Risk Factors Selection for Predicting Thalassemia Patients using Linear Discriminant Analysis

Thalassemia is an inherited blood disorder caused by abnormal production of hemoglobin. In order to establish an efficient thalassemia prognosis process, the practitioners suggest using complete blood count (CBC) report. Based on CBC report, practitioners often use professional experience and domain knowledge to discover the cause and relevant risk factors. Thus, to the best of our knowledge, this research is the first that uses machine learning techniques to accurately classify and predict thalassemia patients using the parameters of CBC report. WBC, RBC, HB, HCT, Platelets and an additional parameter Ferritin (Iron) are the selected parameters for the experimentations. The experimental analysis of the results show that RBC, HB, and Ferritin (Iron) plays a vital role in the establishment of an efficient thalassemia prognosis process.