An Enhanced Analysis of Blood Cancer Prediction Using Deep Learning

Abstract

The field of cancer research and therapy has been revolutionized by the rapid development of artificial intelligence (AI).Focusing on early cancer diagnosis, individualized therapy, and addressing ethical problems, this study seeks to investigate the many ways in which AI-driven tools are expanding the frontiers of oncology. There are a variety of tests and medical experts involved in the diagnostic process, which is time-consuming and expensive. The study has mapped out automated approaches, with deep learning being the automatic classification crown gem due to its higher performance. This study proposes a novel approach utilizing attention mechanism-based machine learning in conjunction with image processing techniques for the precise detection and classification of leukemia cells. The proposed method provides a promising approach for accurate and efficient detection and classification of leukemia cells, which could potentially improve the diagnosis and treatment of leukemia.

Introduction

The text focuses on blood cancer, particularly leukemia, and explores the application of machine learning and image processing techniques for its accurate detection and classification. Blood cancer originates in the bone marrow, where abnormal blood cells proliferate and disrupt the normal production of red blood cells, white blood cells, and platelets. Early and accurate diagnosis is critical, as treatment outcomes depend on factors such as cancer type, patient age, disease progression, and spread.

The study highlights the growing role of machine learning in healthcare, especially in medical imaging and disease prediction. A review of existing literature shows that artificial intelligence (AI), artificial neural networks (ANNs), and other machine learning models have demonstrated strong potential in supporting blood cancer diagnosis, improving accuracy, reducing unnecessary tests, and assisting clinicians rather than replacing them. However, challenges such as data imbalance, high dimensionality, lack of standardized datasets, limited data diversity, and the need for expert-labeled training data remain significant barriers.

The existing system section discusses limitations in current AI-based cancer diagnosis approaches, including insufficient and imbalanced datasets, inconsistent data collection, high-dimensional medical data, and regulatory and practical challenges in healthcare adoption.

To address these issues, the proposed system evaluates and compares machine learning classifiers—Random Forest, K-Nearest Neighbors (KNN), and AdaBoost—using performance metrics beyond accuracy, such as precision, recall, ROC curves, and survival probability, which are more suitable for imbalanced medical datasets. Experimental results show that the proposed approach, particularly using Random Forest with an improved structure, outperforms existing methods in terms of accuracy, precision, scalability, and computational efficiency.

Conclusion

A patient\'s medical history, physical examination, blood tests, imaging tests, and biopsies can all be used in the process of determining whether or not they have blood cancer. This is a difficult and intricate process. Deep learning analysis of data from new approach that has been used to diagnose blood cancer. This technique uses a combination of AI and data collected from network sensors to identify the presence of cancerous cells. AI are composed of interconnected computational nodes that are capable of learning how to recognize patterns from data. It can be used to diagnose even the rarest forms of blood cancer and may be less invasive and more accurate than traditional methods. Despite the approach\'s benefits, there are still some obstacles. One of the main challenges trusts the accuracy of the AI since they are still in the early stages of development. The AI applicability to other medical conditions in blood cancer detection or analyzing whether other cancer types can be detected by AI or using Bayesian methods for cancer detection. In addition, more research can be conducted to improve the detection procedure\'s speed and accuracy so that it can be utilized in real-time clinical applications. Last but not least, more research is needed to take advantage of AI\'s low cost and scalability for cancer detection, particularly in developing nations, so that more people can get life-saving treatments.

References

[1] V.S.Saranya, Parasa Rajya Lakshmi, \"Matrix-Based Deep Learning Approach to AI-Driven Cancer Detection, Personalized Treatment, and Ethical Consideration. \" International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 6, pp. 112–120, 2024, ISSN:2147-6799. [2] N. P. Dharani, G. Sujatha, \"Blood Cancer Detection Using Improved Machine Learning Algorithms.” International Conference on Circuit Power and Computing Technologies, pp.1136-1141, November 06, 2023, DOI: 10.1109. [3] Althaf Ali A, K. Hemalatha, N. Mohana Priya, \"An Enhanced Analysis of Blood Cancer Prediction Using ANN Sensor-Based Model.” Engineering Proceedings, 2023, https://doi.org/10.3390/engproc2023059065. [4] Wiebke Rösler, Michael Roiss, \"Advancements in Machine Learning (ML): Transforming the Future of Blood Cancer Detection and Outcome Prediction.” Healthbook TIMES Oncology Hematology, vol. 20, issue 2, 2024, DOI: 10.36000/HBT.OH.2024.20.146. [5] Tejal Nemade. \"Leukemia Detection employing Machine Learning: A Review and Taxonomy.” International Journal of Artificial Intelligence, Internet of Things and Cloud Computing, vol. 1, pp. 58-63, August 2022, ISSN: 2583-8911. [6] Eiryo Kawakami, Nozomu Yanaihara, \"Application of Artificial Intelligence for Preoperative Diagnostic and Prognostic Prediction in EpithelialOvarian Cancer Based on Blood Biomarkers.” American Association of Cancer Research, Volume 25 Issue 10, May 15, 2019, DOI:10.1158/1078-0432.CCR-18-3378. [7] Vaibhav Rupapara, Furqan Rustam, \"Blood cancer prediction using leukemia microarray gene data and hybrid logisticvector trees model.” Scientific reports, 2022, https://doi.org/10.1038/s41598-022-04835-6. [8] Shabbir Syed-Abdul, Rianda-Putra Firdani, “Artificial Intelligence based Models for Screening of Hematologic Malignancies using Cell Population Data,” Scientific reports, 2020, https://doi.org/10.1038/s41598-020-61247-0. [9] Abdullah Y. Muaad, Noha F. Mahmoud, “A Deep Learning Computer-Aided Diagnosis Framework for Human Peripheral Blood Cell Identification\" Diagnostics, 2022, https://doi.org/10.3390/diagnostics12112815. [10] Dow-Mu Koh, Nickolas Papanikolaou, \"Artificial intelligence and machine learning in cancer imaging\" Communication medicine, 2022, https://doi.org/10.1038/s43856-022-00199-0.

Copyright

Copyright © 2026 Dr. P. Tamilselvan , Mrs. A. Jayalakshmi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.