Multi-Source Data Fusion For Early Cervical Cancer Prediction: A Synergistic Ensemble Intelligence Framework
DOI:
https://doi.org/10.29284/345yxv58Keywords:
Machine Learning, Cervical Cancer, SMOTE Tomek, SHAP, Cross Validation.Abstract
In developed countries, due to the adoption of structured approaches in healthcare sectors by involving prediction, detection, and prevention, cervical cancer is now becoming a highly uncommon disease. The medical services sector receives significant advantages through the implementation of machine learning techniques for the prognosis of various diseases. Diseases such as heart disease, thyroid, chronic renal disease, and various kinds of cancer can now be easily detected in their earliest stages and prevented through early medication. I observed that most of the existing research is constrained by class disparities, limited generalizability, and inadequate interpretation. With the goal to determine the best features to aid in early cervical cancer prediction, this research study utilized an ensemble machine learning approach, integrating the datasets. By combining minority class oversampling with noise reduction, the 1SMOTE-Tomek technique enhances class separability and addresses class imbalance. The framework predicts cervical cancer with an accuracy of 97.14% using the 2LightGBM model for prediction. The SMOTE-Tomek mechanism was incorporated into the proposed framework to solve the class imbalance. Through integrating noise reduction with minority class oversampling, I was able to successfully handle class separation. 3SHAP-based explainability is used to measure feature contributions and facilitate well-informed clinical decision-making in order to guarantee transparency and clinical interpretability. In accordance with experimental results, the proposed method performs superior in terms of prediction performance, resilience, and interpretability than traditional single-model approaches. These results suggest that explainable intelligence, balanced data processing, and synergistic learning works as an effective decision-support approach to early cervical cancer detection.
References
1. Kondo, T. S., Ngondya, D., & Rusheke, H. (2025). Application of artificial intelligence in cervical cancer diagnosis using risk factors: A systematic review. Telematics and Informatics Reports, 20, 100250.
2. Uddin, K. M. M., Al Mamun, A., Chakrabarti, A., Mostafiz, R., & Dey, S. K. (2024). An ensemble machine learning-based approach to predict cervical cancer using hybrid feature selection. Neuroscience Informatics, 4(3), 100169.
3. Rawat, P., Bajaj, M., Mehta, S., Sharma, V., & Vats, S. (2023, March). A study on cervical cancer prediction using various machine learning approaches. In 2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA) (pp. 1101-1107). IEEE.
4. Srivastav, S., Guleria, K., & Sharma, S. (2023, March). Predictive Machine Learning Approaches for Cervical Cancer Detection: An Analytical Comparison. In 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom) (pp. 951-956). IEEE.
5. Devi, S., & Gaikwad, S. R. (2023). Prediction and detection of cervical malignancy using machine learning models. Asian Pacific journal of cancer prevention: APJCP, 24(4), 1419.
6. Su, J., Lu, H., Zhang, R., Cui, N., Chen, C., Si, Q., & Song, B. (2025). Cervical cancer prediction using machine learning models based on routine blood analysis. Scientific Reports, 15(1), 22655.
7. Lu, J., Song, E., Ghoneim, A., & Alrashoud, M. (2020). Machine learning for assisting cervical cancer diagnosis: An ensemble approach. Future Generation Computer Systems, 106, 199-205.
8. Uddin, K. M. M., Al Mamun, A., Chakrabarti, A., Mostafiz, R., & Dey, S. K. (2024). An ensemble machine learning-based approach to predict cervical cancer using hybrid feature selection. Neuroscience Informatics, 4(3), 100169.
9. Ijaz, M. F., Attique, M., & Son, Y. (2020). Data-driven cervical cancer prediction model with outlier detection and over-sampling methods. Sensors, 20(10), 2809.
10. Mahadik, A., Sharma, P., & Narawade, V. (2023, October). Breast cancer prediction with gradient boost and xgboost. In International Conference on Computer & Communication Technologies (pp. 19-37). Singapore: Springer Nature Singapore.
11. Mahadik, V. N. A., & Sharma, P. (2023). Comparison based on examination of machine learning techniques for minimising the amount of features utilised in breast cancer forecast. European Chemical Bulletin, 12(Special Issue 4), 20623–20627.
12. Hanzala, A., Akter, T., & Rahman, M. S. (2025). A hybrid approach for cervical cancer detection: Combining D-CNN, transfer learning, and ensemble models. Array, 27, 100434. doi.org
13. Schiffman, M., Castle, P. E., Jeronimo, J., Rodriguez, A. C., & Wacholder, S. (2007). Human papillomavirus and cervical cancer. The lancet, 370(9590), 890-907.
14. Chen, M., Shi, X., Zhang, Y., Wu, D., & Guizani, M. (2017). Deep feature learning for medical image analysis with convolutional autoencoder neural network. IEEE transactions on big data, 7(4), 750-758.
15. Siegel, R. L., Kratzer, T. B., Wagle, N. S., Sung, H., & Jemal, A. (2026). Cancer statistics, 2026. Ca, 76(1), e70043.
16. Luo, W. (2021). Predicting cervical cancer outcomes: statistics, images, and machine learning. Frontiers in Artificial Intelligence, 4, 627369.
17. https://my.clevelandclinic.org/health/body/23279-cervix
18. https://www.cancer.gov/publications/dictionaries/cancerterms/def/pap-smear
19. https://gco.iarc.who.int/today/en/fact-sheets-cancers
20. Ponce‐Bobadilla, A. V., Schmitt, V., Maier, C. S., Mensing, S., & Stodtmann, S. (2024). Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development. Clinical and translational science, 17(11), e70056.
21. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357.
22. Batista, G. E., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter, 6(1), 20-29.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
