Diagnosis of Diabetes Mellitus using K Nearest Neighbor Algorithm

Diabetes is one of the major global health problems. According to WHO 2011 report, around 346 million people worldwide are suffering from diabetes mellitus. Diabetes Mellitus is a metabolic disease where the improper management of blood glucose levels lead to the risk of many diseases like heart attack, kidney disease and renal failure. In Diabetes Mellitus, body does not properly use the insulin hormone secreted by Pancreas gland. There are so many computerized methods for the diagnosis of Diabetes Mellitus but the main drawback of these methods is that the patient has to undergo several medical tests to provide the input values to the computerized diagnostic system which proves to be very costly and time consuming. With the rapid advancement in the field of Artificial Intelligence, there are so many techniques and algorithms in A.I. that can be effectively used for the prediction and diagnosis of various diseases. These algorithms in artificial intelligence prove to be cost-effective and time saving for diabetic patients and doctors. In this paper, we are diagnosing Diabetes Mellitus using KNearest neighbour algorithm which is one of the most important techniques of A.I. The dataset is taken from www.stanford.edu/~hastie/Papers /LARS/diabetes.data.

[1]  Mosin I. Hasan,et al.  Comparative study of Naïve Bayes Classifier and KNN for Tuberculosis , 2011 .

[2]  Praveen Kumar,et al.  Diagnosis of Diabetes Mellitus based on Risk Factors , 2010 .

[3]  Yu Wang,et al.  A Fast KNN Algorithm for Text Categorization , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[4]  S. Jaafar,et al.  Diabetes mellitus forecast using artificial neural network (ANN) , 2005, 2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research.

[5]  Vaibhav Bajpai,et al.  Application of Artificial Neural Network (ANN) technique for Diagnosing Diabetes Mellitus , 2008, 2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems.

[6]  Andrew P. Bradley,et al.  Intelligible Support Vector Machines for Diagnosis of Diabetes Mellitus , 2010, IEEE Transactions on Information Technology in Biomedicine.

[7]  Asha Gowda Karegowda,et al.  Cascading K-means Clustering and K-Nearest Neighbor Classifier for Categorization of Diabetic Patients , 2012 .

[8]  Y Angeline Christobel,et al.  A NEW CLASSWISE K NEAREST NEIGHBOR (CKNN) METHOD FOR THE CLASSIFICATION OF DIABETES DATASET , 2013 .

[9]  Mu Zhu,et al.  The K-nearest neighbor algorithm predicted rehabilitation potential better than current Clinical Assessment Protocol. , 2007, Journal of clinical epidemiology.