Cervical cancer perceived behavioral risk factors using logistic regression technique

Abstract

Cervical cancer represents a considerable global health challenge, mainly because of ineffective screening programs in low-income countries. The current study aimed to forecast cervical cancer incidence by analyzing behavioral risk factors through logistic regression, employing feature engineering techniques such as principal component analysis (PCA). PCA successfully condensed the dataset into ten principal components, capturing 89% of the variance, while stratified K-fold cross-validation ensured a balanced representation of classes. With the application of L1 regularization, the logistic regression model achieved an accuracy of 97.2%, an area under the curve (AUC) of 98.1%, an F1 score of 97.2%, a specificity of 96.1%, and a log loss of 0.17. The performance of the models was comparatively evaluated, and the results revealed that the logistic regression model achieved the highest accuracy of 97.2% compared with decision trees at 93.33%, random forest at 93.33%, XGBoost at 93.33%, naive Bayes at 91.67%, and non-regularized logistic regression at 87.55%. This research underscores the importance of early prediction of cervical cancer based on behavioral risk factors and suggests a robust, easily implementable workflow to improve classification accuracy. Future research should concentrate on refining these predictive tools to overcome social and behavioral barriers to prevention, particularly within underserved populations.

Keywords

principal component analysis / cervical cancer / behavioral risk factors / logistic regression / feature engineering / regularization

Funding

This research received no external funding.

Acknowledgments

None.

Additional information

The online version contains supplementary materials available at http://www.jbr-pub.org.cn/article/doi/10.7555/JBR.39.20250047?pageType=en.

References

[1] Zhang S, Xu H, Zhang L, et al. Cervical cancer: Epidemiology, risk factors and screening[J]. Chin J Cancer Res, 2020, 32(6): 720-728. doi: 10.21147/j.issn.1000-9604.2020.06.05

[2] Kashyap N, Krishnan N, Kaur S, et al. Risk factors of cervical cancer: A case-control study[J]. Asia Pac J Oncol Nurs, 2019, 6(3): 308-314. doi: 10.4103/apjon.apjon_73_18

[3] Paul SB, Tiwary BK, Choudhury AP. Studies on the epidemiology of cervical cancer in southern Assam[J]. Assam Univ J Sci Technol, 2011, 7(1): 36-42. doi: 10.1186/s12905-023-02504-y

[4] Suehiro TT, Damke GMZF, Damke E, et al. Cervical and oral human papillomavirus infection in women living with human immunodeficiency virus (HIV) and matched HIV-negative controls in Brazil[J]. Infect Agent Cancer, 2020, 15: 31. doi: 10.1186/s13027-020-00301-y

[5] Ghasemi M, Savabi-Esfahani M, Noroozi M, et al. Prediction of cervical cancer screening: Application of the information-motivation-behavioral skills model[J]. BMC Cancer, 2024, 24(1): 351. doi: 10.1186/s12885-024-12098-9

[6] Huang J, Deng Y, Boakye D, et al. Global distribution, risk factors, and recent trends for cervical cancer: A worldwide country-level analysis[J]. Gynecol Oncol, 2022, 164(1): 85-92. doi: 10.1016/j.ygyno.2021.11.005

[7] Kumar R, Dubey N, Kumar A, et al. Leveraging machine learning for early detection of cervical cancer: Analyzing demographic, clinical, and lifestyle risk factors[J]. Rom J Biophys, 2025, 35(1): 33-40. doi: 10.59277/RJB.2025.1.03

[8] Sobar, Machmud R, Wijaya A. Behavior determinant based cervical cancer early detection with machine learning algorithm[J]. Adv Sci Lett, 2016, 22(10): 3120-3123. doi: 10.1166/asl.2016.7980

[9] Asadi F, Salehnasab C, Ajori L. Supervised algorithms of machine learning for the prediction of cervical cancer[J]. J Biomed Phys Eng, 2020, 10(4): 513-522. doi: 10.31661/jbpe.v0i0.1912-1027

[10] Deng X, Wang Y, Li J. Identifying key risk factors for cervical cancer using ensemble learning methods[J]. IEEE Access, 2022, 10: 1-12. doi: 10.1109/ACCESS.2021.3137641

[11] Nithya B, Ilango V. Evaluation of machine learning based optimized feature selection approaches and classification methods for cervical cancer prediction[J]. SN Applied Sciences, 2019, 1: 641. doi: 10.1007/s42452-019-0645-7

[12] Tseng CJ, Lu CJ, Chang CC. Integration of data mining classification techniques and ensemble learning to identify risk factors and diagnose ovarian cancer recurrence[J]. Artif Intell Med, 2017, 78: 47-54. doi: 10.1016/j.artmed.2017.06.003

[13] Mohi Uddin KM, Sikder IA, Hahan MN. A comparative study on machine learning classifiers for cervical cancer prediction: A predictive analytic approach[J/OL]. EAI Endorsed Transactions on Internet of Things, 2024, 11. https://publications.eai.eu/index.php/IoT/article/view/6223.

[14] Pimple S, Mishra G. Cancer cervix: Epidemiology and disease burden[J]. Cytojournal, 2022, 19: 21. doi: 10.25259/CMAS_03_02_2021

[15] Wu W, Zhou H. Data-driven diagnosis of cervical cancer with support vector machine-based approaches[J]. IEEE Access, 2017, 5: 25189-25195. doi: 10.1109/ACCESS.2017.2763984

[16] Ashok B, Aruna P. Comparison of feature selection methods for diagnosis of cervical cancer using SVM classifier[J]. Int J Eng Res Appl, 2016, 6(1): 94-99.

[17] Osuwa AA, Öztoprak H. Importance of continuous improvement of machine learning algorithms from a health care management and management information systems perspective[C]// Proceedings of 2021 International Conference on Engineering and Emerging Technologies. Istanbul: IEEE, 2021: 1-5.

[18] Kaur P, Singh G, Kaur P. Intellectual detection and validation of automated mammogram breast cancer images by multi-class SVM using deep learning classification[J]. Inf Med Unlocked, 2019, 16: 100151. doi: 10.1016/j.imu.2019.01.001

[19] Úbeda-Colomer J, Martin Ginis KA, Monforte J, et al. Predicting physical activity in university students with disabilities: The role of social ecological barriers in the theory of planned behaviour[J]. Disabil Health J, 2019, 12(4): 574-580. doi: 10.1016/j.dhjo.2019.06.008

[20] Webb TL, Sheeran P. Does changing behavioral intentions engender behavior change? A meta-analysis of the experimental evidence[J]. Psychol Bull, 2006, 132(2): 249-268. doi: 10.1037/0033-2909.132.2.249

[21] Corney KB, Pasco JA, Stuart AL, et al. Social determinants of health and cognitive function: A cross-sectional study among men without dementia[J]. Brain Behav, 2023, 13(11): e3235. doi: 10.1002/brb3.3235

[22] Fitch JL, Ravlin EC. Willpower and perceived behavioral control: influences on the intention-behavior relationship and postbehavior attributions[J]. Soc Behav Pers: Int J, 2005, 33(2): 105-124. doi: 10.2224/sbp.2005.33.2.105

[23] Dillard JP. An application of the integrative model to women's intention to be vaccinated against HPV: Implications for message design[J]. Health Commun, 2011, 26(5): 479-486. doi: 10.1080/10410236.2011.554170

[24] Larkey L. Las mujeres saludables: Reaching Latinas for breast, cervical and colorectal cancer prevention, and screening[J]. J Community Health, 2006, 31(1): 69-77. doi: 10.1007/s10900-005-8190-2

[25] Luszczynska A, Durawa AB, Scholz U, et al. Empowerment beliefs and intention to uptake cervical cancer screening: Three psychosocial mediating mechanisms[J]. Women Health, 2012, 52(2): 162-181. doi: 10.1080/03630242.2012.656187

[26] Osamor J, Nwachukwu C, Iwendi C, et al. Predicting cervical cancer risk factors using machine learning models[C]// Osamor J, Nwachukwu C, Iwendi C, et al. Proceedings of Data Analytics and Management Singapore: Springer, 2025, 1297.

[27] Deng X, Luo Y, Wang C. Analysis of risk factors for cervical cancer based on machine learning methods[C]// Proceedings of 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems. Nanjing: IEEE, 2018: 631-635.

[28] Prusty S, Patnaik S, Dash SK. SKCV: stratified K-fold cross-validation on ML classifiers for predicting cervical cancer[J]. Front Nanotechnol, 2022, 4: 972421. doi: 10.3389/fnano.2022.972421

[29] Suman SK, Hooda N. Predicting risk of cervical cancer: A case study of machine learning[J]. J Stat Manag Syst, 2019, 22(4): 689-696. doi: 10.1080/09720510.2019.1611227