Timing Matters: A Machine Learning Method for the Prioritization of Drug-Drug Interactions Through Signal Detection in the FDA Adverse Event Reporting System and Their Relationship with Time of Co-exposure

Vera Battini; Marianna Cocco; Maria Antonietta Barbieri; Greg Powell; Carla Carnovale; Emilio Clementi; Andrew Bate; Maurizio Sessa

doi:10.1007/s40264-024-01430-8

Timing Matters: A Machine Learning Method for the Prioritization of Drug-Drug Interactions Through Signal Detection in the FDA Adverse Event Reporting System and Their Relationship with Time of Co-exposure

Drug Saf. 2024 Apr 30. doi: 10.1007/s40264-024-01430-8. Online ahead of print.

Authors

Vera Battini^{1

2}, Marianna Cocco³, Maria Antonietta Barbieri^{3

4}, Greg Powell⁵, Carla Carnovale⁶, Emilio Clementi^{6

7}, Andrew Bate^{8

9}, Maurizio Sessa³

Affiliations

¹ Department of Drug Design and Pharmacology, University of Copenhagen, Jagtvej 160, 2100, Copenhagen, Denmark. vera.battini@unimi.it.
² Pharmacovigilance and Clinical Research, International Centre for Pesticides and Health Risk Prevention, Department of Biomedical and Clinical Sciences (DIBIC), ASST Fatebenefratelli, Sacco University Hospital, Università degli Studi di Milano, Milan, Italy. vera.battini@unimi.it.
³ Department of Drug Design and Pharmacology, University of Copenhagen, Jagtvej 160, 2100, Copenhagen, Denmark.
⁴ Department of Clinical and Experimental Medicine, University of Messina, Messina, Italy.
⁵ Safety Innovation and Analytics, GSK, Durham, NC, USA.
⁶ Pharmacovigilance and Clinical Research, International Centre for Pesticides and Health Risk Prevention, Department of Biomedical and Clinical Sciences (DIBIC), ASST Fatebenefratelli, Sacco University Hospital, Università degli Studi di Milano, Milan, Italy.
⁷ Scientific Institute, IRCCS E. Medea, Bosisio Parini, LC, Italy.
⁸ GSK, London, UK.
⁹ London School of Hygiene and Tropical Medicine, University of London, London, UK.

PMID: 38687463
DOI: 10.1007/s40264-024-01430-8

Abstract

Introduction: Current drug-drug interaction (DDI) detection methods often miss the aspect of temporal plausibility, leading to false-positive disproportionality signals in spontaneous reporting system (SRS) databases.

Objective: This study aims to develop a method for detecting and prioritizing temporally plausible disproportionality signals of DDIs in SRS databases by incorporating co-exposure time in disproportionality analysis.

Methods: The method was tested in the Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS). The CRESCENDDI dataset of positive controls served as the primary source of true-positive DDIs. Disproportionality analysis was performed considering the time of co-exposure. Temporal plausibility was assessed using the flex point of cumulative reporting of disproportionality signals. Potential confounders were identified using a machine learning method (i.e. Lasso regression).

Results: Disproportionality analysis was conducted on 122 triplets with more than three cases, resulting in the prioritization of 61 disproportionality signals (50.0%) involving 13 adverse events, with 61.5% of these included in the European Medicine Agency's (EMA's) Important Medical Event (IME) list. A total of 27 signals (44.3%) had at least ten cases reporting the triplet of interest, and most of them (n = 19; 70.4%) were temporally plausible. The retrieved confounders were mainly other concomitant drugs.

Conclusions: Our method was able to prioritize disproportionality signals with temporal plausibility. This finding suggests a potential for our method in pinpointing signals that are more likely to be furtherly validated.