From Coverage to Costs: Multi-Model Analysis of Factors Shaping Cervical Cancer Prevention

Xinyang Qian

doi:10.54097/7jcd2688

Authors

Xinyang Qian

DOI:

https://doi.org/10.54097/7jcd2688

Keywords:

Cervical cancer; vaccination coverage; projected cost; logistics regression; decision tree.

Abstract

World Health Organization (WHO) is developing a global strategy for cervical cancer prevention to scale the human papillomavirus vaccination coverage to 90%. To measure the weight of predictors affecting cervical cancer prevention effect, this paper analyzes the contribution of factors in both statistical and machine learning methods, including logistics regression, multinominal logit regression, random forest, extremely randomized forest, GBDT, and XGBoost. Data processing and model effectiveness analysis comparison are done, varying vaccination coverage, cost, region, and assumptions. The paper finds that current cost, current mortality prevention, projected cost, projected cost prevention, and current HPV vaccination coverage are leading factors influencing future cervical cancer prevention. In contrast, the current CC prevention rate is the major factor indicating current HPV vaccination coverage. Predictions are consistent across the six models. In conclusion, although high vaccination coverage can reduce CC infection rates, the high cost of vaccination still affects vaccine coverage and thus the effectiveness of cervical cancer prevention.

Downloads

Download data is not yet available.

References

[1] Foziya Ahmed Mohammed, et al. Cervical Cancer Stages, Human Papillomavirus Integration, and Malignant Genetic Mutations: Integrative Analysis of Datasets from Four Different Cohorts. Cancers, 2023, 15: 5595-5595.

[2] Canfell Karen, et al. Mortality Impact of Achieving WHO Cervical Cancer Elimination Targets: A Comparative Modelling Analysis in 78 Low-Income and Lower-Middle-Income Countries. The Lancet, 2020, 395: 591-603,

[3] Lehtinen Matti, et al. Eradication of Human Papillomavirus and Elimination of HPV-Related Diseases – Scientific Basis for Global Public Health Policies. Expert Review of Vaccines, 2019, 18: 153-160.

[4] Lehtinen M, et al. Effectiveness of gender-neutral or girls-only vaccination against human papillomavirus. Int J Cancer, 2018, 142(5): 949-958.

[5] Arroyo Mühr, Laila Sara, et al. Concomitant Human Papillomavirus (HPV) Vaccination and Screening for Elimination of HPV and Cervical Cancer. Nature Communications, 2024, 15: 3679.

[6] Hoare Alexander, et al. Sampling and Sensitivity Analyses Tools (SaSAT) for Computational Modelling. Theoretical Biology and Medical Modelling, 2008, 5.

[7] Bhatla N, Albero G, Bruni L. Human Papillomavirus and Related Cancers. Fact Sheet, 2024.

[8] Gibin, Willian oliveira. Cervical Cancer Vaccines. Dataset from Kaggle.com, 2020. www.kaggle.com/datasets/willianoliveiragibin/cervical-cancer-vaccines.

[9] Hanen Karamti, et al. Improving Prediction of Cervical Cancer Using KNN Imputed SMOTE Features and Multi-Model Ensemble Learning Approach. Cancers, 2023, 15: 4412-4412.

[10] Kalbhor M, Shinde S V, Jude H. Cervical cancer diagnosis based on cytology pap smear image classification using fractional coefficient and machine learning classifiers. Telecommun. Comput. Electron. Control, 2022, 20: 1091-1102.

[11] Youneszade Nina, et al. Deep Learning in Cervical Cancer Diagnosis: Architecture, Opportunities, and Open Research Challenges. IEEE Access, 2023, 6133-6149.