ArticleJournal of the American Pharmacists Association : JAPhA
Risk stratification of potential drug interactions involving common over-the-counter medications and herbal supplements by a large language model.
Article in Journal of the American Pharmacists Association : JAPhA. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 8 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
8 citing papers in PubMed.
- Large Language Models in Adverse Drug Reaction Detection and Pharmacovigilance: A Systematic Review of Current Applications, Challenges, and Future Directions.Diagnostics (Basel, Switzerland) · 2026Review
- Large Language Model Performance and Clinical Reasoning Tasks.JAMA network open · 2026Article
- Drug-drug interaction identification using large language models.medRxiv : the preprint server for health sciences · 2025Article
- Global patterns of polypharmacy after acute heart failure hospitalization: Prevalence and outcomes from the REPORT-HF registry.European journal of heart failure · 2025Article
- Designing Patient-Centered Communication Aids in Pediatric Surgery Using Large Language Models.Journal of pediatric surgery · 2025Article
- The Digital Standardized Patient: An Artificial Intelligence Coach for Cultural Dexterity in Surgical Care.Journal of the American College of Surgeons · 2025Article
- Synthetic medical education in dermatology leveraging generative artificial intelligence.NPJ digital medicine · 2025Article
- A Future of Self-Directed Patient Internet Research: Large Language Model-Based Tools Versus Standard Search Engines.Annals of biomedical engineering · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
7 authors.
Funding
Abstract
backgroundAs polypharmacy, the use of over-the-counter (OTC) drugs, and herbal supplements becomes increasingly prevalent, the potential for adverse drug-drug interactions (DDIs) poses significant challenges to patient safety and health care outcomes.
objectiveThis study evaluates the capacity of Generative Pre-trained Transformer (GPT) models to accurately assess DDIs involving prescription drugs (Rx) with OTC medications and herbal supplements.
methodsLeveraging a popular subscription-based tool (Lexicomp), we compared the risk ratings assigned by these models to 43 Rx-OTC and 30 Rx-herbal supplement pairs.
resultsOur findings reveal that all models generally underperform, with accuracies below 50% and poor agreement with Lexicomp standards as measured by Cohen's kappa. Notably, GPT-4 and GPT-4o demonstrated a modest improvement in identifying higher-risk interactions compared to GPT-3.5.
conclusionThese results highlight the challenges and limitations of using off-the-shelf large language models for guidance in DDI assessment.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.