Abstract: Adverse drug reactions (ADR) result in significant morbidity and mortality in patients, and a substantial proportion of these ADRs are caused by drug--drug interactions (DDIs). Pharmacovigilance methods are used to detect unanticipated DDIs and ADRs by mining Spontaneous Reporting Systems, such as the US FDA Adverse Event Reporting System (FAERS). However, these methods do not provide mechanistic explanations for the discovered drug--ADR associations in a systematic manner. In this paper, we present a systems pharmacology-based approach to perform mechanism-based pharmacovigilance. We integrate data and knowledge from four different sources using Semantic Web Technologies and Linked Data principles to generate a systems network. We present a network-based Apriori algorithm for association mining in FAERS reports. We evaluate our method against existing pharmacovigilance methods for three different validation sets. Our method has AUROC statistics of 0.7--0.8, similar to current methods, and event-specific thresholds generate AUROC statistics greater than 0.75 for certain ADRs. Finally, we discuss the benefits of using Semantic Web technologies to attain the objectives for mechanism-based pharmacovigilance.
Learning Objective 1: Develop a mechanism-based pharmacovigilance method that mines spontaneous reporting systems to detect unanticipated drug-drug interactions and adverse reactions that manifest due to those drug-drug interactions.
Learning Objective 2: Provide an explanation of all possible underlying biological mechanisms, ranked on a confidence metric, behind drug-drug interactions and drug-adverse reaction associations observed in patients.
Learning Objective 3: Present an architecture that can easily integrate data and knowledge from multiple heterogeneous biomedical sources simultaneously, and can generate a systems pharmacology network composed of drugs, proteins, pathways and phenotypes.
Learning Objective 4: Compare our method with two existing state-of-the-art methods in pharmacovigilance over three validation datasets.
Maulik Kamdar (Presenter)
Mark Musen, Stanford University