ANALYSIS ON ADVERSE DRUG REACTION USING DIFFERENT DATA MINING TECHNIQUES

Abstract

Drug toxicity is a pressing health problem which is also an impediment to the development of therapeutically effective drugs. Despite many on-going efforts to determine the toxicity beforehand, computational prediction of drug side-effects remains a challenging task. An approach to predict side-effects by utilizing side-information sources for the drugs, while simultaneously comparing state-of-the-art machine learning methods to improve accuracy. Specifically, the thesis implements a data analysis pipeline for obtaining side-information that are useful for the prediction task. Then formulates the drug side-effect prediction as a machine learning problem: Given disease indications and structural features (as side-information sources) of drugs, for which some measurements of side-effect exist, predict side effect for a new drug. This paper summarizes adverse drug using mining different methods, general database analysis in data mining.