High-Accuracy Machine Learning Models for Cervical Cancer Prediction Using Ensemble Techniques and Class Imbalance Correction
Al Hassani, Oras, Subaramaniam, Kasthuri and Palaniapan, Sellappan (2026) High-Accuracy Machine Learning Models for Cervical Cancer Prediction Using Ensemble Techniques and Class Imbalance Correction. ICAROB2026, 31. ISSN 2188-7829
Abstract
This study develops a machine learning-based predictive model for cervical cancer detection using a dataset of 835 patient records encompassing 36 clinical and demographic features. A systematic methodology was employed, including mean imputation for missing data, StandardScaler for feature normalisation, and the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. Multiple algorithms, Decision Tree, Random Forest, XGBoost, Support Vector Machine, Logistic Regression, and K-Nearest Neighbours, were trained and evaluated using an 80/20 train-test split. The results confirm the feasibility of using ensemble-based models as reliable clinical decision-support tools for early cancer screening.
Actions (login required)
 |
Edit Item |