DESIGN AND DEVELOPMENT OF A FRAMEWORK FOR PHARMACEUTICAL DRUG TO DRUG INTERACTION PREDICTION SYSTEM USING MACHINE LEARNING

The Drug–Drug Interaction Prediction System helps healthcare professionals quickly identify possible drug interactions. It uses machine learning algorithms like Random Forest, Decision Tree, Logistic Regression, and Naive Bayes along with NLP techniques. TF-IDF is used to convert text data into numerical form for better accuracy. The system includes features like user login, secure data handling, prediction, and admin monitoring. Overall, it provides a reliable and efficient solution for drug interaction prediction.

[1] Feixiong Cheng and Zhiyong Zhao, “Machine learning-based prediction of DDIs,” Journal of the American Medical Informatics Association (JAMIA), 2014. [2] Jae Yong Ryu et al., “Deep learning improves DDI prediction,” Proceedings of the National Academy of Sciences (PNAS), 2018. [3] Peng Zhang et al., “Label propagation for DDI prediction,” Scientific Reports, 2015. [4] Andrej Kastrin et al., “Statistical learning for DDIs,” PLOS ONE, 2018. [5] Raziur Ferdousi et al., “Computational DDI prediction,” Journal of Biomedical Informatics (JBI), 2017.