Machine learning-based drug risk ranking evaluation method

A machine learning and risk grading technology, applied in the field of machine learning, can solve the problems of difficult risk-return evaluation research, lack of return data, spontaneous reporting of data quality impact, etc.

Active Publication Date: 2019-01-25
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Due to the lack of return data, it can only rely entirely on spontaneously reported partial information, making it difficult to conduct risk-return-based evaluation studies
At the same time, it is also affected by the quality of self-reported data

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
  • Machine learning-based drug risk ranking evaluation method
  • Machine learning-based drug risk ranking evaluation method
  • Machine learning-based drug risk ranking evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0084] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0085] Such as figure 1 As shown, the present invention discloses a method for evaluating drug risk classification based on machine learning, comprising the following steps:

[0086] step 1)

[0087] Step 1.1), obtain the original ADR database, the original ADR data is obtained from the National Adverse Drug Reaction Monitoring Center; this data is the adverse reaction report collected from the National Drug Evaluation Center Adverse Drug Reaction Spontaneous Reporting System database from 2010 to 2011, as the analysis data;

[0088]Step 1.2), data processing;

[0089] Step 1.2.1), the original data may have problems such as missing items, duplication, drug names and adverse reaction names, etc.

[0090] To solve the problem, first delete the missing items in the data, uniquely process the duplicate items, and re-normalize the non-standard names...

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 machine learning-based drug risk ranking evaluation method. According to the method, on the basis of western drug report data in the adverse drug reactions (ADR) of Chinese drugs, a machine learning algorithm is utilized to study the problem of drug risk ranking; three main indicators, namely, a severity report rate, an ADR injury index and an ADR coverage rate, are usedas ranking standards; a support vector machine-based classification algorithm is used to perform risk ranking evaluation on the adverse drug reactions of Western drugs; and the drugs are classified into five safety ranks according to the risks of the adverse reactions. The method of the invention is of great reference significant for the evaluation of the risks of adverse drug reactions.

Description

technical field [0001] The invention relates to a drug risk grading evaluation method, which specifically constructs a grading model for drug risk grading based on the characteristics of adverse drug reactions, and belongs to the technical field of machine learning. Background technique [0002] In recent years, in pharmacovigilance, countries around the world have established a network-based collection system for spontaneous reports of adverse drug reactions. However, the utilization and development of data resources are still insufficient. The main research focuses on the improvement and application of signal detection methods based on imbalance analysis, comparative analysis of signal mining, and the elimination of data masking effects, etc. There is a lack of application research on machine learning methods based on big data. [0003] However, domestic and foreign studies on drug grading mainly focus on the risks of certain types of drugs, lack of systematic evaluation,...

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): G16H70/40
CPCG16H70/40
Inventor 魏建香刘天宇刘美含
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