A Proposed Model for Detecting Drug-Drug Interactions in Hypertension and Diabetes Treatments

Abstract

Hypertension and diabetes are two of the most prevalent chronic diseases in the world, and in their management, a drug combination is usually required. However, drug-drug interactions (DDIs) cause harmful side effects, endangering the safety of the patient and the efficacy of treatment. The proposed study examines the issues of co-management of medications for hypertension and diabetes. The mechanism of action and metabolic pathways common to these drugs create a complex environment, increasing the risk of side effects and decreasing the efficacy of treatment. Artificial intelligence (AI) can be employed to predict drug interactions, pharmacodynamics, and side effects. In this research, an intelligent model is implemented to forecast the outcome of drug interactions in the treatment of diabetes and hypertension. The proposed method can assist in reducing the time and expense required to identify the optimal drug combinations for clinical applications. The DDI dataset was obtained from the Drug Bank database, taking into account drug pairs for hypertension and diabetes. Additionally, some chemical features are extracted from the Simplified Molecular Input Line Entry System (SMILES) strings of the drug pairs. Different machine learning algorithms are applied to these features, such as Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). the performance of XGBoost was better than the others and achieved outstanding accuracy. The proposed model predicted a mean of 97% accuracy for DDIs. The study again highlights the importance of computationally founded predictive modeling in promoting the efficiency of drug administration and lowering the incidence of adverse reactions.