Mining association patterns of drug-interactions using post marketing FDA’s spontaneous reporting data

• Published in: Journal of biomedical informatics 2016-04, Vol.60, p.294-308
• Main Authors: Ibrahim, Heba, Saad, Amr, Abdo, Amany, Sharaf Eldin, A.
• Format: Article
• Language: English
• Subjects: Adverse Drug Reaction Reporting Systems; Algorithms; Association rule mining; Computer Systems; Data mining; Data Mining - methods; Databases, Factual; Drug Interactions; Drug-Related Side Effects and Adverse Reactions; Drugs; Drugs, Generic; Drug–drug interaction; Humans; Logistic regression; Marketing; Pharmacovigilance; Proportional reporting ratio; Regression Analysis; Reporting; RxNorm; Samples; Software; Spontaneous; Statistical methods; United States; United States Food and Drug Administration
• ISSN: 1532-0464; 1532-0480
• DOI: 10.1016/j.jbi.2016.02.009

[Display omitted] •Drug interactions contribute 6–30% of all adverse drug events.•Proper data preprocessing helps to avoid spurious DI signals.•We propose hybrid apriori that shows efficiency to extract DIs from FAERS data.•We can assess the algorithm performance despite lack of a domain gold standard.•We can validate potential DIAE signals via logistic regression modeling. Pharmacovigilance (PhV) is an important clinical activity with strong implications for population health and clinical research. The main goal of PhV is the timely detection of adverse drug events (ADEs) that are novel in their clinical nature, severity and/or frequency. Drug interactions (DI) pose an important problem in the development of new drugs and post marketing PhV that contribute to 6–30% of all unexpected ADEs. Therefore, the early detection of DI is vital. Spontaneous reporting systems (SRS) have served as the core data collection system for post marketing PhV since the 1960s. The main objective of our study was to particularly identify signals of DI from SRS. In addition, we are presenting an optimized tailored mining algorithm called “hybrid Apriori”. The proposed algorithm is based on an optimized and modified association rule mining (ARM) approach. A hybrid Apriori algorithm has been applied to the SRS of the United States Food and Drug Administration’s (U.S. FDA) adverse events reporting system (FAERS) in order to extract significant association patterns of drug interaction-adverse event (DIAE). We have assessed the resulting DIAEs qualitatively and quantitatively using two different triage features: a three-element taxonomy and three performance metrics. These features were applied on two random samples of 100 interacting and 100 non-interacting DIAE patterns. Additionally, we have employed logistic regression (LR) statistic method to quantify the magnitude and direction of interactions in order to test for confounding by co-medication in unknown interacting DIAE patterns. Hybrid Apriori extracted 2933 interacting DIAE patterns (including 1256 serious ones) and 530 non-interacting DIAE patterns. Referring to the current knowledge using four different reliable resources of DI, the results showed that the proposed method can extract signals of serious interacting DIAEs. Various association patterns could be identified based on the relationships among the elements which composed a pattern. The average performance of the method showed 85% precision, 80% negative predictive v