Predictive Machine Learning Analysis for Leukemia Diagnosis Using K-Means Clustering

Abstract

The aim of the study is to employ a machine learning algorithm to predict the presence of leukemia and identify its type based on clustering concept. The K-means clustering technique is utilized to predict the class type. The dataset consists of blood sample reports from 300 cancer patients, encompassing 13 parameters. An AI-assisted program is employed to predict four types of blood cancer diseases: Chronic Myeloid Leukemia, Acute Lymphocytic Leukemia, Non-Hodgkin Lymphoma, and Hodgkin Lymphoma. The absence of any of these types is also predicted which is categorized as Benign. The result of AI assisted system is validated using performance metrics.