Language models for drug–drug interactions: current applications, pitfalls, and future directions

Abstract

Introduction Advanced artificial intelligence (AI) frameworks particularly, large language models (LLMs) have recently attracted attention for automating Drug – drug interactions (DDIs) extraction and prediction tasks. However, there is a scarcity of reviews on how LLMs can rapidly identify known and novel DDIs.Areas covered This review summarizes the state of LLM-based DDI extraction and prediction, based on a broad literature search from PubMed, Embase, Web of Science, Scopus, IEEE Xplore, the Cochrane Library, ACM Digital Library, Google Scholar, and Semantic Scholar published between January 2000 and February 2025. For DDI extraction from biomedical text and databases, we detail methods utilizing transformer-based models, such as domain-specific BioBERT and general GPT-based architectures. These models have demonstrated improved performance over traditional methods with fine-tuned BioBERT variants achieving F1 scores often exceeding 80% on benchmark datasets like SemEval and TAC for identifying interaction types, including pharmacokinetic/pharmacodynamic (PK/PD) interactions. For DDI prediction, we discuss prediction frameworks including hybrid models (e.g. SmileGNN, DrugDAGT), conversational agents (e.g. ChatGPT), and prompt-based methods (e.g. DDIPrompt). While performance varies, state-of-the-art hybrid models achieve high accuracy (e.g. ~0.96 AUC, ~0.91 F1) on benchmark. Key methodological challenges are highlighted, including data biases and limitations in data quality/access (especially for rare/novel DDIs), the complexity of incorporating patient-specific factors, and the significant issue of limited interpretability and explainability of complex model decisions.Expert opinion LLMs offer potential for advancing pharmacovigilance and clinical decision support. However, realizing this and establishing clinical trust requires urgently addressing current limitations, particularly enhancing model explainability, improving reliability (mitigating hallucinations), and resolving data quality issues. Future research must prioritize rigorous clinical validation (prospective studies), developing robust explainable AI (XAI) techniques, refining data curation, and integrating multimodal patient data. Collaborative efforts are important for integrating validated LLMs effectively into medication safety infrastructure.

Topics & Concepts