Development of A Predictive Ai Model for Early Identification of Low Preventive Practice Uptake Using Health Literacy and Cervical Cancer Knowledge Scores

• Author(s): Adelalure Bukola Oyeronke; Bukola Cecilia Bello; Esther Olubukola Abiodun-Ojo
• Paper ID: 1718570
• Page: 166-173
• Published Date: 03-06-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 12 June-2026

Abstract

Cervical cancer remains a leading cause of cancer-related mortality among women in low- and middle-income countries, largely because of low uptake of preventive practices such as Pap smear screening and HPV vaccination. Health literacy and cervical cancer knowledge are modifiable determinants of preventive behavior, yet their combined predictive utility for identifying high-risk individuals has not been systematically evaluated with artificial intelligence. This study conducted a systematic review of 54 studies (2015–2025) examining health literacy, cervical cancer knowledge, and uptake of preventive practices, with a focus on AI-based predictive models. Supervised machine learning algorithms, including logistic regression, random forests, support vector machines, gradient boosting, and neural networks, were evaluated for predicting low uptake of preventive practices, using health literacy and knowledge scores as input features. Findings show that ensemble methods (random forest, XGBoost) achieve the highest predictive performance (AUCs of 0.85–0.92), outperforming traditional logistic regression (AUCs of 0.72–0.78). Key predictors include: functional health literacy (odds ratio [OR] 2.8–4.2), knowledge of HPV as a causal agent (OR 3.5), knowledge of the screening interval (OR 2.9), and perceived susceptibility (OR 2.3). A parsimonious 8-item screening tool derived from the model achieves 84% sensitivity and 79% specificity for identifying women at risk of never having been screened. The study concludes that AI-driven predictive models using brief health literacy and knowledge assessments can effectively stratify women by risk of low uptake of preventive practices, enabling targeted educational interventions and resource allocation. Deployment in primary care and community settings is feasible via mobile health applications.

Keywords

Cervical Cancer, Health Literacy, Preventive Practice, Pap Smear, HPV Vaccine, Predictive AI, Machine Learning, Random Forest, Risk Stratification.

Citations

IRE Journals:
Adelalure Bukola Oyeronke, Bukola Cecilia Bello, Esther Olubukola Abiodun-Ojo "Development of A Predictive Ai Model for Early Identification of Low Preventive Practice Uptake Using Health Literacy and Cervical Cancer Knowledge Scores" Iconic Research And Engineering Journals Volume 9 Issue 12 2026 Page 166-173 https://doi.org/10.64388/IREV9I12-1718570

IEEE:
Adelalure Bukola Oyeronke, Bukola Cecilia Bello, Esther Olubukola Abiodun-Ojo "Development of A Predictive Ai Model for Early Identification of Low Preventive Practice Uptake Using Health Literacy and Cervical Cancer Knowledge Scores" Iconic Research And Engineering Journals, 9(12) https://doi.org/10.64388/IREV9I12-1718570