Developing a Logistic Regression Machine Learning Model that Predicts Viral Load Outcomes for Children Living with HIV in Gutu District, Zimbabwe

Belinda Ndlovu; Fungai Jacqueline  Kiwa; Martin  Muduva; Colletor T. Chipfumbu; Sheltar  Marambi

doi:10.47540/ijias.v5i3.2275

Authors

Belinda Ndlovu National University of Science and Technology
Fungai Jacqueline Kiwa Chinhoyi University of Technology, Zimbabwe
Martin Muduva Midlands State University, Zimbabwe
Colletor T. Chipfumbu Midlands State University, Zimbabwe
Sheltar Marambi Midlands State University, Zimbabwe

DOI:

https://doi.org/10.47540/ijias.v5i3.2275

Keywords:

HIV, Logistic Regression, Machine Learning, Viral Load

Abstract

HIV remains a major public health issue globally, particularly in poor resource settings such as the Gutu district of Zimbabwe. The study aimed to develop a predictive viral load outcome model for HIV children based on the CRISP-DM research process. Secondary clinical data for children aged 0–17 years in Gutu were retrieved from the Demographic Health Information System (DHIS2). The study identified age, adherence status, gender, and geographical location as correlated with viral load outcomes. A supervised machine learning logistic regression model was trained with data balance and proper management of complexities. Grid search-based hyperparameter tuning was performed to improve model performance further. The evaluation metrics were accuracy, sensitivity, F1 Score, and area under the receiver operating characteristic curve (AUC-ROC). The model’s performance resulted in 89% accuracy, with all the metrics showing a strong performance. A confusion matrix was used to visualize the results. The findings add to the knowledge on viral load outcome prediction and HIV care in Zimbabwe. The findings suggest that early diagnosis and targeted interventions can improve viral load outcomes in children in Gutu. For future research, the development of the model will be based on more representative data sets and applied to other settings to determine differences in other regions and understand the dynamics of HIV care in children.

References

Almuhaideb, A., Dou, D., & Alhajj, R. (2021). Applications of machine learning in healthcare.

Alyafei, A., & Carr, R. E. (2024). The Health Belief Model of Behavior Change.

Anuar, H., Shar, S. A., Gafor, H., Mahmood, M. I., & Ghazi, H. F. (2020). Usage of Health Belief Model (HBM) in Health Behavior. Malaysian Journal of Medicine and Health Sciences.

Bhattacharya, A., Mehrotra, P., & Satyanaravana, V. A. (2023). Barriers to antiretroviral therapy adherence among children and adolescents living with HIV in low-resource settings. Journal of Pediatric Infectious Diseases Society, 12(1), 48–55.

Bouchard, A., Bourdear, F., Roger, J., Thaillefer, V. T., Sheehan, N. L., Schnitzer, M., & Wang, G. (2022). Predictive Factors of Detectable Viral Load in HIV-Infected Patients. Aids Research and Human Retrovirus.

Brahmbhatt, H. (2020). Psychological outcomes in HIV-infected youth: The impact of stigma and adherence. Journal of the International AIDS Society.

Chiramba, N. W., Ndlovu, B., Dube, S., Jacqueline, F., & Muduva, M. (2024). Optimizing Antiretroviral Therapy (ART) Adherence Through Predictive Analytics Using Machine Learning Techniques. IEOM, 2021 (July).

Fuyana, C., Ndlovu, B., Dube, S., Maguraushe, K., & Malungana, L. (2025). Optimizing HIV Care Through Machine Learning-Assisted Prediction and Personalized Treatment. In V. Bhateja, P. Patel, & J. Tang (Eds.), Smart Innovation, Systems and Technologies (Vol. 436, pp. 149–161). Springer Nature

Gachago, L., Phiri, S., & Govender, K. (2022). Socioeconomic factors and HIV treatment outcomes in rural children. AIDS Research and Human Retroviruses.

Gafor, H., Carr, R. E., Shar, S. A., & Anuar, H. (2024). The Health Belief Model of Behavior Change.

Goga, A. E., Jackson, D. J., & Lombard, C. (2021). HIV treatment outcomes among children living in resource-limited settings: Challenges and solutions. Pediatrics and Neonatology, 1-10.

Green, E. C., Murphy, E. M., & Gryboski, K. (2020). The Health Belief Model.

Indicator Registry. (n.d.). Retrieved from https://indicatorregistry.unaids.org/: https://indicatorregistry.unaids.org/indicator/people-living-hiv-who-have-suppressed-viral-loads

Kakkar, F., Lee, T., Hawkes, M. T., & Brophy, J. (2020). Challenges to achieving and maintaining viral suppression among children living with HIV.

Kilroy, D. L. (2020). Study of a User-driven Location-based Point-of-Interest Recommendation System.

Kim, S. H., Gerver, S. M., & Fidler, S. (2022). The impact of ART adherence on long-term viral suppression. Current Opinion in HIV and AIDS, 45-52.

Kojima, N., Shrestha, R. K., & Klausner, J. D. (2021). Addressing social determinants of health in HIV prevention and care.

Lao, X., Zhang, H., Yan, L., Zhao, H., Zhao, Q., Lu, H., . . . Liang, X. (2023). Thirteen-year viral suppression and immunologic recovery of LPV/r-based regimens in pediatric HIV treatment: a multicenter cohort study in resource-constrained settings of China. Frontiers in Medicine, 10.

Lopez, M., Antonio, O., & Crossa, A. (2022). Multivariate Statistical Machine Learning Methods for Genomic Prediction. Multivariate Statistical Machine Learning Methods for Genomic Prediction (pp. 1–691). Springer International Publishing.

Machekano, R., Mapangisana, T., Maposhere, C., Mutetwa, R., Manasa, J., Shamhu, T., Munyati, S. (2023). Clinic-based SAMBA-II vs centralized laboratory viral load assays among HIV-1 infected children, adolescents and young adults in rural Zimbabwe: A randomized controlled trial.

Mahamboro, D. B., Fauk, N. K., Ward, P. R., & Merry, M. S. (2022). Stigma and discrimination towards people living with HIV/AIDS: A qualitative study. International Journal of Environmental Research and Public Health, 19(6), 3483.

Makota, R. B., & Musenge, E. (2023). Predicting HIV infection in the decade (2005–2015) pre-COVID-19 in Zimbabwe: A supervised classification-based machine learning approach. PLOS Digital Health, 2(6).

Mauthner, N. S. (2020). Research philosophies and why they matter. In How to Keep Your Doctorate on Track. Edward Elgar Publishing.

Mavhu, W., Willis, N., & Bernays, S. (2020). Enhancing psychosocial support for children living with HIV. Journal of the International AIDS Society.

Mebrahtu, T., Mohammed, F., & Mensa, G. A. (2023). Psychosocial correlates of ART adherence among adolescents living with HIV. 561-571.

Mukumbang, F. C., Ambe, A. N., & Adebiyi, B. O. (2021). Family-centered interventions for managing pediatric HIV.

Nagler, T. (2024). Statistical Learning Theory.

Nash, D. (2022). Machine learning for HIV care and research: Promises and pitfalls.

Ndlovu, B., Maguraushe, K., & Mabikwa, O. (2025). Machine Learning and Explainable AI for Parkinson’s Disease Prediction: A Systematic Review. The Indonesian Journal of Computer Science, 14(2).

Nichols, J. S. (2021). Adherence challenges among HIV-infected children: Barriers and strategies. Pediatric Infectious Disease Journal.

Nusinovichi, S., Tham, Y. C., Yan, M. Y., Ting, T. S., Li, J., Sabanayagam, C., & Wong, T. Y. (2020). Logistic regression was as good as machine learning for predicting major chronic diseases. Journal of Clinical Epidemiology.

Okonji, E. F., Mukumbang, F. C., & Orth, Z. (2021). Socioeconomic disparities in HIV outcomes among African children.

Pantelic, M., Sprague, L., & Stangl, A. (2022). The science of stigma reduction.

Poku, N. K., Whiteside, A., & Sandkjaer, B. (2020). HIV/AIDS, stigma and globalization.

Shamount, F., Zhu, T., & Clifton, D. A. (2020). Machine Learning for Clinical Outcome Prediction.

Slogrove, A. L. (2020). Global challenges in pediatric HIV: Unmet needs and opportunities.

Slogrove, A. L., Mahy, M., & Abrams, E. J. (2021). Children and adolescents living with HIV: The need for more healthcare innovation. The Lancet Child & Adolescent Health, 612-624.

Solutions, S. (2020). What is logistic regression?

Topol, E. J. (2020). High-performance medicine: The convergence of human and artificial intelligence.

W.C Mukura, N., & Ndlovu, B. (2023). Performance Evaluation of Artificial Intelligence in Decision Support System for Heart Disease Risk Prediction. Who, 2018, 83–93.

Wang, R. Y., & String, D. M. (2020). Beyond Accuracy: What Data Quality Means to Data Consumers. Journal of Management Information Systems.

Wirth, R., & Hipp, J. (2000). CRISP-DM: Towards a Standard Process Model for Data Mining. Proceedings of the Fourth International Conference on the Practical Application of Knowledge Discovery and Data Mining, (24959), 29–39.

World Health Organisation. (2021). Consolidated guidelines on HIV prevention, testing, treatment, service delivery and monitoring. Optics InfoBase Conference Papers (p. 249).