Study of Adverse Drug effects Using Knowledge Discovery Methods

This is pilot study to find associations, trends and patterns resulting in useful knowledge about drugs and their side effects or adverse drug reactions reported in scientific literature. Method of manual addition of data about drugs, side effects/adverse drug reactions, disease reported in scientific literature has been used to create tables as data collection technique. The current analysis has been done on approximately 2000 records. Several point estimates like the Reporting Odds Ratio (ROR), Proportional ADR Reporting Ratio (PRR) and Yule's Q, have been used, in combination with additional estimators of the precision of point estimates such as the Chi-square test, or the lower limits of the 95% confidence intervals of the point estimates. Around fourteen potentially significant associations (signals) have been detected. Keywords— Adverse Drug Events, Signal detection, Associations, Data mining