An In-Depth Examination of Drug-Drug Interaction Databases: Enhancing Patient Safety through Advanced Predictive Models and Artificial Intelligence Techniques

Sumayli, Abdulaziz Alkhallaf; Daghriry, Abdulrahim Ibrahim; Sharahili, Mohammed Ali; Alanazi, Abdulhakim Awadh; Alanazi, Adel Abdullah; Alharbi, Ibrahim Fraih; Alghamdi, Fahad Nayesh; Alqarni, Kamal Ali; Aljohani, Naser Mutiq; Alfaqir, Abdulmohsen Mohammad; Shajiri, Ibrahim Mohammed; Albalawi, Abdulrahman Rashid; Alatwi, Fahd Moter; Alrashdi, Munif Sadan; Altaymani, Khalid Abdullah; Alsharari, Meshal Basheer; Albalawi, Alnashmi Mahdi; Alanazi, Sultan Radhi; Alanazi, Abdullah Samah

doi:10.21608/jmals.2024.410645

An In-Depth Examination of Drug-Drug Interaction Databases: Enhancing Patient Safety through Advanced Predictive Models and Artificial Intelligence Techniques

Document Type : Original Article

Authors

KSAFH King Salman Armed Forces Hospital in Northwestern Region, Saudi Arabia

10.21608/jmals.2024.410645

Abstract

Background: Drug-drug interactions (DDIs) pose a significant risk to patient safety, leading to adverse effects and increased hospitalizations. With the rise of polypharmacy, especially among elderly patients and those with chronic conditions, understanding and predicting DDIs has become imperative for effective clinical management. Methods: This review synthesizes current literature on drug-drug interaction databases and their role in predicting DDIs. A systematic search of relevant databases focused on studies utilizing artificial intelligence (AI) and machine learning techniques for DDI prediction. Key databases, such as DrugBank, PubChem, and the Pharmacogenomics Knowledgebase (PharmGKB), were analyzed for their contributions to DDI research. Results: The findings indicate that AI-driven methodologies significantly enhance the identification and prediction of DDIs. Various machine learning techniques, including conventional and unconventional methods, have been employed to assess drug interactions effectively. The review highlights real-world examples of critical DDIs, demonstrating the clinical implications of these interactions. Databases provide essential tools for healthcare providers to manage medications and prevent adverse events.
Conclusion: Integrating drug-drug interaction databases into clinical practice is crucial for improving patient safety and treatment efficacy. Future research should focus on enhancing the predictive capabilities of these models through continuous data integration and validation. By leveraging advanced computational techniques, healthcare systems can better anticipate and mitigate the risks associated with drug interactions.

Keywords