Leukemia Prediction with AI: A Performance Comparison of K-Means and GMM

Read full text Summarise with VIRAT
Authors: Tabasum Guledgudd, Sayed Abulhasan Quadri, C. Noorullah Shariff
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Leukemia, a severe form of blood cancer, disrupts white blood cells, weakening the immune system. Early detection and diagnosis are critical. This study utilizes artificial intelligence, specifically K-means and Gaussian Mixture Model (GMM) clustering algorithms, to classify and predict four types of leukemia—Chronic Myelogenous Leukemia (CML), Acute Lymphocytic Leukemia (ALL), Non-Hodgkin Lymphoma (NHL), and Hodgkin Lymphoma (HL) along with benign cases. Using blood sample reports, we compare the performance of these algorithms based on accuracy, precision, and recall. Accuracy measures the correctness of predictions, precision evaluates the avoidance of false positives, and recall assesses the identification of all leukemia instances. In the course of this study, we have developed a conceptual framework that outlines the end-to-end process, from data acquisition to final classification. This framework integrates clustering techniques to optimize leukemia diagnosis, providing a systematic approach for analysing blood sample data. Our findings highlight the strengths and weaknesses of K-means and GMM, guiding the selection of the most effective algorithm for reliable leukemia diagnosis through AI and machine learning techniques.

Fields of Study & Subjects

Digital Imaging for Blood Diseases Artificial Intelligence in Healthcare Hematological disorders and diagnostics

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
1 January 2026
Language
EN