Abstract: In this study detection of association between drugs and Adverse Drug Reactions (ADRs), is carried out by using Naive Bayes method. Adverse event reports submitted to the United States Food and Drug Administration (FDA) were reviewed to find top 10 drugs causing frequent ADRs for a particular period. The main objective of this paper is to evaluate drugs associated with list of outcomes provided by FDA. For a particular category of disease, drugs creating outcomes are ranked using Naive Bayes method. FDA represents ADRs in Preferred Terms(PT) by referring Medical Dictionary for Regulatory Activities (MedDRA).To create conceptual hierarchy System Organ Class (SOC) present in MedDRA is mapped with low level Preferred Terms (PT) in FDA dataset. For each SOC the drugs are ranked based on posterior probability obtained by Naive Bayes method. Data mining model has been built to analyse drugs associated with outcome for a disease category in SOC level. The newly designed tool is user friendly and applicable to pharmaceutical industries, policy makers and practitioners.