Acute Lymphoblastic Leukemia Prediction using Classification

Abstract

Leukemia’s are cancers of the hematopoietic stem cells that cause the bone marrow to be replaced by neoplastic cells in a diffuse manner. Leukemia has been linked to a variety of potential causes, including genetic and environmental factors, infections, and immunodeficiency conditions. Based on the cell type involved, the blast cells' level of maturity, and the leukemia's swiftly deadly course in untreated individuals, leukemia’s are categorized. The primary objective of this work is to predict Acute Lymphoblastic Leukemia (ALL) image classification using a proposed EHO_ LLRBFNN classification algorithm. The proposed algorithm is compared with popular existing classification algorithms such as k- Nearest Neighbor (k-NN), Naïve Bayes (NB), Support Vector Machine (SVM), and Elephant Herd Optimization (EHO). From the result observation, it is noticed that the proposed EHO_ LLRBFNN algorithm provides high Precision, Recall, F-Score, Accuracy, and minimum error rate than existing algorithms.