Survey Paper on Predicting Drug Combination Risk Levels

Abstract

Polypharmacy, the simultaneous use of multiple medications, significantly increases the risk of adverse Drug-Drug Interactions (DDIs), posing serious challenges to patient safety and healthcare systems. Traditional DDI detection methods are often binary and lack clinical interpretability, failing to provide actionable risk assessments for healthcare professionals. This survey comprehensively reviews computational approaches for DDI prediction, with a focus on Graph Neural Network (GNN) architectures and their integration with Large Language Models (LLMs) for enhanced clinical decision support. We analyze ten representative works spanning relational graph convolutional networks, meta path based heterogeneous networks, multimodal fusion frameworks, and hybrid approaches. Our analysis reveals that while GNN based methods show superior performance in capturing molecular relationships, significant gaps remain in clinical interpretability, risk level classification, and real world deployment. Building on these insights, we propose an integrated framework combining GNNs for molecular analysis with LLMs for contextual reasoning and recommendation refinement. The proposed system categorizes DDI risks into low, moderate, and high levels and suggests safer alternative drugs. We discuss the societal relevance of DDI prediction systems in promoting sustainable healthcare and their alignment with Sustainable Development Goals (SDGs). Finally, we outline future research directions including real time clinical integration, multimodal data fusion, and enhanced explainability for non-technical users.