A Comprehensive Review of Machine Learning Techniques for Breast Cancer Classification
Best Journal of Innovation in Science, Research and Development · 2026 · 156-161
DOI: 10.67249/738945 ↗At a glance
Journal article in Best Journal of Innovation in Science, Research and Development, 2026. Written by Anuradha Muttamwar and 2 co-authors.
Abstract (original language)
Breast cancer is one of the most serious health challenges facing women globally. Catching it early can dramatically improve a patient's chances of survival, but the process of identifying whether a tumor is cancerous still depends heavily on manual examination by specialist doctors — a process that is slow, inconsistent, and not always accessible. This paper explores how machine learning can help solve this problem. We tested eight classification algorithms on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset — 569 real patient biopsy samples with 30 cell measurements each. Our preprocessing included outlier removal, RobustScaler normalization, SMOTE class balancing, and RFECV feature selection. We then used SHAP (Shapley Additive Explanations) to make the best model's decisions understandable to clinicians.
Cite
APA
Muttamwar, A., Uikey, I., & Raut, A. (2026). A Comprehensive Review of Machine Learning Techniques for Breast Cancer Classification. Best Journal of Innovation in Science, Research and Development, 156-161. https://doi.org/10.67249/738945
Vancouver
Muttamwar A, Uikey I, Raut A. A Comprehensive Review of Machine Learning Techniques for Breast Cancer Classification. Best Journal of Innovation in Science, Research and Development. 2026:156-161. doi:10.67249/738945
BibTeX
@article{Muttamwar2026,
author = {Muttamwar, Anuradha and Uikey, Ishika and Raut, Aishwarya},
title = {A Comprehensive Review of Machine Learning Techniques for Breast Cancer Classification},
journal = {Best Journal of Innovation in Science, Research and Development},
year = {2026},
pages = {156--161},
doi = {10.67249/738945}
}
EUVIMED