Supercharge Your Innovation With Domain-Expert AI Agents!

Medical time sequence data comprehensive information extraction method

A technology of time series data and comprehensive information, applied in medical informatics, computer-aided medical procedures, informatics, etc., can solve the problem of limited ability to capture information interaction, and achieve the effect of good analysis performance

Active Publication Date: 2021-06-29
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have relatively limited ability to capture information interaction

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
  • Medical time sequence data comprehensive information extraction method
  • Medical time sequence data comprehensive information extraction method
  • Medical time sequence data comprehensive information extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The preferred embodiments of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0033] See attached figure 1 , Embodiment 1 implements a method for extracting comprehensive information of medical time-series data according to the present invention, with figure 1 It is a flow chart of the method of Embodiment 1, comprising the following steps:

[0034] S1 obtains the medical time series feature matrix X=(x 1 ,x 2 ,...,x t ...,x T ), where t∈{1,2,…,T} is the index of the time step, x t ∈ R |C| Represents the feature vector corresponding to the time step t, |C| represents the length of the feature vector;

[0035] For example, the x t It can be a vector composed of the original medical characteristic values ​​of the tth time step (such as 1 hour), such as blood sugar (Glucose), pH value, lactate value (Lactate), keto-acid value (Keto-acid), low pressure value, High pressure value, plasma HCO3 concentration, ...

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 medical time sequence data comprehensive information extraction method, and belongs to the technical field of artificial intelligence data processing. The method comprises the following steps: acquiring a medical time sequence characteristic matrix X = (x1, x2,..., xt,..., xT); performing dynamic modeling on the X to obtain cumulative expressions h1, h2,..., ht,..., hT; interacting the output of each time step with the output of the last time step to obtain an interaction result si,T of each time step; distributing an attention weight beta[i],T for interaction between each time step and the last time step; performing multiplication and addition operation on siT and beta[i],T to summarize a total expression gT after interaction of all time steps and the last time step; and splicing the hT and the gT to comprehensively modelling the X. The interaction between the time steps can be well modeled, so that the dynamically changing health condition of a patient can be more effectively learned, the changes are different from people, the importance of different interactions is distinguished through an attention mechanism, and therefore, the ability of more comprehensively representing the EMR data of the patient can be provided, better analysis performance can be obtained, and a fine-grained medical analysis result can be provided.

Description

technical field [0001] The invention relates to a data processing method, in particular to a method for extracting comprehensive information of medical time series data, and belongs to the technical field of artificial intelligence data processing. Background technique [0002] Healthcare analytics aims to analyze various healthcare data through a data-driven approach to aid healthcare decision-making and provide personalized treatment recommendations to improve patient management. With the progress of health information construction and the development of big data, international researchers have paid more and more attention to and participated in the preservation and mining of medical big data. Among them, electronic health records (EHR) are used for One of the important data sources for healthcare analytics. Electronic health records contain various forms of information, such as demographic information (such as age, gender, height, time of admission and discharge, death, ...

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): G16H50/50G16H50/30G06N3/04G06N3/08
CPCG16H50/50G16H50/30G06N3/084G06N3/048G06N3/044
Inventor 蔡庆鹏郑凯平王伟姚畅张美慧
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com