A Survey of Thalassemia and Iron Deficiency Anaemia Classification using a Voting Classifier

Abstract

Thalassemia is viewed as a prevalent inherited blood disease that has gotten exorbitant consideration in the field of medical research around the world. Inherited diseases have a high risk that children will get these diseases from their parents. If both the parents are β-Thalassemia carriers then there are 25% chances that each child will have β-Thalassemia intermediate or β-Thalassemia major, which in most of its cases leads to death. Prenatal screening after counseling of couples is an effective way to control β-Thalassemia. Iron deficiency anemia (IDA) is considered one of the most common nutritional deficiencies globally, making it a prevalent health issue. Its prevalence varies among different populations and geographic regions. To diagnose iron deficiency anemia (IDA), healthcare professionals typically perform a series of tests to evaluate the patient's iron status and identify the underlying cause of the deficiency. Thalassemia and iron deficiency anemia are thus two common hematological disorders characterized by abnormal hemoglobin synthesis and reduced iron levels, respectively. Distinguishing between these conditions is crucial for accurate diagnosis and appropriate treatment. Hereby, we propose a classification approach based on an SGR-voting classifier to differentiate between thalassemia and iron deficiency anemia. SGR-VC is an ensemble of three machine learning algorithms: Support Vector Machine, Gradient Boosting Machine, and Random Forest.