Stochastic Based Clustering and Improved Whale Optimization Algorithm to Predict Sickle Cell Anemia in Tribes of Nilgris

Genetic disease which is known as sickle cell anaemia (SCA) affects red blood cells (RBCs). A change in HBB gene causes aberrant haemoglobin to be produced. Red blood cells (RBC) with this defective haemoglobin have a sickle shape, which can result in a range of health problems. In this research, a classification-based prediction model is suggested by implementing the data mining technique for predicting the SCA disease. For features selection, the Improved Whale Optimization (IWO) is used and for classification, a stochastic based Clustering algorithm is used. The data set used in this work is a collection of sickle cell anemia test results of the tribe peoples who lives in the different areas of Nilgiris region. This dataset contains the data of 300 patients with 14 features related to SCA which are acquired from NAWA-Nilgiri Adivasi Welfare Association in Nilgris. 60% of a dataset is used for testing, while 40% is used for training. Based on testing dataset, the suggested model is assessed in terms of specificity, accuracy, PPV, sensitivity, MCC and NPV. The suggested model has overtaken the other entire compared model in expressions of all the parameters.