Machine Learning–Based Assessment of Clinical and Demographic Predictors of CD4 Status in HIV/AIDS Patients
DOI:
https://doi.org/10.33003/fjs-2025-1001-4511Keywords:
HIV/AIDS, SVM, ANN, NB, logistic regressionAbstract
Human Immunodeficiency Virus (HIV) is the pathogenic organism responsible for acquired immune deficiency syndrome (AIDS) in the human body. The pathogen targets and destroys white blood cells, weakening the body's defenses against infection. HIV is an infectious virus that primarily affects CD4+ T cells. As a result of this infection, the number of these cells steadily decreases, which are essential for protecting the body against foreign antigens, leading to AIDS over time. The main focus of this research is to determine the predictive techniques for evaluating the clinical and demographic factors that affect immune function among individuals living with HIV/AIDS. Clinical and demographic data were collected from the records department of Rasheed Shakoni Teaching Hospital in Dutse, located in the Jigawa Central Senatorial Zone of Nigeria. Data were extracted from HIV/AIDS patients’ case files who received antiretroviral treatment (ART) between January 2019 and January 2024. Four classification algorithms were used: Logistic Regression, Artificial Neural Network, Naïve Bayes, and Support Vector Machine. The models’ predictive performance was tested using four metrics. A total of 274 HIV/AIDS patients were analyzed. Logistic regression had AUC 0.9342, accuracy 0.9348; SVM had AUC 0.9243, accuracy 0.9565; ANN had AUC 0.8980, accuracy 0.0870; Naïve Bayes had AUC 0.6818, accuracy 0.6957. Logistic regression outperformed all. The results enhance prediction reliability and support better health planning, care, and HIV prevention.
References
Abbass, A. K., Ali Yasir. (2008). “Congenital and Acquired Immunodeficiency” Basic Immunology. Data status, 209–223. (2018).
Anubha (2014 ). “Binary Text Classification Using an Ensemble of Naïve Bayes and Support Vector Machines”. GESJ: Computer Science and Telecommunications, 2(52), 37–45. .
Agbelusi O, Oluyemi Olufunke C, Olashinde O. (2015) “Evaluation of Immune Survival Factors in Pediatric HIV-1 Infection”. Annual National Academic Journal. Vol. 91, No. 8. pp 298-312
Chen, M .jia, Yang C,J. (2018) “The Changing HIV-1 Genetic Characteristics and Transmitted Drug Resistance among Recently Infected Population in Yunnan China”. Epidiomol infection. 146(6), 775-781 (doi 10.1017/5095026).
Center for Disease and Control (2024), “General Overview of HIV, Including Transmission Prevention, Testing and Control” https://cdc.gov/hiv/index.
Degninou Yehadji, Geraldine Gray, Carlos Arias Vicente, Petros Isaakidis.(2025) “Development of machine learning algorithms to predict Viral load suppression among HIV patient in Conakry (Guinea)”. DOI: https://doi.org/10.3380/frial.2025.144687.
Erel orel, Rachel Estra, Janne Estill. (2022). “Prediction of HIV status based on socio- behavioural characteristics in East and Southern Africa” https://doi.org/10.1371/journal.pone.0264429.
Jantawan, B., Tsai, C. (2014). “A Classification Model on Graduate Employability Using Bayesian Approaches”. International Journal of Innovative Research in Computer and Communication Engineering. Vol 2 Issue 6 Juni 2014.
Jessica P. Eri J and Jeria J.(2022). “Machine Learning and Clinical Informatics for Improving HIV care Continuum Outcomes”. (doi: https://doi.org/10.1007/sl1904.021.00552-3
JISACA (2024) www. Punch newspaper on World HIV Day “Jigawa to Roll out Drugs at PHC” [Accessed on 17 September 2024].
Jaiteh Musa, Edith Phalane,Yeganew A, Shiferaw. (2025) The Application of Machine Learning Algorithms to Predict HIV Testing in Repeated Adult Population–Based Surveys in South Africa: Protocol for a Multiwave Cross-Sectional Analysis (IRRID): DERR1-10.2196/59916
Jialu Li, Yiwei Hao, Ying Liu, Liang Wu. (2024). “Supervised machine learning algorithms to predict the duration and risks of long term hospitalization in HIV- infected individuals: A retrospective study”. DOI: https://doi.org/10.3389/fpubh.2023.1282324
Mao Q, Yingiao Dong, Shangbin Liu, Danni Xia.(2025). “Predicting disease progression in people living with HIV using machine learning and a nomogram: a 10- year cohort study based in Xinjiang, China” doi: https://doi.org/10.1136/bmjopen-2025-105026.
Miedema, F., et al. (2000). The Dominant Source of CD4+ and CD8+ T-Cell Activation in HIV Infection is Antigenic Stimulation.
Mutai Charles K, Patrick E Mcsharry, Innocent Nganye. (2021) Use of Machine Learning Techniques to Identify HIV Predictors for Screening in Sub-Saharan Africa. ( https://doi.org/10.1186/s12874-021-01346-2)
Muhammad, A. B., Ishaq, O. O., Janet, B. B., Alhassan, M. A., Samaila Manzo, and Shehu, S. (2025).“A Hybrid ExpAR-FIGARCH-ANN Model for Time Series Forecasting”. Journal of Statistical Sciences and Computational Intelligence, 1(4), 283–293. https://doi.org/10.64497/jssci.68
Muhammad, A. B., Olawoyin, I. O., Yahaya, A., Gulumbe, S. U., Muhammad, A. A., & Salisu, I. A. (2024). “Credit Risk Analysis: An Assessment of the Performance of Six Machine Learning Techniques in Credit Scoring Modelling”. FUDMA Journal of Sciences, Vol. 8 No. 6, December 2024 (Special Issue), pp. 163 – 173. DOI: https://doi.org/10.33003/fjs-2024-0806-2893.
N. Cristianini and J. Shawe-Taylor (2019). An Introduction to Support Vector Machines. Cambridge University Press, 2000.
Neidja M Barreto Q (2012) logistics regression model for determining factors associated with HIV infection among blood donors www.rbhh.org (doi 10:5581/1516-8484.20120053)
Nigerian Bulletin, (2014). World HIV/AIDS Day: 10 Facts about HIV/AIDS in Nigeria You Probably Didn’t Know. Available from www.nigeriabulletin.com/threads world HIV/AIDS day 10-fact-about-HIV-AIDS-IN- NIGERIA-you- probably-didn’t-know.24303/. [Accessed 28 July, 2014].
Ngcobo Sanele, Edith Madela Mntla, Jonathan Shock. (2024) Artificial intelligence for HIV care: a global systematic review of current studies and emerging trends https://doi.org/10.1002/jia2.70045
Ojunga, N., Olaruwanju, and Olasihende.(2014) . The Application of Logistic Regression in Modeling of Survival Chances of HIV-Positive Patients under Highly Active Antiretroviral Therapy (HAART): A Case of Nyakach District, Kenya. Journal of Medicine and Clinical Sciences. Vol. 3, No 3. pp. 14-20.
Joshi, Kavita Sanjeev, Pranav Milind Ambardeka, Rushabh Yatish Gujarath.(2022) Logistic Regression‑Based Parametric Analysis Of HIV‑Associated Dementia Using A Screening Tool In A Tertiary Care Hospital In Mumbai DOI: https://doi.org/10.4103/ijstd.ijstd_80_21
Raper, J. L. (2007). Complete Blood Cell Count as a Surrogate CD4 Cell Marker for HIV Monitoring in Resource-Limited Settings.
Sameem, A., et al., (2010). Classification and Regression Tree in Prediction of Survival of AIDS Patients, Malaysian Journal of Computer Science. Vol. 23.No 3. pp 153-165
Singh, and Yashik, (2010) predicting immune risk in treatment of naïve HIV patient using machine learning algorithms (doi: https://doi.org/10.3389/fnut.2024-1443076)
Sendila Ernesy Asari, Rahmi Susanti, Ismail AB, rfansyah Baharuddin. (2025) Prediction Model of Human Immunodeficiency Virus Status at Abdoel Wahab Sjahranie Hospital, Samarinda Indonesia. DOI: https://doi.org/10.14710/jphtcr.v8i1.24302
Seboka Binyam Tariku, Delelegn Emwodew Yehualashet & Getanew Aschalew Tesfa (2023) Artificial Intelligence and Machine Learning Based Prediction of Viral Load and CD4 Status of People Living with HIV (PLWH) on Anti-Retroviral Treatment in Gedeo Zone Public Hospitals. https://doi.org/10.2147/IJGM.S397031.
Song, L., Biang Xi and Zan Yo. (2015). Multiple Introduction and Naturally Occuring Drug Resistance of HCV Among HIV Infected Intravenous drug Users in Yunnan.
T. Joachims. (2018) Making large-scale support vector machine learning practical. In Advances in Kernel Methods: Support Vector Learning. B.
Umar Madaki, S., Bello Muhammad , A., and Ahmad Hamisu , H.. (2025). “Predicting Bronchopulmonary Dysplasia in Infants: A Comparative Evaluation of Probit and Machine Learning Models”. Proceedings of 2025 International Conference on Data Science and Official Statistics (ICDSOS). 2025(1), 660–665. https://doi.org/10.34123/icdsos.v2025i1.617
UNAIDS, 2012. Together We Will End AIDS. Available fromwww.unaids.org. [Accessed 12 June, 2013] UNAIDS, 2013. Global Report on HIV. Available from http://www.unaids.org/en/resources/documents/20 13/ name, 85053, en.asp. [Accessed 2nd August, 2014]
WHO, (2012). Towards Universal access: Scaling up Priority HIV/AIDS interventions in the Health Sector. Progress Report 2010.Available from http://whqlibdoc.who.int [Accessed January 15, 2014]
WHO,(2022). www.who. Int >Data>GHO HIV and Statistics. Data on the Size of the HIV Epidemic
Yashik Singh and Maurice Mars.(2010) Support vector machines to forecast changes in CD4 count of HIV-1 positive patients. ISSN 1992-2248 ©2010 Academic Journals
Zeming Li and Yanning Li (2020) journal of medical informatics and decision making. https://doi.org/10.1186/s12911-020-01157-3.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Manzo Samaila, Ado Osi Abdulhameed, Abdu Mannir, Bello Muhammad Abba, Usman Dauda
This work is licensed under a Creative Commons Attribution 4.0 International License.
