A Comprehensive Study of Machine Learning algorithms for Predicting Leukemia Based on Biomedical Data

Abstract

Leukemia is known as the cancers of the blood or bone marrow. Bone marrow which is known as the spongy tissue creates blood cells. So for blood cell productivity problems, Leukemia can boost. It generally impacts the leukocytes or white blood cells. It grows gradually in our bodies. In this paper our goal is to detect leukemia applying Machine Learning which can help in medical science to detect a patient is a cancer patient or not. Therefore we needed a system for decision making in the Leukemia detection system. That’s why we propose some well-known algorithms to get better accuracy to detect Leukemia in our paper. We have used some different types of machine learning algorithms like Naïve Bayes, Support Vector Machine(SVM), Decision Tree and K-nearest neighbor (KNN) algorithm to get the result that a patient is a cancer patient or not. We collect our data from Z H Shikder Medical College and Hospital which include 401 data in our dataset. Among them, the Decision tree algorithm gives the best result with 100% accuracy of prediction. In this paper, we have also shown the comparative results analyzing different algorithms precision, recall and F1 score for our all data samples.