Discrimination between Iron Deficiency Anaemia (IDA)and β-Thalassemia Trait (β-TT) Based on PatternBased Input Selection Artificial Neural Network (PBISANN)

Discrimination between iron deficiency (IDA) anemia and β-thalassemia trait(β-TT) is a time consuming and costly problem. Because, they have approximatesimilar effects on routine blood test indices, in some cases, the complementary tests,which are expensive and time consuming, would be needed for differentiate theanemia. Complete blood count (CBC) is a fast, inexpensive, and accessible medicaltest that is used as a primary test for diagnosis anemia. However, when the CBCindices cannot exactly state the subject, more advanced tests such as electrophoresisof hemoglobin must be performed. In this study, the CBC indices have beenconsidered as the inputs of classifier and the chosen architecture is pattern-basedinput selection artificial neural network (PBIS-ANN). For evaluation the proposedmethod, traditional methods, which are still using for the problem such as MentzerIndex (MI), and several automated anemia diagnostic systems such as artificialneural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS) and multilayer perceptron (MLP) have been compared with the proposed method. The resultsindicate that the proposed method significantly outperforms the mentioned methods.