Analysis of anemia using data mining techniques with risk factors specification

Deficiency in healthy Red Blood Cells (RBC) leads to insufficient oxygen to be carried to whole blood tissues. Many reasons cause such an issue like iron or vitamin deficiency which is known as Anemia. Pregnant women, children under the age of 6, people with a low vitamin diet and losing their blood due to surgery or injury are at risk that will tend to have anemia. Such a disease can be diagnosed by blood test called Complete Blood Count (CBC), which evaluates Hemoglobin levels of patient's blood. Undiagnosed or untreated left disease, such as anemia, can cause health problems such as severe fatigue and pregnancy complications. Different types of anemia, especially those associated with iron or vitamin deficiency, can be ameliorated, especially when detected at an early stage. In this paper, four techniques, Bayesian Network (BN), Naive Bayes (NB), Logistic Regression (LR) and Multilayer Perceptron (MLP) have been applied to predict anemia based on 539 data, with 10 attributes, collected from laboratories. The LR has given better results compared to other considered techniques. In addition, attribute evaluators such as information gain have been applied to demonstrate the high performance of the system with minimum characteristics.