Related Experiment Video
Updated: Feb 24, 2026

Drug Repurposing Hypothesis Generation Using the "RE:fine Drugs" System
Published on: December 11, 2016
Revisiting Disproportionality: Prescription-Adjusted and TF-IDF-Inspired Metrics for Post-Market ADR Detection
Ijay Kaz-Onyeakazi1, Heejun Kim1
1University of North Texas, Denton, Texas, United States.
This study introduces novel metrics for detecting adverse drug reactions (ADRs) in post-market surveillance, improving pharmacovigilance by integrating prescription data. The EF-IDF method showed superior performance in identifying ADR signals for ADHD medications.
Area of Science:
- Pharmacovigilance and Drug Safety
- Computational Pharmacoepidemiology
- Health Informatics
Background:
- Post-market surveillance for adverse drug reactions (ADRs) faces challenges due to underreporting and lack of drug utilization data.
- Existing signal detection methods may not adequately account for variations in drug prescription volumes.
Purpose of the Study:
- To develop and evaluate novel signal detection metrics for ADRs that incorporate drug utilization data.
- To improve the accuracy and efficiency of pharmacovigilance by addressing data limitations.
Main Methods:
- Proposed three new signal detection metrics: EF-IDF (TF-IDF-inspired) and two prescription-adjusted measures.
- Integrated prescription data from Bloomberg Intelligence with the FDA Adverse Event Reporting System (FAERS) data.
- Evaluated metric performance using ADHD medications as a case study, focusing on precision-at-10% for 12 ingredients.
Main Results:
- The EF-IDF metric achieved the highest mean precision (0.56), outperforming traditional proportional reporting ratio (PRR) and other prescription-adjusted metrics.
- Prescription volume was found to negatively influence all evaluated metrics, highlighting the importance of contextual factors in ADR detection.
Conclusions:
- Bias-aware, data-integrated methods like EF-IDF offer significant improvements for ADR signal detection in pharmacovigilance.
- Future research should focus on temporal modeling and more specific prescription data for enhanced ADR identification.
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
Therapeutic Drug Monitoring: Drug Analysis Methods
Therapeutic Drug Monitoring: Affecting Factors
Measurement of Bioavailability: Pharmacodynamic Methods
Pharmaceutical Poisoning: Potential Scenarios

