Survival prediction method and system based on multi-granularity graph pattern mining

A technology of survival prediction and graph mode, which is applied in the fields of medical data mining, medical informatics, health index calculation, etc., can solve problems such as expansion is not simple, and achieve the effect of reducing time complexity

Active Publication Date: 2019-10-15
SHANDONG UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these extensions are not simple

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
  • Survival prediction method and system based on multi-granularity graph pattern mining
  • Survival prediction method and system based on multi-granularity graph pattern mining
  • Survival prediction method and system based on multi-granularity graph pattern mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] According to an aspect of one or more embodiments of the present disclosure, a survival prediction method based on multi-granularity graph pattern mining is provided.

[0058] Step S1: Receive medical history data of the insured person, and construct statistical characteristics of the insured person in statistics;

[0059] Step S2: For each insured person, construct a heterogeneous information network based on his medical history data;

[0060] Step S3: Use a multi-granularity graph pattern mining algorithm to mine medical treatment patterns from heterogeneous information networks as pattern features;

[0061] Step S4: Adopt the Cox survival prediction model to evaluate the partial regression coefficients of the statistical features and the model features respectively, and calculate the risk of each feature based on the proportional risk assumption as an enhanced feature;

[0062] Step S5: Combine statistical features, pattern features, and enhanced features into a complete featu...

Embodiment 2

[0127] According to an aspect of one or more embodiments of the present disclosure, a computer-readable storage medium is provided.

[0128] A computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor of a terminal device and executing the survival prediction method based on multi-granularity graph pattern mining.

Embodiment 3

[0130] According to an aspect of one or more embodiments of the present disclosure, a terminal device is provided.

[0131] A terminal device comprising a processor and a computer-readable storage medium, the processor is used to implement each instruction; the computer-readable storage medium is used to store a plurality of instructions, the instruction is suitable for being loaded by the processor and executed A survival prediction method based on multi-granularity graph pattern mining.

[0132] When these computer-executable instructions run in the device, the device executes the methods or processes described in the various embodiments of the present disclosure.

[0133] In this, the computer program product may include a computer-readable storage medium, which carries computer-readable program instructions for executing various aspects of the present disclosure. The computer-readable storage medium may be a tangible device that can hold and store instructions used by the instru...

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 discloses a survival prediction method and system based on multi-granularity graph mode mining, and the method comprises the steps: receiving the medical history data of insured persons,and carrying out the statistical construction of the statistical features of the insured persons; for each insured person, constructing a heterogeneous information network according to the medical history data of the insured person; mining a medical mode from the heterogeneous information network by adopting a multi-granularity graph mode mining algorithm to serve as a mode feature; evaluating partial regression coefficients of the statistical characteristics and the mode characteristics through a Cox survival prediction model, and calculating the risk of each characteristic based on proportional risk hypothesis to serve as an enhanced characteristic; combining the statistical characteristics, the mode characteristics and the enhanced characteristics as a complete characteristic set, andperforming survival prediction by adding a random forest scoring function for evaluating the deletion data prediction condition.

Description

Technical field [0001] The present disclosure belongs to the technical field of electronic health data processing, and relates to a survival prediction method and system based on multi-granularity graph pattern mining. Background technique [0002] The statements in this section merely provide background information related to the present disclosure, and do not necessarily constitute prior art. [0003] Survival prediction research is to predict how long an event of interest (also called a "failure event") will occur from a certain moment based on follow-up information. Generally speaking, the main research goals of survival prediction include exploring the role of prognostic factors and predicting how new patients will perform. Therefore, it will help doctors answer real-world questions such as how much benefit a certain medical treatment will bring to patients, and the estimated life span of patients after treatment. The events of interest for survival prediction are not limite...

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): G16H50/30G16H50/70
CPCG16H50/30G16H50/70
Inventor 史玉良任永健郑永清张坤陈志勇
Owner SHANDONG UNIV
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