A risk classification method of antibiotics based on cluster analysis

A technology of risk grading and cluster analysis, applied in the field of cluster analysis, can solve problems such as undetectable adverse reactions

Inactive Publication Date: 2019-01-25
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (2) When classifying antibiotics, we creatively introduced the TF-IDF algorithm to extract key adverse reactions. Although the key adverse reactions can reasonably represent this type of antibiotics, it is obviously impossible to examine all related adverse reactions. This is also one of the limitations of this study;

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 risk classification method of antibiotics based on cluster analysis
  • A risk classification method of antibiotics based on cluster analysis
  • A risk classification method of antibiotics based on cluster analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0064] 1) Data collection and processing:

[0065] 1.1) Obtain the original ADR database. All ADR data in this study come from the China Food and Drug Administration (CFDA); select the adverse drug reaction spontaneous report database in my country within two years from 2010 to 2011. Response report data;

[0066] 1.2) Using Microsoft Visual FoxPro to split and preprocess the selected data; 1,209,342 valid records were obtained, 59,220 (4.9%) of the report type were "serious", and 1,150,122 (95.1%) were "general". %); there are 4,875 records of antibiotic data; three record attribute values ​​of report type (general, serious), antibiotic name, and adverse reaction name are extracted, and there are 76 species names and 400 corresponding adverse reaction names;

[0067] 2) signal detection of data: carry out signal detection to described sample by P...

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 an antibiotic risk classification research based on cluster analysis, Based on the reported data of Adverse Drug Reaction (ADR) in China, the study compares the differences ofADR signal detection between different subsamples by PRR detection method, uses FCM method for clustering analysis, uses artificial scoring method to classify the risk of antibiotics, and uses TF-IDFAlgorithm for Feature Extraction. A method for classifying the risk of antibiotics based on clustering analysis in the adverse drug reaction report of China is provided.

Description

technical field [0001] The invention relates to a method for grading antibiotic drug risks based on cluster analysis, in particular to a grading model for constructing drug risk grading based on the characteristics of adverse drug reactions, belonging to the field of cluster analysis. Background technique [0002] The present invention mainly adopts the FCM clustering analysis algorithm to establish a risk classification model, and introduces the TF-IDF algorithm to perform targeted scoring on different adverse reactions, and the classification results are relatively reasonable. However, this risk grading model for antibiotics and their adverse reactions also has certain limitations, the limitations are as follows: [0003] (1) The data of this research comes from the spontaneous report database of adverse drug reactions, and the report simply divides the adverse reactions into two types: general and serious, and the classification of the degree of injury is relatively vague...

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): G06F16/35G06K9/62G06F17/50
CPCG06F2111/04G06F30/20G06F18/23
Inventor 魏建香潘轩超刘美含
Owner NANJING UNIV OF POSTS & TELECOMM
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