📋 Browse Articles

Drug-drug interactions (DDIs) are a significant source of morbidity and adverse drug events (ADEs), particularly in situations of polypharmacy and complex medication regimens. While rules-based software integrated in electronic health records (EHRs) has demonstrated proficiency in identifying DDIs present in medication regimens, large language model (LLM) based identification requires thorough benchmarking and performance evaluation using high-quality datasets for safe use. The purpose of this study was to develop a series of performance benchmarking experiments specifically for LLM performance in identification and management of DDIs using a specifically curated clinician-annotated dataset of clinically-relevant DDIs. Show less

An analysis of dose, dose frequency, human pharmacokinetics, and potential drug-drug interactions (DDI) was performed on small-molecule oral drugs approved by the FDA from 2020 to 2024 (n = 104). Although most oral drugs are administered QD (67%), BID and TID regimens are also regularly approved (32%). First-in-class (FIC) drugs and drugs with Orphan Drug Designation (ODD) have a higher frequency of BID or TID administration compared to drugs without those designations (BID and TID = 50% for FIC drugs vs 19% for non-FIC; BID and TID = 41% for ODD vs 20% non-ODD). Most drugs are >95% plasma protein bound (58%), with a large fraction >99% bound (29%). Of these drugs, 22% have black box warnings and 42% list contraindications. An examination of DDI revealed the most frequent warning around CYP3A4 induction (60%). These findings will help medicinal chemists better understand and predict typical and nontypical profiles of oral drugs. Show less

Drug-drug interactions (DDI) are an important cause of adverse drug reactions (ADRs). Could large language models (LLMs) serve as valuable tools for pharmacovigilance specialists in detecting DDIs that lead to ADR notifications? Show less

The use of multiple medications increases the risk of harmful drug-drug interactions (DDIs). Conventional DDI screening databases vary in coverage and often trigger low-relevance alerts, contributing to alert fatigue. Large language models (LLMs) have emerged as potential tools for DDI identification, however, their performance compared to established databases using real-world patient data remains under-explored. Show less

Psychiatric diseases are often treated with several drugs. In addition, the risk of developing somatic comorbidities which may require drug therapy is higher in patients with than in patients without psychiatric diseases. Further on, the risk of drug-drug interactions (DDI) increases with the number of drugs taken. The aim of this study was to analyze whether already known DDI between psychiatric drugs and somatic medications still occur in everyday clinical practice. Show less

Background Psychiatric diseases are often treated with several drugs. In addition, the risk of developing somatic comorbidities which may require drug therapy is higher in patients with than in patients without psychiatric diseases. Further on, the risk of drug-drug interactions (DDI) increases with the number of drugs taken. The aim of this study was to analyze whether already known DDI between psychiatric drugs and somatic medications still occur in everyday clinical practice. Methods We analyzed 9,276 spontaneous adverse drug reaction (ADR) reports from Germany contained in the Show less

Background The co-administration of drugs known to interact greatly impacts morbidity, mortality, and health economics. This study aims to examine the drug–drug interaction (DDI) phenomenon with a large-scale longitudinal analysis of age and gender differences found in drug administration data from three distinct healthcare systems. Methods This study analyzes drug administrations from population-wide electronic health records in Blumenau (Brazil; 133 K individuals), Catalonia (Spain; 5.5 M individuals), and Indianapolis (USA; 264 K individuals). The stratified Show less

Drug-drug interactions (DDIs) can produce unpredictable pharmacological effects and lead to adverse events that have the potential to cause irreversible damage to the organism. Traditional methods to detect DDIs through biological or pharmacological analysis are time-consuming and expensive, therefore, there is an urgent need to develop computational methods to effectively predict drug-drug interactions. Currently, deep learning and knowledge graph techniques which can effectively extract features of entities have been widely utilized to develop DDI prediction methods. In this research, we aim to systematically review DDI prediction researches applying deep learning and graph knowledge. The available biomedical data and public databases related to drugs are firstly summarized in this review. Then, we discuss the existing drug-drug interactions prediction methods which have utilized deep learning and knowledge graph techniques and group them into three main classes: deep learning-based methods, knowledge graph-based methods, and methods that combine deep learning with knowledge graph. We comprehensively analyze the commonly used drug related data and various DDI prediction methods, and compare these prediction methods on benchmark datasets. Finally, we briefly discuss the challenges related to drug-drug interactions prediction, including asymmetric DDIs prediction and high-order DDI prediction. Show less

Few data are available on the clinical impact of drug-drug interactions (DDIs). Most of the studies are limited to the analysis of exposure to potential DDI or the targeted impact of the combination of a few drugs or therapeutic classes. The analysis of adverse drug reaction (ADR) reports could be a mean to study generally the adverse effects identified due to a DDI. Our objective was to describe the characteristics of ADRs resulting from DDIs reported to the French Pharmacovigilance system and to identify the drugs most often implicated in these ADRs. Considering all ADR reports from January 01, 2012, to December 31, 2016, we identified all cases of ADR resulting from a DDI (DDI-ADRs). We then described these in terms of patients' characteristics, ADR seriousness, drugs involved (two or more per case), and ADR type. Of the 4,027 reports relating to DDI-ADRs, 3,303 were related to serious ADRs. Patients with serious DDI-ADRs had a median age of 76 years (interquartile range: 63-84); 53% were male. Of all serious DDI-ADRs, 11% were life-threatening and 8% fatal. In 36% of cases, the DDI causing the ADR involved at least three drugs. Overall, 8,424 different drugs were mentioned in the 3,303 serious DDI-ADRs considered. Altogether, drugs from the "antithrombotic agents" subgroup were incriminated in 34% of serious DDI-ADRs. Antidepressants were the second most represented therapeutic/pharmacological subgroup (5% of serious DDI-ADRs). Among the 3,843 ADR types reported in the 3,303 serious DDI-ADRs considered, the most frequently represented were hemorrhage (40% clinical hemorrhage; 6% biological hemorrhage), renal failure (8%), pharmacokinetic alteration (5%), and cardiac arrhythmias (4%). Hemorrhagic accidents are still an important part of serious ADRs resulting from DDIs reported in France. The other clinical consequences of DDIs seem less well identified by pharmacovigilance. Moreover, more than one-third of serious DDI-ADRs involved at least three drugs. Show less