Survey Paper on Predicting Drug Combination Risk Levels

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.

Drug-Drug Interactions, Graph Neural Net- works, Polypharmacy, Clinical Decision Support, Large Lan- guage Models, Risk Prediction

1. W. Zhang, C. Li, and M. Zhao, “Accurate prediction of drug combination risk levels based on relational graph convolutional network and multi- head attention,” IEEE Access, 2024. [Google Scholar] [Crossref]

2. L. Tian, Q. Wang, and Z. Zhou, “Predicting drug combination side ef- fects based on a meta-path-based heterogeneous graph neural network,” BMC Bioinformatics, 2025. [Google Scholar] [Crossref]

3. W. Li, W. Ma, M. Yang, and X. Tang, “Drug repurposing based on the DTD-GNN graph neural network: Revealing the relationships among drugs, targets, and diseases,” BMC Genomics, 2024. [Google Scholar] [Crossref]

4. L. Zhang, X. Kang, and X. Yang, “MOSAIC: A multi-granularity cross- modal framework for predicting synergistic drug combinations,” IEEE Journal of Biomedical and Health Informatics, 2025. [Google Scholar] [Crossref]

5. W. Liu, J. Zhang, and G. Qiao, “HMMF: A hybrid multi-modal fusion framework for predicting drug side effect frequencies,” BMC Bioinformatics, 2024. [Google Scholar] [Crossref]

6. S. Zhang, C. Yu, and C. Zhang, “SCATrans: Semantic cross-attention transformer for drug-drug interaction prediction through multimodal biomedical data,” BMC Bioinformatics, 2025. [Google Scholar] [Crossref]

7. Jalali, P. Johannesson, and E. Perjons, “DDIs-Graph: An approach to identify drug-drug interactions and recommend alternative drugs,” in Recent Advances in Drug Discovery and Bioinformatics. Cham, Switzerland: Springer, 2024. [Google Scholar] [Crossref]

8. F. Tanvir, K. Saifuddin, M. Islam, and E. Akbas, “DDI prediction with heterogeneous information network: Meta-path based approach,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2024. [Google Scholar] [Crossref]

9. N. Abdu, S. Idrisnur, and H. Said, “Inappropriate medication prescribing, polypharmacy, potential drug-drug interactions, and medication regimen complexity in older adults,” BMC Geriatrics, 2025. [Google Scholar] [Crossref]

10. O. N. Dara, A. Ibrahim, and T. Mohammed, “Advancing medical imaging: Detecting polypharmacy and adverse drug effects with graph convolutional networks,” Journal of Medical Imaging and Health Infor- matics, 2025. [Google Scholar] [Crossref]

• Design and Performance Test of a Prototype MRI-Compatible Cascaded Pressure Microsensor