A Data-Driven Medical Decision Framework for Associating Adverse Drug Events with Drug-Drug Interaction Mechanisms

Area of Science:

• Pharmacology
• Computational Biology
• Drug Safety

Background:

• Adverse drug events (ADEs) arise from complex drug-drug interactions (DDIs), leading to significant morbidity and mortality.
• Current research often focuses on detecting ADEs rather than understanding the underlying DDI mechanisms.
• Elucidating DDI mechanisms is crucial for effective pharmacovigilance and predicting adverse drug reactions (ADRs).

Purpose of the Study:

• To present a novel data-driven framework for knowledge-driven analysis of ADE mechanisms.
• To identify and rank DDI mechanisms associated with potential ADEs.
• To categorize ADEs based on the number of identified DDI mechanism associations.

Main Methods:

• Developed a framework combining a semantic inference system and enrichment analysis.
• Applied the framework to identify potential ADE mechanisms.
• Ranked mechanisms by DDI relevance and categorized ADEs by mechanism associations.
• Validated the framework using commercial and public DDI resources.

Main Results:

• Successfully identified and ranked DDI mechanisms relevant to ADEs.
• Demonstrated the framework's effectiveness in categorizing ADEs based on DDI mechanism associations.
• Validated the framework's capability using established DDI databases.

Conclusions:

• The developed framework is effective for identifying ADE mechanisms.
• This approach offers a valuable tool for enhancing pharmacovigilance efforts.
• Future research can expand the framework by incorporating broader datasets for deeper insights.