An Interpretable Predictive Model for Cervical Cancer Risk Prediction using Hybrid Feature Selection and Ensemble Learning
International Journal of Applied Information Systems · 04.05.2026 · 13 (2) · 67-78
DOI: 10.5120/ijais09d1560bfb24 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Applied Information Systems, online erschienen am 04.05.2026. Verfasst von A.S.M. Sabiqul Hassan und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Cervical cancer has been known as a continuous health threat among women for a long time.There are some screening techniques available to identify this disease, but those are not compatible now due to their high-cost and time-consuming issues.In this study, a ML based interpretable model has been proposed to analyze the risk factors of cervical cancer for trustworthy decision making.Several ML algorithms: KNN, LR, DT, RF, NB, SVM, XGBoost, and Ensemble Learning (Soft Voting) were applied on a publicly available cervical cancer dataset collected from the UCI dataset repository.The result analysis demonstrated that tree or plane based models: DT, RF, and SVM generated best accuracy but ensemble model maintained a balanced result in all evaluation metrics (accuracy: 0.959, precision: 0.643, recall: 0.818, f1-score: 0.720, and roc-auc: 0.882).Additionally, a web version of this model was deployed with explainability based on the top features.This type of decision making tool can be used in the healthcare sector in future with further improvements.
Zitieren
APA
Hassan, A. S., Azad, M. M. U., Paul, G., Alam, M. S., & Amin, M. R. (2026). An Interpretable Predictive Model for Cervical Cancer Risk Prediction using Hybrid Feature Selection and Ensemble Learning. International Journal of Applied Information Systems, 13(2), 67-78. https://doi.org/10.5120/ijais09d1560bfb24
Vancouver
Hassan AS, Azad MMU, Paul G, Alam MS, Amin MR. An Interpretable Predictive Model for Cervical Cancer Risk Prediction using Hybrid Feature Selection and Ensemble Learning. International Journal of Applied Information Systems. 2026;13(2):67-78. doi:10.5120/ijais09d1560bfb24
BibTeX
@article{Hassan2026,
author = {Hassan, A.S.M. Sabiqul and Azad, Md. Mohsin Uddin and Paul, Goutam and Alam, Muhammed Samsuddoha and Amin, Md. Ruhul},
title = {An Interpretable Predictive Model for Cervical Cancer Risk Prediction using Hybrid Feature Selection and Ensemble Learning},
journal = {International Journal of Applied Information Systems},
year = {2026},
volume = {13},
number = {2},
pages = {67--78},
doi = {10.5120/ijais09d1560bfb24}
}
EUVIMED