Poster Session

Start Date

20-5-2016 12:30 PM

Document Type

Poster Abstract

Description

Adverse Drug Reactions (ADRs) are a major cause of morbidity and mortality in world. There is thus a growing need of methods facilitating the automated detection of drugs-related ADR; especially ADRs that were not known from clinical trials but later arise due to drug-drug interactions. In this research our goal is to discover the severe unknown Adverse Drug Reactions caused by a combination of drugs, also known as Drug-Drug-Interaction. We propose to use Association Rule Mining to find the ADRs caused by using a combination of drugs yet not known to be caused if these drugs were taken individually. For evaluation, we will test out the proposed strategies on real-world medical data extracted from the spontaneous adverse drug reaction reporting system called FAERS. The results mined by our tool will be checked both manually by literature review and then verified by domain experts for interestingness and accuracy.

Keywords

adverse drug reactions

Creative Commons License

Creative Commons Attribution-Noncommercial-Share Alike 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 License.

Share

COinS
 
May 20th, 12:30 PM

Towards Pharmacovigilance Using Machine Learning To Identify Unknown Adverse Reactions Triggered By Drug-Drug Interaction

Adverse Drug Reactions (ADRs) are a major cause of morbidity and mortality in world. There is thus a growing need of methods facilitating the automated detection of drugs-related ADR; especially ADRs that were not known from clinical trials but later arise due to drug-drug interactions. In this research our goal is to discover the severe unknown Adverse Drug Reactions caused by a combination of drugs, also known as Drug-Drug-Interaction. We propose to use Association Rule Mining to find the ADRs caused by using a combination of drugs yet not known to be caused if these drugs were taken individually. For evaluation, we will test out the proposed strategies on real-world medical data extracted from the spontaneous adverse drug reaction reporting system called FAERS. The results mined by our tool will be checked both manually by literature review and then verified by domain experts for interestingness and accuracy.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.