PENERAPAN DATA MINING DALAM PENGELOMPOKAN PENDERITA THALASSAEMIA

Abstrak

Thalassaemia is the genetic disease caused by deficiency and syinthesis of globin chains. It influences our body by decreasing eroticist and hemoglobin degree. People with Thalassaemia in 2015 at Tasikmalaya, Garut, and ciamis west java were 203 people. They organized in POPTI Tasikmalaya branch that placed in Dr. Soekardjo and Preasetya Bunda hospital. On the therapy process, they have different time needs and blood volume needs in every transfusion process. On the other hand, the difference transfusion levels also influence in giving iron chelation medicine. Furthermore, the method needed to help POPTI committee and health staff in appropriating blood volume and Iron Chelating Agent trough Thalassaemia people. Datamining method used by applying clustering method used K-means algorithm. Furthermore, this research conducted to categorized people with Thalassaemia based on blood volume need and HB in every transfusion process. Moreover, the pattern known by minor Thalassaemia, intermediate Thalassaemia, and mayor Thalassaemia based on age pattern, HB level in transfusion process, and blood volume needs. The research method in this research is begin by pre observation and data mining analysis method to analyze data on data mining using 3 steps of KDD such as data cleaning, data integration, data selection, data transformation, and data knowledge presentation. Further, the result of this research has 374 data that divided into 3 cluster. They are cluster 1 that has 214 data, cluster 2 has 137 data, and cluster 3 that has 23 data with the pattern that shows that the transfusion blood volume increase based on patient’s age.