1-8
Comparison of Data Mining Algorithms for Diagnosis of Diabetes Mellitus
Authors: Ahmed Sami Jaddoa & Ziyad Tariq Mustafa Al-Ta'i
Number of views: 81
Diabetes is specified as the most chronic and deadliest disease that results in increasing blood sugar. The medical data
mining approaches were utilized for detectingun observed patterns in the medical field sof sets of data for medical
diagnosis and treatment. Data classification for diabetes mellitus is quite significant. Where utilizing two types of data
sets, the first is local, collected from consulting laboratories at Baqubah General Hospital, and the second is global, which
is the Pima India Diabetes Database. The experiment on the Local dataset shows that the accuracy if K-NN is 90 %, the
accuracy of the SVM has been 98 %, the accuracy of the NB is 98 % and the accuracy of RF is 98 %. The experiment on
the Pima dataset shows that the accuracy of K-NN is 81 %, the accuracy of SVM has been82 %, the accuracy of NB is 84
% and the accuracy of RF is 82 %.