ENHANCED STACKING ENSEMBLE MODEL FOR CERVICAL CANCER PREDICTION
DOI:
https://doi.org/10.15282/Keywords:
Ensemble, Machine Learning, Prediction, Cervical cancer, ModelAbstract
Early prediction of cervical cancer is crucial for positive treatment outcomes and reducing the high mortality rate among women. This research aims at enhancing ensemble Machine Learning model to improve existing methods and enable early diagnosis of the disease. Traditional methods have limitations in terms of sensitivity and specificity; hence, there is a need for more accurate and reliable predictive models. Existing machine learning models often face challenges such as overfitting, underfitting, and variability in prediction performance; this research, which integrates different Machine Learning techniques to improve prediction, offers a potential solution to these challenges. In this study, an ensemble approach was used to develop an enhanced ensemble Machine Learning model using Support Vector Machine (SVM), Extreme Gradient Boosting (XGB), and Random Forest (RF). The three algorithms were chosen for their robustness against overfitting and for improving prediction accuracy. Furthermore, the study overcame issues of imbalanced datasets by applying Synthetic Minority Oversampling Technique (SMOTE) and Random Undersampling (RUS) before training and testing the Machine Learning algorithms to obtain better results and improve the accuracy of the model. This study achieved a higher accuracy of 95%, 97% precision, recall of 96%, and 97% F1-score. The result indicates that the enhanced ensemble approach correctly identifies a large majority of cervical cancer cases, showing its reliability in prediction and assisting medical experts in early diagnosis. However, this study is limited to secondary datasets, which involve the collection of only secondary source datasets from the UCI repository for training and validating Machine Learning models. Future work should focus on advancing to Deep Learning to overcome the limitation of utilising feature extraction in Machine Learning algorithms and adding a lot more medical images to the dataset.
Downloads
References
[1] M. Arora, S. Dhawan, and K. Singh, “Data-driven prognosis of cervical cancer using class balancing and machine learning techniques,” EAI Endorsed Transactions on Energy Web, vol. 7, no. 30, 2020. https://doi.org/10.4108/eai.13-7-2018.164264.
[2] L. J. Muhammad, E. A. Algehyne, S. S. Usman, A. Ahmad, C. Chakraborty, and I. A. Mohammed, “Supervised machine learning models for prediction of COVID-19 infection using epidemiology dataset,” SN Computer Science, vol. 2, no. 1, Art. no. 11, 2021. https://doi.org/10.1007/s42979-020-00394-7.
[3] A. Tak, P. M. Parihar, S. Fatehpuriya, and Y. Singh, “Optimised feature selection and cervical cancer prediction using machine learning classification,” Scripta Medica, vol. 53, no. 3, pp. 205–211, 2022.
[4] K. Kaushik, A. Bhardwaj, S. Bharany, et al., “A machine learning-based framework for the prediction of cervical cancer risk in women,” Sustainability, vol. 14, no. 19, Art. no. 11947, 2022. https://doi.org/10.3390/su141911947.
[5] A. Abubakar, M. Ajuji, and I. U. Yahya, “DeepFMD: Computational analysis for malaria detection in blood-smear images using deep-learning features,” Applied System Innovation, vol. 4, no. 4, Art. no. 82, 2021. https://doi.org/10.3390/asi4040082.
[6] C. H. Bhavani and A. Govardhan, “Ensemble modelling for the prediction of cervical cancer by analysing data balancing techniques,” European Chemical Bulletin, vol. 12, Special Issue 3, pp. 2063–2072, 2023. https://doi.org/10.31838/ecb/2023.12.s3.259.
[7] S. Ahmed, S. Madanian, F. Mirza, and S. Zaim, “Prediction of natural gas consumption in Bahçeşehir using machine learning models,” in Proceedings of the 31st Australasian Conference on Information Systems (ACIS 2020), Wellington, New Zealand, 2020.
[8] R. Weegar and K. Sundstrom, “Using machine learning for predicting cervical cancer from Swedish electronic health records by mining hierarchical representations,” PLOS ONE, vol. 15, no. 8, pp. 1–19, 2020.
[9] S. El Khamlichi, I. B. A. Ouahab, M. Bouharma, F. Elouaai, A. Sedqui, and A. Muarady, “An evaluation of machine learning algorithms and feature selection methods for cervical cancer risk prediction using clinical features,” International Journal of Intelligent Systems and Applications in Engineering, vol. 10, no. 4, pp. 470–479, 2022.
[10] A. Desiani, E. S. Kresnawati, M. Arhami, et al., “Majority voting as ensemble classifier for cervical cancer classification,” Science and Technology Indonesia, vol. 8, no. 1, pp. 84–92, 2023. https://doi.org/10.26554/sti.2023.8.1.84-92.
[11] A. Desiani, E. S. Kresnawati, M. Arhami, et al., “Majority voting as ensemble classifier for cervical cancer classification,” Science and Technology Indonesia, vol. 8, no. 1, pp. 84–92, 2023. https://doi.org/10.26554/sti.2023.8.1.84-92.
[12] L. Sun, L. Yang, X. Liu, et al., “Optimisation of cervical cancer screening: A stack integrated machine learning algorithm based on demographic, behavioral and clinical factors,” Frontiers in Oncology, vol. 12, pp. 1–10, 2024.
[13] S. Jahan, M. D. S. Islam, L. Islam, et al., “Automated invasive cervical cancer disease detection at early stage through suitable machine learning model,” SN Applied Sciences, vol. 3, Art. no. 806, 2021. https://doi.org/10.1007/s42452-021-04786-z.
[14] F. J. Shaikh and D. S. Rao, “Prediction of cancer disease using machine learning approach,” Materials Today: Proceedings, vol. 50, no. 1, pp. 40–47, 2022.
[15] K. Chadaga, S. Prabhu, and N. Sampathila, “Predicting cervical cancer biopsy results using demographic and epidemiological parameters: A custom stacked ensemble machine learning approach,” Cogent Engineering, vol. 9, no. 1, Art. no. 2143040, 2022. https://doi.org/10.1080/23311916.2022.2143040.
[16] W. Xiao, C. Liu, and X. Liu, “A hybrid LSTM-based ensemble learning approach for cervical cancer prediction,” Journal of Advanced Transportation, 2021.
[17] O. Attallah, “CerCan-Net: Cervical cancer classification model via multi-layer feature ensembles of lightweight CNNs and transfer learning,” Expert Systems with Applications, 2023.
[18] E. Karim and N. Neehal, “An empirical study of cervical cancer diagnosis using ensemble methods,” in Proceedings of the 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), 2019.
[19] F. Khanam and M. D. R. H. Mondal, “Ensemble machine learning algorithms for the diagnosis of cervical cancer,” in Proceedings of the 2021 International Conference on Science & Contemporary Technologies (ICSCT), 2021.
[20] R. Pramanik, B. Banerjee, and R. Sarkar, “MSENet: Mean and standard deviation based ensemble network for cervical cancer detection,” Engineering Applications of Artificial Intelligence, vol. 123, Art. no. 106336, 2023. https://doi.org/10.1016/j.engappai.2023.106336.
[21] R. Alsmariy, G. Healy, and H. Abdelhafez, “Predicting cervical cancer using machine learning methods,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 7, pp. 173–184, 2020.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Fatima Isa Jibrin*, Lawan Jibrin Muhammad
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
