OBJECTIVES: The aim of the present study was to develop and evaluate an Adverse Drug Reaction Risk Score (ADR-risk score) to identify patients who are at increased risk to develop an adverse drug reaction (ADR). METHODS: Data for the development of ADR-risk score were collected from a public teaching hospital of northern-India. Variables associated with ADRs were identified by a forward stepwise logistic regression analysis and used to compute the ADR risk score. The ADR risk score was then evaluated for performance by receiver operator characteristic (ROC) curve. RESULTS: Of 887 patients (mean [SEM] age, 44.6 [0.6] years) 99 (11.2%) experienced an ADR. The number of drugs and a cardiac disease condition were the strongest predictors of ADRs, followed by kidney disease, diabetes, and age ≥60 years. These variables were used to compute the ADR risk score. The area under the ROC curve, which assesses the accuracy of the risk score to predict ADRs, was 0.76 (95% confidence interval, 0.70- 0.81), and 76% of accuracy. CONCLUSIONS: The ADR risk score is likely to contribute to a better identification of ADRs and those at risk for ADRs. The present study proposes a method of identifying patients who are at increased risk for an ADR and who may be targeted at reducing drug-related illnesses.