Prediction of precancerous cervical cancer lesions among women living with HIV on antiretroviral therapy in Uganda: a comparison of supervised machine learning algorithms.
Cervical cancer
Supervised machine learning
Women living with HIV
Journal
BMC women's health
ISSN: 1472-6874
Titre abrégé: BMC Womens Health
Pays: England
ID NLM: 101088690
Informations de publication
Date de publication:
08 Jul 2024
08 Jul 2024
Historique:
received:
25
10
2023
accepted:
25
06
2024
medline:
9
7
2024
pubmed:
9
7
2024
entrez:
8
7
2024
Statut:
epublish
Résumé
Cervical cancer (CC) is among the most prevalent cancer types among women with the highest prevalence in low- and middle-income countries (LMICs). It is a curable disease if detected early. Machine learning (ML) techniques can aid in early detection and prediction thus reducing screening and treatment costs. This study focused on women living with HIV (WLHIV) in Uganda. Its aim was to identify the best predictors of CC and the supervised ML model that best predicts CC among WLHIV. Secondary data that included 3025 women from three health facilities in central Uganda was used. A multivariate binary logistic regression and recursive feature elimination with random forest (RFERF) were used to identify the best predictors. Five models; logistic regression (LR), random forest (RF), K-Nearest neighbor (KNN), support vector machine (SVM), and multi-layer perceptron (MLP) were applied to identify the out-performer. The confusion matrix and the area under the receiver operating characteristic curve (AUC/ROC) were used to evaluate the models. The results revealed that duration on antiretroviral therapy (ART), WHO clinical stage, TPT status, Viral load status, and family planning were commonly selected by the two techniques and thus highly significant in CC prediction. The RF from the RFERF-selected features outperformed other models with the highest scores of 90% accuracy and 0.901 AUC. Early identification of CC and knowledge of the risk factors could help control the disease. The RF outperformed other models applied regardless of the selection technique used. Future research can be expanded to include ART-naïve women in predicting CC.
Sections du résumé
BACKGROUND
BACKGROUND
Cervical cancer (CC) is among the most prevalent cancer types among women with the highest prevalence in low- and middle-income countries (LMICs). It is a curable disease if detected early. Machine learning (ML) techniques can aid in early detection and prediction thus reducing screening and treatment costs. This study focused on women living with HIV (WLHIV) in Uganda. Its aim was to identify the best predictors of CC and the supervised ML model that best predicts CC among WLHIV.
METHODS
METHODS
Secondary data that included 3025 women from three health facilities in central Uganda was used. A multivariate binary logistic regression and recursive feature elimination with random forest (RFERF) were used to identify the best predictors. Five models; logistic regression (LR), random forest (RF), K-Nearest neighbor (KNN), support vector machine (SVM), and multi-layer perceptron (MLP) were applied to identify the out-performer. The confusion matrix and the area under the receiver operating characteristic curve (AUC/ROC) were used to evaluate the models.
RESULTS
RESULTS
The results revealed that duration on antiretroviral therapy (ART), WHO clinical stage, TPT status, Viral load status, and family planning were commonly selected by the two techniques and thus highly significant in CC prediction. The RF from the RFERF-selected features outperformed other models with the highest scores of 90% accuracy and 0.901 AUC.
CONCLUSION
CONCLUSIONS
Early identification of CC and knowledge of the risk factors could help control the disease. The RF outperformed other models applied regardless of the selection technique used. Future research can be expanded to include ART-naïve women in predicting CC.
Identifiants
pubmed: 38978015
doi: 10.1186/s12905-024-03232-7
pii: 10.1186/s12905-024-03232-7
doi:
Types de publication
Journal Article
Comparative Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
393Informations de copyright
© 2024. The Author(s).
Références
WHO. Cervical cancer: Key facts, WHO website. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/cervical-cancer .
Sung H. Global Cancer Statistics 2020. GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA. Cancer J. Clin. 2021;71(3):209–249. https://doi.org/10.3322/caac.21660 .
Sarah Maria N, Olwit C, Kaggwa MM, Nabirye RC, Ngabirano TD. Cervical cancer screening among HIV-positive women in urban Uganda: a cross sectional study. BMC Womens Health. 2022;22(1):1–10. https://doi.org/10.1186/s12905-022-01743-9 .
Mwantake MR, Kajoka HD, Kimondo FC, Amour C, Mboya IB. Factors associated with cervical cancer screening among women living with HIV in the Kilimanjaro region, northern Tanzania: a cross-sectional study. Prev Med Rep. 2022;30:101985. https://doi.org/10.1016/j.pmedr.2022.101985 .
doi: 10.1016/j.pmedr.2022.101985
pubmed: 36176589
pmcid: 9512833
CDC. Basic Information About Cervical Cancer. [Online]. Available: https://www.cdc.gov/cancer/cervical/basic_info/index.htm .
Ononogbu U, et al. Cervical cancer risk factors among HIV-infected Nigerian women. BMC Public Health. 2013;13(1). https://doi.org/10.1186/1471-2458-13-582 .
Anastos K, et al. Risk factors for cervical precancer and cancer in HIV-infected, HPV-positive Rwandan women. PLoS ONE. 2010;5(10):3–8. https://doi.org/10.1371/journal.pone.0013525 .
doi: 10.1371/journal.pone.0013525
Stelzle D, et al. Estimates of the global burden of cervical cancer associated with HIV. Lancet Glob Heal. 2021;9(2):e161–9. https://doi.org/10.1016/S2214-109X(20)30459-9 .
doi: 10.1016/S2214-109X(20)30459-9
Kelly H, et al. Association of antiretroviral therapy with high-risk human papillomavirus, cervical intraepithelial neoplasia, and invasive cervical cancer in women living with HIV: a systematic review and meta-analysis. Lancet HIV. 2018;5(1):e45–58. https://doi.org/10.1016/S2352-3018(17)30149-2 .
doi: 10.1016/S2352-3018(17)30149-2
pubmed: 29107561
WHO, WHO guideline for screening and treatment of cervical pre-cancer lesions for cervical cancer prevention, second edition: use of mRNA tests for human papillomavirus (HPV). 2018. [Online]. Available: https://www.who.int/publications/i/item/9789240030824 .
Isabirye A, Mbonye MK, Kwagala B. Predictors of cervical cancer screening uptake in two districts of Central Uganda. PLoS One. 2020;15(12):1–11. https://doi.org/10.1371/journal.pone.0243281 .
MOH. Strategic Plan for Cervical Cancer Prevention, no. April 2010, 2010.
Pry JM, et al. Articles cervical cancer screening outcomes in Zambia, 2010–19 : a cohort study. Lancet Glob Heal. 2010;9(6):e832–40. https://doi.org/10.1016/S2214-109X(21)00062-0 .
doi: 10.1016/S2214-109X(21)00062-0
Bhavani C, Govardhan A. Cervical cancer prediction using stacked ensemble algorithm with SMOTE and RFERF. Mater Today Proc. 2021;xxxx. https://doi.org/10.1016/j.matpr.2021.07.269 .
Asadi F, Salehnasab C, Ajori L. Supervised algorithms of machine learning for the prediction of cervical cancer. J Biomed Phys Eng. 2020;10(4):513–22. https://doi.org/10.31661/jbpe.v0i0.1912-1027 .
doi: 10.31661/jbpe.v0i0.1912-1027
Lu J, Song E, Ghoneim A, Alrashoud M. Machine learning for assisting cervical cancer diagnosis: an ensemble approach. Futur Gener Comput Syst. 2020;106:199–205. https://doi.org/10.1016/j.future.2019.12.033 .
doi: 10.1016/j.future.2019.12.033
Mudawi NA, Alazeb A. A model for Predicting Cervical Cancer using machine learning algorithms. Sensors. 2022;22(11). https://doi.org/10.3390/s22114132 .
Kaushik K, et al. A machine learning-based Framework for the prediction of Cervical Cancer Risk in Women. Sustain. 2022;14(19). https://doi.org/10.3390/su141911947 .
Uphia. Uganda population-based HIV impact assessment. 2020;21(1):1–4. [Online]. Available: https://phia.icap.columbia.edu/wp-content/uploads/2022/08/UPHIA-Summary-Sheet-2020.pdf .
Nithya B, Ilango V. Evaluation of machine learning based optimized feature selection approaches and classification methods for cervical cancer prediction. SN Appl Sci. 2019;1:1–16. https://doi.org/10.1007/s42452-019-0645-7 .
doi: 10.1007/s42452-019-0645-7
Gowri K, Saranya M. Cervical Cancer Prediction using Outlier deduction and Over sampling methods. Int. J. Innov. Res. Eng. 2022;3(3):186–190. [Online]. Available: www.theijire.comhttp://creativecommons.org/licenses/by/4.0/ .
Muhammad Fazal YS, Ijaz M, Attique. Outlier detection and over-sampling methods. Sensors. 2020:1–22.
Alsmariy R, Healy G, Abdelhafez H. Predicting cervical cancer using machine learning methods. Int J Adv Comput Sci Appl. 2020;11(7):173–84. https://doi.org/10.14569/IJACSA.2020.0110723 .
doi: 10.14569/IJACSA.2020.0110723
Abdullah F, Bin Ashraf, Momo NS. Comparative analysis on Prediction Models with various Data Preprocessings in the Prognosis of Cervical Cancer, 2019 10th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2019. 2019:1–6. https://doi.org/10.1109/ICCCNT45670.2019.8944850 .
Parikh D, Menon V. Machine learning Applied to Cervical Cancer Data. Int J Math Sci Comput. 2019;5(1):53–64. https://doi.org/10.5815/ijmsc.2019.01.05 .
doi: 10.5815/ijmsc.2019.01.05
Tanimu JJ, Hamada M, Hassan M, Kakudi H, Abiodun JO. A machine learning method for classification of Cervical Cancer. MPDI Electron. 2022;1–23. https://doi.org/10.3390/electronics11030463 .
Pathmanathan I, et al. TB preventive therapy for people living with HIV: key considerations for scale-up in resource-limited settings. Int J Tuberc Lung Dis. 2018;22(6):596–605. https://doi.org/10.5588/ijtld.17.0758 .
doi: 10.5588/ijtld.17.0758
pubmed: 29862942
Beshaw MA, Balcha SA, Lakew AM. Effect of isoniazid prophylaxis therapy on the prevention of tuberculosis incidence and associated factors among hiv infected individuals in northwest Ethiopia: retrospective cohort study. HIV/AIDS - Res Palliat Care. 2021;13:617–29. https://doi.org/10.2147/HIV.S301355 .
doi: 10.2147/HIV.S301355
Memiah P, et al. Prevalence and risk factors associated with precancerous cervical cancer lesions among HIV-infected women in resource-limited settings. AIDS Res Treat. 2012;2012. https://doi.org/10.1155/2012/953743 .
Makuza JD, Nsanzimana S, Muhimpundu MA, Pace LE, Ntaganira J, Riedel DJ. Prevalence and risk factors for cervical cancer and pre-cancerous lesions in Rwanda. Pan Afr Med J. 2015;22:1–8. https://doi.org/10.11604/pamj.2015.22.26.7116 .
doi: 10.11604/pamj.2015.22.26.7116
Delam H, Izanloo S, Bazrafshan M-R, Eidi A. Risk factors for cervical cancer. J Heal Sci Surveill Syst. 2020;35(1):105–9. https://doi.org/10.1016/0021-9681(82)90024-8 .
doi: 10.1016/0021-9681(82)90024-8
Assefa AA, Astawesegn FH, Eshetu B. Cervical cancer screening service utilization and associated factors among HIV positive women attending adult ART clinic in public health facilities, Hawassa town, Ethiopia: a cross-sectional study. BMC Health Serv Res. 2019;19(1):1–11. https://doi.org/10.1186/s12913-019-4718-5 .
doi: 10.1186/s12913-019-4718-5