Using Multi-Feature Selection with machine learning for De novo Acute Myeloid Leukemia in Egypt
Passent Elkafrawy, Ibrahim I. M. Manhrawy, Hanaa Fathi, Mohammed Qaraad, Ayda K. Kelany · 2019
De novo Acute Myeloid Leukemia is one of the diseases from which many people die each year. It is the most common type of all types of cancer and causes death of people all over the world. Classification methods are an efficient means to separate data. Especially in the field of medicine, where these methods are widely used in diagnosis and analysis for decision-making. In this paper, we consider group feature selection in a multiclass classification of other ways. The performance will be compared between different machine learning algorithms: Random Forest classifier (RF), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM) and Naive Bayes (NB) on AML dataset National Cancer Institute (NCI), Cairo University. The main objective is to evaluate the correction in the classification of the data concerning the efficiency and effectiveness of each algorithm in terms of accuracy, precision, sensitivity, and specificity. Experimental results determine that LR gives the enormous accuracy (92.30%) with the lowest error rate. All experiments are affected within a simulation environment and manipulated in Python 3.7 data mining tool.