Leukemia diagnosis with machine learning ensemble from gene expression data
International Journal of Development Research
Leukemia diagnosis with machine learning ensemble from gene expression data
Received 06th August, 2021; Received in revised form 14th August, 2021; Accepted 06th September, 2021; Published online 30th September, 2021
Copyright © 2021, Jakelyne Machado Lima Silva et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
One of the great challenges of treating leukemia is targeting specific therapies for different categories. Classification models have been improved, making them decisive for improving the treatment of the disease. In this study, gene expression data was used and then different computational machine learning models were applied to establish the diagnosis of Acute Lymphoblastic Leukemia and Acute Myeloid Leukemia type leukemias. Three approaches, combined with data mining techniques, were used: one using a Support Vector Machine algorithm as core, the second one using an Artificial Neural Network and the third one using the Machine Learning Ensemble combination (Artificial Neural Network, Support Vector Machine, Random Forest, Gradient Boosting and k-NN). The Ensemble model achieved a consistent overall performance above 94% for five different learning algorithm evaluation metrics.
