Related Experiment Video
Updated: Jun 7, 2026

High-throughput and Comprehensive Drug Surveillance Using Multisegment Injection-Capillary Electrophoresis-Mass Spectrometry
Published on: April 23, 2019
Mining multi-item drug adverse effect associations in spontaneous reporting systems
Rave Harpaz1, Herbert S Chase, Carol Friedman
1Department of Biomedical Informatics, Columbia University, 622 West 168th St, VC5, New York, NY 10032, USA. rave.harpaz@dbmi.columbia.edu
This study introduces a novel data mining approach to identify complex adverse drug event (ADE) associations from large datasets. The method successfully extracted numerous multi-drug adverse event relationships, validating existing ones and uncovering potential new drug interactions.
Area of Science:
- Pharmacovigilance
- Data Mining
- Drug Safety
Background:
- Current pharmacovigilance relies on bivariate analysis, studying single drug-adverse effect pairs.
- Detecting multi-item adverse drug event (ADE) associations involving multiple drugs and effects is crucial but challenging.
- Association rule mining, a data mining technique, is adapted for detecting complex ADE associations.
Purpose of the Study:
- To apply association rule mining to the FDA's AERS database for identifying multi-item ADE associations.
- To demonstrate the value of this tailored data mining method on a large scale.
- To explore the potential for discovering novel multi-drug adverse event relationships.
Main Methods:
- Utilized association rule mining, a data mining technique.
- Applied the method to the FDA's Adverse Event Reporting System (AERS) data.
- Analyzed 162,744 suspected ADE reports from 2008.
Main Results:
- Identified 1167 multi-item ADE associations.
- 67% of identified associations were clinically validated as previously recognized ADEs.
- Several potentially novel ADEs and 4% known drug-drug interactions were also identified.
Conclusions:
- Multi-item ADEs can be effectively extracted from the FDA AERS using the proposed methodology.
- The developed method serves as a valid approach for the initial identification of multi-item ADEs.
- Limitations related to the method and data quality were identified.
Related Concept Videos
Pharmacovigilance
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...
Drug Toxicity: Risk factors
Drug Toxicity: Overview
Pharmaceutical Poisoning: Potential Scenarios
Drug Accumulation During Multiple Dosing: Intermittent IV Infusions
Therapeutic Drug Monitoring: Affecting Factors

