Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for eliminating adverse drug reaction data shading effect based on decision tree layering

A technology for adverse reactions and masking effects, applied in the field of signal detection, can solve the problems of signal masking and affecting signal accuracy, and achieve the effects of stable sensitivity, alleviating adverse effects and improving sensitivity.

Active Publication Date: 2020-12-25
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The current spontaneous reporting database has a large number and variety of ADRs, and signal detection is easily affected by confounding factors, which may cause some important signals to be obscured, which will affect the accuracy of signal detection

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
  • Method for eliminating adverse drug reaction data shading effect based on decision tree layering
  • Method for eliminating adverse drug reaction data shading effect based on decision tree layering
  • Method for eliminating adverse drug reaction data shading effect based on decision tree layering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] 1 Data collection

[0044] (1) Summary of original data: Select the ADR monitoring data in Jiangsu Province between January 1, 2010 and December 31, 2017, and record it as data set DATA1, with a total of 680,743 records, including 951 kinds of drugs and 3364 kinds Adverse reactions.

[0045] (2) Establish a standard library: In order to judge the validity of the data classification test results, it is necessary to establish a standard library with known adverse reactions as a reference. Through the network collection of relevant drug instructions, adverse drug reaction information reports issued by the State Food and Drug Administration, pharmacovigilance alerts and various regulatory documents, etc., to establish a known ADR library, which is called the standard library and recorded as data Set DATA2. In DATA2, there are 499,331 drug-adverse reaction combinations, including 5236 drugs and 2461 adverse reactions.

[0046] 2 Data preprocessing

[0047](1) In order to...

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 method for eliminating an adverse drug reaction data shading effect based on decision tree layering. The method is used for researching the problem of eliminating the adversedrug reaction data shading effect based on decision tree layering on the basis of Chinese adverse drug reaction (namely ADR) report data, evaluation indexes based on a standard library are designed,a decision tree for realizing multi-level layering is constructed, differences of data set signal detection before and after layering are compared by an MHRA signal detection method, and finally, a multi-level layering strategy based on the decision tree for reducing the adverse drug reaction data shading effect is provided. The invention provides a reference method for eliminating the data shading effect in signal detection of Chinese adverse drug reaction reports.

Description

technical field [0001] The invention belongs to the field of signal detection, and in particular relates to a method for eliminating the masking effect of adverse drug reaction data based on decision tree layering in my country. Background technique [0002] The current spontaneous reporting database has a large number and variety of ADRs, and signal detection is easily affected by confounding factors, which may cause some important signals to be obscured, which will affect the accuracy of signal detection. Stratified research on drug-adverse reaction reports shows that, compared with direct signal detection on unstratified data, stratification will reveal new associations between drugs and adverse reaction events, which is conducive to reducing confounding factors and masking signals Impact. [0003] In addition, the existing stratification studies have independently studied the impact of confounding factors on signal detection, and in the context of a large number and var...

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): G16H70/40G16H10/40
CPCG16H70/40G16H10/40
Inventor 魏建香阮倩昀卢志强
Owner NANJING UNIV OF POSTS & TELECOMM