Effective Stacking Algorithms for Predicting Breast Cancer in Women

DOI

10.2991/978-94-6239-644-9_7How to use a DOI?

Keywords

Breast cancer prediction; stacking algorithms; ensemble learning; Support Vector Classifier; machine learning in healthcare

Abstract

Breast cancer remains the leading cause of cancer incidence among women worldwide, accounting for 2.3 million new cases in 2022 and nearly 666,000 deaths. Early identification of high-risk individuals is critical for guiding prevention, screening, and genetic counselling. Traditional risk prediction models, including those based on BRCA1/2 mutations and clinical features, often suffer from limited accuracy and generalizability. To address this gap, this study evaluates the effectiveness of stacking ensemble algorithms, which combine multiple machine learning models to optimize prediction performance. A systematic comparative analysis was performed using clinical datasets, where base learners such as k-Nearest Neighbour (KNN), Random Forest (RF), Support Vector Classifier (SVC), and Naïve Bayes (NB) were integrated into stacking frameworks with meta-models. Results indicate that stacking consistently outperformed individual models across all performance metrics, with the greatest improvements observed in recall -- a critical metric for medical decision-making, as it reduces the risk of missing malignant cases. The SVC-based stacks emerged as the most effective, achieving accuracy of 97.37%, recall exceeding 95%, and F1-scores of 96.47%. These findings underscore the clinical relevance of stacking in breast cancer prediction, providing a robust and generalizable tool for early detection. Beyond technical performance, this framework highlights the potential for integrating physician judgment and clinical variables to enhance predictive reliability.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Lavanya Prasad
AU  - Shweta Loonkar
AU  - Karishma Desai
PY  - 2026
DA  - 2026/04/19
TI  - Effective Stacking Algorithms for Predicting Breast Cancer in Women
BT  - Proceedings of the Global Innovation and Technology Summit “AAROHAN 3.0”_Engineering track (GITS-EAS 2025)
PB  - Atlantis Press
SP  - 83
EP  - 93
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-644-9_7
DO  - 10.2991/978-94-6239-644-9_7
ID  - Prasad2026
ER  -