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

A method and system for analyzing electronic medical records of ICU patients based on deep learning

An electronic medical record and deep learning technology, applied in the field of information intelligence, can solve the problems of low time complexity, unsuitable robustness and rationality, and difficulty in exploring the relationship between markers, so as to reduce the occurrence of drugs and optimize the loss function Effect

Active Publication Date: 2022-05-10
XIAMEN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the traditional multi-label classification model has low time complexity, it is difficult to explore the hidden connections between labels.
Even some models take into account the relationship between markers, but the way they consider it is not robust and reasonable

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
  • A method and system for analyzing electronic medical records of ICU patients based on deep learning
  • A method and system for analyzing electronic medical records of ICU patients based on deep learning
  • A method and system for analyzing electronic medical records of ICU patients based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The embodiments of the invention are described in detail below in combination with the accompanying drawings. It should be noted that the embodiments described in the accompanying drawings are only exemplary and are only used to explain the invention and cannot be understood as limitations on the invention. The following describes an ICU patient electronic medical record analysis method and system based on deep learning according to an embodiment of the present invention in combination with the accompanying drawings.

[0041] See Figure 1 and Figure 2 As shown in, an electronic medical record analysis method for ICU patients based on deep learning, comprising:

[0042] S101, receive the input ICD code and drug vector, input the ICD code and drug vector into two multi-layer perceptron respectively, generate two hidden layers with the same dimension, and calculate the correlation of the two hidden layers;

[0043] S102, based on the initialized sparsity coefficient, calculate...

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 relates to a method and system for analyzing electronic medical records of ICU patients based on deep learning, including: receiving input ICD codes and drug vectors, and inputting the ICD codes and drug vectors into two multi-layer perceptrons to generate two dimensions The same hidden layer, and calculate the correlation of the two hidden layers; based on the initialized sparse coefficient, use KL divergence to calculate the distance between the sparse coefficient and the average activation degree of neurons after the middle layer of the autoencoder is activated, and put it in To the loss function; use the hidden layer as the middle layer of the autoencoder, use a multi-layer perceptron to decode, and output prescriptions including multiple drugs; Put in the loss function as drug loss. By acquiring the mapping relationship between the patient's ICD code and the prescription, the present invention digs out the potential relationship between the medicines and gives recommendations, which has high reliability.

Description

technical field [0001] The invention relates to the field of information intelligence, in particular to an ICU patient electronic medical record analysis method and system based on deep learning. Background technology [0002] With the promotion of big data and electronic medical cases. More and more patient information and electronic medical record data are stored in medical systems and databases. And with the rapid development of artificial intelligence and the continuous improvement of server computing power, now we have the ability to study the distribution and characteristics of these data, so as to help with clinical diagnosis, prescription recommendation and health management. [0003] Recently, electronic health record has gradually become a research hotspot. EHR data has attracted a large number of scholars to study it with its rich amount of information. For example, some scholars use EHR data to build a medical knowledge map. This atlas sorts out different situations a...

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 Patents(China)
IPC IPC(8): G16H10/60G06K9/62G06N3/04G06N3/08
CPCG16H10/60G06N3/08G06N3/044G06N3/045G06F18/2411
Inventor 杨帆梁云帆林开标赖永炫姚毅虹
Owner XIAMEN 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