A data mining approach for the diagnosis of diabetes mellitus

In our country diagnosis of a disease are done mostly by expertise and experienced doctors, but still there are cases of wrong diagnosis and treatment. [1] Patient have to undergo various test which are very costly and sometimes all of them are not required so in this way it will hugely increase the bill of a patient unnecessarily. In such cases our proposed work will be very helpful. The aim of this paper is to propose an intelligent and effective methodology for the automated detection of Diabetes Mellitus. This methodology is based on Neural Network. There have been many computerized methods to diagnose Diabetes Mellitus but the drawback of all these methods is that patient still has to undergo various medical tests to provide the input values to the computerized diagnostic system and the overall cost for diagnosis will remain almost same for the patient but in our proposed model user itself sitting from home can diagnose whether he/she is suffering from Diabetes Mellitus or not. There is only need to provide some physical parameter values and on the basis of provided information´s our model will detect whether that person is suffering from Diabetes Mellitus or not. In our work we have used Neural Network, for designing and testing Neural Network we used MATLAB software.