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

Drug risk grading method based on naive random oversampling and support vector machine

A technology of support vector machine and risk classification, which is applied in the field of drug risk classification based on naive random oversampling and support vector machine, which can solve the problems of lack of machine learning automatic decision-making and so on.

Inactive Publication Date: 2021-08-31
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

RX and OTC can be transformed into each other under certain conditions. At present, this kind of transformation is mainly through the application of pharmaceutical companies and the approval of the state. The approval process is mainly expert investigation, mainly manual, and lacks the method of automatic decision-making based on machine learning.

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
  • Drug risk grading method based on naive random oversampling and support vector machine
  • Drug risk grading method based on naive random oversampling and support vector machine
  • Drug risk grading method based on naive random oversampling and support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] The method for drug risk classification based on naive random oversampling and support vector machine includes the following steps:

[0061] Step 1: Query the factors associated with the risk of adverse drug reactions in the spontaneously reported data, and establish the I 1 , I 2 , I 3 as an indicator of risk;

[0062] Step 2: Calculate the three index values ​​of each drug based on the self-reported data;

[0063] The third step: taking drugs as objects and using three indicators as characteristics to establish a drug risk matrix;

[0064] Step 4: According to the National Essential Drugs List, classify the two types of drugs in the drug risk matrix. Prescription drugs are marked as "0" and non-prescription drugs are marked as "1". The marked data set is the original data, which is recorded as D 0 ;

[0065] Step 5: Since the number of prescription drugs is much larger than that of non-prescription drugs, the sample expansion of non-prescription drug data in the ...

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 drug risk grading method based on naive random oversampling and a support vector machine, and the method comprises the steps: constructing risk indexes I1, I2 and I3 based on adverse drug reaction risk factors, processing adverse drug reaction spontaneous report data, calculating three risk index values, taking a drug as an object, taking the risk indexes as features, constructing a drug risk matrix, inquiring national basic drug catalogs, marking drug categories, expanding non-prescription drug data by using naive oversampling, realizing the balance of prescription drug and non-prescription drug sample sizes, establishing a classification model and verifying by using a dichotomy support vector machine, and realizing intelligent management of drug risk classification. According to the method, unbalanced sampling is carried out on processed data, then binary classification of drugs is realized by using the support vector machine, and finally, the function of automatic classification according to adverse reactions of different drugs is realized.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to a drug risk classification method based on naive random oversampling and support vector machines. Background technique [0002] With the rapid advancement of science and technology and its wide application in medicine, it has provided important tools for relieving patients' pain and curing various diseases, greatly improving the health level of patients, not only improving the quality of life of patients, but also effectively prolonging the life expectancy of patients. Longevity has brought a lot of convenience to our life. Because of the unpredictable adverse drug reaction (Adverse Drug Reaction, ADR) of drugs after marketing, it poses a threat to human health. [0003] Adverse drug reaction spontaneous reporting system plays an important role in timely detection of adverse reactions, timely assessment of drug safety risks, and ensuring drug safety. [000...

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): G16H70/40G06N20/10
CPCG16H70/40G06N20/10
Inventor 胡天玲魏建香黄溢凡李天贤
Owner NANJING UNIV OF POSTS & TELECOMM
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