Accurate Machine Learning Algorithms Based on Detection of Leukemia Disease: A Review

Abstract

Blood cell disorders are often detected in advanced stages as the number of cancer cells is much higher than the number of normal blood cells. As one of the important aspects of diagnosing leukemia and determining its progress is identifying malignant cells. This paper illustrates the discovery of leukemia and its four main types through machine learning algorithms, as it was found that Computer-Aided Diagnosis (CAD) has progressed rapidly over the past few years. To identify leukemia, multiple machines learning algorithms have been created for early detection. Leukemia is a condition synonymous with white blood cells (WBC) that affect the bone marrow and/or blood. The early, healthy, and reliable diagnosis of leukemia has a major role in treating patients and saving their lives. To define leukemia in relation to its subtypes, several methods have been developed. However, these approaches include improvements in efficiency, learning process, and performance. This research paper is explained to enhance and provide rapid and stable detection of leukemia. To facilitate real-time collaboration between patients and healthcare providers for leukemia research, early diagnosis, and treatment. Thus it can save patients and doctors time and money. While the use of machine learning algorithms has shown accurate results, it depends on the shape and size of the sample and the type of algorithm used to classify the subtypes of leukemia (leukemia).