patients' medical costs, and improve the quality of medical services. However, the current prediction of patient length of stay is based on data modeling such as clinical tests and demographics, which ignores the impact of patients' comorbidities on the length of hospital stay; Early prediction of length of hospital stay. Therefore, how to accurately predict the length of hospital stay of patients in the early stage of admission has important practical significance. Contents of the invention [0003] Aiming at the above-mentioned shortcomings in the prior art, the present invent...

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): G16H40/20G16H50/50G16H50/70G06N3/04G06N3/08
CPCG16H40/20G16H50/50G16H50/70G06N3/084G06N3/045
Inventor 邱航胡智栩王利亚周德嘉丁舒涵
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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