Adaptive Explanation-Aware Stacking for Cervical Cancer Risk Prediction

DOI

10.2991/978-94-6239-664-7_18How to use a DOI?

Keywords

Cervical cancer; machine learning; ensemble methods; stacking classifier; explanation-aware modeling

Abstract

Cervical cancer is a leading cause of morbidity and mortality among women globally, particularly in developing countries with limited screening infrastructure. Conventional single classifier ML techniques struggle with learning complex feature interactions and extreme class imbalance in medical datasets, resulting in poor recall performance that is unacceptable for cancer detection. We propose Hyper Adaptive Explanation-Aware Stacking (HAES) as a cervical cancer risk prediction model that aggregates GBDT models, considering both confidence of out-of-sample predictions and alignment of feature importance over each base learner to generate superior meta-features. Using a dataset of 858 patients with 34 risk factors from Hospital Universitario de Caracas, our approach addresses the 803:55 class imbalance through rigorous preprocessing (IQR outlier detection) and RandomOverSampler balancing. Extensive comparison with 14 machine learning algorithms demonstrates superior ensemble performance, achieving 99.38% accuracy, perfect recall of 100%, 98.80% precision, 99.40% F1-score, and 99.86% ROC AUC. Perfect recall is clinically vital in cancer screening, as missed positive cases can lead to serious harm. The primary innovation is the explanation-aware meta-feature generation for interpretable ensemble predictions with no compromise on state-of-the-art performance for realistic clinical applicability.

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  - Amit Kumar Ghosh
AU  - Md Maruf Hasan
AU  - Md Najmus Sakib
AU  - Ahmmed Md Nayeem
AU  - Md Asaduzzaman
AU  - Md. Abdulla Hill Kafi
PY  - 2026
DA  - 2026/06/08
TI  - Adaptive Explanation-Aware Stacking for Cervical Cancer Risk Prediction
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 235
EP  - 249
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_18
DO  - 10.2991/978-94-6239-664-7_18
ID  - Ghosh2026
ER  -