Privacy-Preserving Framework for Smart Prediction of Drug Side Effects
Eka Asibong Ibeh, Alalibo Ralph Fiberesima · International Journal of Computer Applications · 2023
Side effects and adverse reactions are major public health concerns and major causes of drug failure.Predicting side effects is crucial for controlling development costs, time, and launching effective drugs for patient health recovery and preventing immediate withdrawal from the market.The new system is smart drug side effect prediction using deep neural network with the chemical structure of drugs.As it is a common experience that a single drug can cause multiple side effects, that's why we have proposed a deep neural network model that can predict multiple side effects for a single drug.This study has examined two side effects: Dizziness and Headache.The dataset was collected for the drug side effects information from the SIDER database.We have achieved an accuracy of '0.9494' with our multi-label classification based proposed model.The proposed model can be used in different stages of the drug development process.The methodology adopted the Agile software design methodology and unified modeling language as design tool.Python programming language was used for its implementation.