A Comprehensive Framework for Advanced Machine Learning and Deep Learning Models in Cervical Cancer Prediction

Cervical cancer is a major public health chal-lenge globally and a leading cause of cancer-related deaths in women. Early detection significantly improves survival rates. In this study, we present a robust machine learning frame-work to predict cervical cancer risk using a range of machine learning (ML) and deep learning (DL) models, including XGBoost (XGB), Gradient Boosting (GB), Random Forest (RF), Multilayer Perceptron (MLP), Decision Tree (DT), Support Vector Machine (SVM), and a Stacking ensemble model. Data preprocessing, feature selection, cross-validation, and hyperparameter tuning were performed to optimize model performance. The experimental results reveal that the Stacking ensemble model achieved the highest accuracy of 99.07%, outperforming individual models. The proposed approach demonstrates the effectiveness of ensemble learning for early cervical cancer detection and offers a scalable solution to support personalized treatment planning and clinical decision-making.