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

Drug combination recommendation method based on time attention mechanism and graph convolutional network

A convolutional network and attention technology, applied in medicine or prescriptions, neural learning methods, biological neural network models, etc., can solve problems such as inability to produce drug combinations

Pending Publication Date: 2020-10-20
NORTHWESTERN POLYTECHNICAL UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With such complexity, rule-based approaches fail to generate compliant drug combinations

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
  • Drug combination recommendation method based on time attention mechanism and graph convolutional network
  • Drug combination recommendation method based on time attention mechanism and graph convolutional network
  • Drug combination recommendation method based on time attention mechanism and graph convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] This embodiment involves a drug combination recommendation method based on temporal attention mechanism and graph convolutional network, see figure 1 Shown: Include the following steps:

[0047] S1: Diagnosis, treatment procedures, and medications make up each patient's medical event x i , in which the diagnosis code and treatment procedure code of each patient become a unified dimensional diagnosis vector after one-hot encoding with the treatment vector Transform into a diagnostic embedding vector using a linear embedding method and the treatment embedding vector Among them, w d and w p Represent the learned embedding matrix respectively, and the calculation method is:

[0048]

[0049] S2: Using the cyclic neural network RNN α Learning diagnostic embedding vectors separately with the treatment embedding vector Get the diagnostic attention parameter α d with the treatment attention parameter α p . Similarly, using another recurrent neural network R...

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 drug combination recommendation method based on a time attention mechanism and a graph convolutional network. According to the invention, reasonable drugs can be recommended for treatment of critical patients in a complex medical environment, and clinicians can be helped to treat patients. Diagnosis and treatment in electronic health records are coded in a unified coding format, time sequence information in diagnosis and treatment is stored, codes are converted into vectors, and the time attention mechanism composed of two layers of recurrent neural networks is used for capturing the time sequence information. The method aims at medicines of prescriptions issued by doctors in the electronic health records and medicines having adverse reactions with known medicines,graph network structure data are converted to describe the relation between different medicine combinations, and medical medication knowledge in a medicine graph network is learned by utilizing the graph convolutional network. Compared with the prior art, the simplified graph convolutional network reduces the calculation parameters of the neural network model and reduces the training and learningtime under the condition of maintaining the prediction accuracy unchanged.

Description

technical field [0001] The present invention relates to a drug combination recommendation method based on temporal attention mechanism and graph convolutional network. Background technique [0002] With the generation of large amounts of medical data, deep learning techniques have shown strong predictive potential in the medical field. In the past decade, the electronic health record (EHR) system that records patient health information has developed rapidly, and it has played a huge role in medical-related research fields, such as the extraction of medical concepts, the construction of patient activity trajectories, etc. Modeling, reasoning of diseases, establishment of clinical decision-making systems and prediction of drug combinations, etc. Using deep learning technology and the rich information in the EHR database, doctors can provide treatment for patients with complex conditions more conveniently and accurately. In general, medical events can be divided into diagnosi...

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): G16H20/10G06N3/04G06N3/08
CPCG16H20/10G06N3/08G06N3/045
Inventor 王震高超王海强李向华朱培灿李学龙
Owner NORTHWESTERN POLYTECHNICAL 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