A mathematical modelling to detect sickle cell anemia using Quantum graph theory and Aquila optimization classifier.

Recently genetic disorders are the most common reason for human fatality. Sickle Cell anemia is a monogenic disorder caused by A-to-T point mutations in the β-globin gene which produces abnormal hemoglobin S (Hgb S) that polymerizes at the state of deoxygenation thus resulting in the physical deformation or erythrocytes sickling. This shortens the expectancy of human life. Thus, the early diagnosis and identification of sickle cell will aid the people in recognizing signs and to take treatments. The manual identification is a time consuming one and might outcome in the misclassification of count as there is millions of red blood cells in one spell. So as to overcome this, data mining approaches like Quantum graph theory model and classifier is effective in detecting sickle cell anemia with high precision rate. The proposed work aims at presenting a mathematical modeling using Quantum graph theory to extract elasticity properties and to distinguish them as normal cells and sickle cell anemia (SCA) in red blood cells. Initially, input DNA sequence is taken and the elasticity property features are extracted by using Quantum graph theory model at which the formation of spanning tree is made followed by graph construction and Hemoglobin quantization. After which, the extracted properties are optimized using Aquila optimization and classified using cascaded Long Short-Term memory (LSTM) to attain the classified outcome of sickle cell and normal cells. Finally, the performance assessment is made and the outcomes attained in terms of accuracy, precision, sensitivity, specificity, and AUC are compared with existing classifier to validate the proposed system effectiveness.