Implementation Of K-Nearest Neighbor - Certainty Factor For Expert System Detection Of Idiopathic Thrombocytopenic Purpura

Idiopathic Thrombocytopenic Purpura (ITP) is an autoimmune disorder. ITP can occur in children and adults. This disease be fatal because the platelet count low due to destruction of excessive platelets so that it interfere with vital organs bleeding occurs. The lack knowledge ordinary people about disease, many assume bruises nosebleeds on body are caused by fatigue. For that, we need a system imitate expertise expert diagnosing this based symptoms felt. method used support K-Nearest Neighbor Certainty Factor methods which combination 2 methods, where classification results from will given certainty value as produce prediction. combining two diagnosis. Based test using 3 scenarios parameter values k=3, k=5, k=7 obtained highest accuracy rate 90,9%.