Advancing Drug-Drug Interactions Research: Integrating AI-Powered Prediction, Vulnerable Populations, and Regulatory Insights

Wenzhun Huang^1,2*Xiao Wang^3,4Yunhao Chen^1,2ChangQing Yu¹Shanwen Zhang^1,2

• ¹School of Electronic Information, Xijing Unversity, Xi'an, China
• ²Key Laboratory of High Precision Industrial Intelligent Vision Measurement Technology, Xi’an, Shaanxi 710123, China, Xi’an, China
• ³School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, 250200, China, Jinan, China
• ⁴Shandong Provincial Key Laboratory of Industrial Big Data and Intelligent Manufacturing, Qilu Institute of Technology, Jinan, 250200, China, Jinan, China

Drug-drug interactions (DDIs) pose a significant and intricate challenge in clinical pharmacotherapy, especially among older adults who often have chronic conditions that necessitate multiple medications. These interactions can undermine the effectiveness of treatments or lead to adverse drug reactions (ADRs), which in turn can increase illness rates and strain healthcare resources. Traditional methods for detecting DDIs, such as clinical trials and spontaneous reporting systems, tend to be retrospective and frequently fall short in identifying rare, population-specific, or complex DDIs. However, recent advancements in artificial intelligence (AI), systems pharmacology, and real-world data analytics have paved the way for more proactive and integrated strategies for predicting DDIs. Innovative techniques like graph neural networks (GNNs), natural language processing, and knowledge graph modeling are being increasingly utilized in clinical decision support systems (CDSS) to improve the detection, interpretation, and prevention of DDIs across various patient demographics. This review aims to provide a thorough overview of the latest trends and future directions in DDIs research, structured around five main areas: (1) epidemiological trends and high-risk drug combinations, (2) mechanistic classification of DDIs, (3) methodologies for detection and prediction, particularly those driven by AI, (4) considerations for vulnerable populations, and (5) regulatory frameworks and pathways for innovation. Special emphasis is placed on the role of pharmacogenomic insights and real-world evidence in developing personalized strategies for assessing DDIs risks. By connecting fundamental pharmacological principles with advanced computational technologies, this review seeks to guide clinicians, researchers, and regulatory bodies. The integration of AI, multi-omics data, and digital health systems has the potential to significantly enhance the safety, accuracy, and scalability of DDIs management in contemporary healthcare.