Data mining methodologies have been developed for exploration and analysis of large quantities of data to discover meaningful patterns and rules. This paper presents a new technique that employs data mining, to find spatial association rules an effective method for discovering diseases from the symptoms. The proposed system has been projected from the physical parameters which will be very helpful for and will make easier for physicians in their diagnosis of diseases. Data of sample of 2492 patients are evaluated in the projected system. The results of the decision support system have completely matched with those of the physicians' decisions. © EuroJournals Publishing, Inc. 2011.