Data mining is the process of extracting or mining the knowledge from large amount of data. It is used in many real world applications. Mining the data from data set and analyzes the data for decision making process. Various data mining algorithms are applied to improve the decision making process. To discover the causal relationship from electronic patient datasets capture the causality among infrequent events. The proposed system to find the optimum membership function of a fuzzy system using particle swarm optimization. PSO has no evolution operators such as crossover and mutation. The particle swarm optimization concept consists of, at each time step, changing the velocity of each particle toward its and locations. All particles are moved to the test optimum solution. These mining adverse drug reaction signals are useful to discover patient critical condition and reduce the computational complexity for drug safety professionals.