Research Article | | Peer-Reviewed

Modelling Count Data for HIV-Positive Patients on Antiretroviral Treatment in Kenya

Received: 3 October 2023     Accepted: 20 October 2023     Published: 31 October 2023
Views:       Downloads:
Abstract

The Acquired Immunodeficiency Syndrome (AIDS), caused by the Human Immunodeficiency Virus (HIV), is a lentivirus that weakens a person's resistance to infection. The National AIDS Control Programme (NASCOP) guidelines advise patients to begin antiretroviral therapy (ART) when an individual`s CD4+ cell count is below 350 cells/ml or when they begin to exhibit symptoms of HIV infection, as defined by WHO stages I through IV. To achieve HIV viral suppression, antiretroviral drug adherence is essential. Measurements on a variable are gathered for each individual at several points in longitudinal research. Although variables with repeated measurements within an individual are correlated, the between individuals are typically presumed to pose independence, and this is a major characteristic of such longitudinal data. A Retrospective Longitudinal study of HIV-Positive patients enrolled on ART from 2018 to 2021 those above 9 years when they sign up for ART. In total, 1489 individuals were involved during research. Data was examined by descriptive statistics. A generalized linear mixed effect model was fitted which took into account the within and between variations due to its flexibility. The number of patients enrolled on ART increases by Age and Gender over the four years. In 2018, 2019, 2020, and 2021 ART coverage was 22.4%, 24.2%, 26.1%, and 27.3% respectively. The variables age, gender and year were found to be the significant predictors. The GLMM with negative binomial distribution was used to analyze the data due to overdispersion in the data and the fact that there was a random factor. The AIC was used as the model selection approach. A model considered as the baseline was built with all possible interactions and major effects, and the best fitting model was defined as the one with the lowest AIC.

Published in International Journal of Statistical Distributions and Applications (Volume 9, Issue 3)
DOI 10.11648/j.ijsd.20230903.11
Page(s) 68-80
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2023. Published by Science Publishing Group

Keywords

Antiretroviral Treatment (ART), Generalized Linear Models (GLM), Generalized Linear Mixed Models (GLMM)

References
[1] Global report, UNAIDS Report on the global AIDS epidemic 2012, pp. 6.
[2] E. Ziegal, (2000). COMPSTAT: Proceedings in Computational Statistics. Technometrics, vol. 44 no. 1, pp. 96.
[3] F. Ye, C. Yue and Y. Yang (2013). Modeling time-independent overdispersion in longitudinal count data. Computational Statistics and Data Analysis, vol. 58 no. pp. 257-264.
[4] Rebecca V. Culshaw (2006), Mathematical Modeling of AIDS Progression: Limitations, Expectations, and Future Directions. Journal of American Physicians and Surgeons Vol 11 no. 4.
[5] Y. Liang and L. Zeger (1986), Longitudinal data analysis using generalized linear models. Biometrika, vol. 73 no. 1, pp. 13-22.
[6] M. Laird and H. Ware, (1982). Random-effects models for longitudinal data. Biometrics, vol. 38 no. 4, pp. 963-974.
[7] UNAIDS report on the Global Aids Epidemic 2010, pp. 107.
[8] S. McClelland, (2009). Public Health Aspects of HIV/AIDS in Low- and Middle-Income Countries: Epidemiology, Prevention and Care. JAMA, vol. 302 no. 5, pp. 573-577.
[9] F. J. Palella, K. M. Delaney, A. C. Moorman, M. O. Loveless, J. Fuhrer, G. A. Satten, S. D. Holmberg, (1998). Declining Morbidity and Mortality among Patients with Advanced Human Immunodeficiency Virus Infection. New England Journal of Medicine, vol. 338 no. 13, pp. 853–860.
[10] Kenya Hiv Prevention Revolution Road Map, NASCOP 2014, pp. 7-8.
[11] H. Zhang, H. Wong, and L. Wu, (2018). A mechanistic nonlinear model for censored and mis-measured covariates in longitudinal models, with application in AIDS studies. Statistics in Medicine, Vol. 37 no. 1, pp. 167-178.
[12] T. Yu and L. Wu, (2018). Robust modelling of the relationship between CD4 and viral load for complex AIDS data. Journal of Applied Statistics, vol. 45 no. 2, pp. 367-383.
[13] T. Wendler and S. Grottrup, (2016). Data Mining with SPSS Modeler, Theory, Exercises and Solutions.
[14] X. Lu, (2014). Statistical Modeling and Prediction of HIV/AIDS Prognosis: Bayesian Analyses of Nonlinear Dynamic Mixtures. USF Tampa Graduate Theses and Dissertations.
[15] S. E. Holte, T. W. Randolph, J. Ding, J. Tien, R. S. McClelland, J. M. Baeten, and J. Overbaugh, (2012). Efficient use of longitudinal CD4 counts and viral load measures in survival analysis. Stat. Med, vol. 31 no. 2 and no. 19, pp. 2086–2097.
[16] H. Donald and G. Robert D. Longitudinal Data Analysis. Wiley, 2006.
[17] B. M. Bolker, M. E. Brooks, C. J. Clark, S. W. Geange, J. R. Poulsen, M. H. H. Stevens, and J. S. S. White, (2009). Generalized linear mixed models: a practical guide for ecology and evolution. Trends in ecology & evolution, vol. 24 no. 3, pp. 127-135.
[18] G. Fitzmaurice, M. Davidian, G. Verbeke, and G. Molenberghs, (Eds.). (2008). Longitudinal data analysis. CRC press. pp. 19-20.
[19] Kenya Aids Indicator Survey, 2012. Acquir Immune Defic Syndr. Volume 66, Supplement 1, May 1, 2014.
[20] D. Renard, (2002). Topics in modeling multilevel and longitudinal data. PhD thesis.
Cite This Article
  • APA Style

    Anna Nanjala Muricho, Thomas Mageto, Samuel Mwalili. (2023). Modelling Count Data for HIV-Positive Patients on Antiretroviral Treatment in Kenya. International Journal of Statistical Distributions and Applications, 9(3), 68-80. https://doi.org/10.11648/j.ijsd.20230903.11

    Copy | Download

    ACS Style

    Anna Nanjala Muricho; Thomas Mageto; Samuel Mwalili. Modelling Count Data for HIV-Positive Patients on Antiretroviral Treatment in Kenya. Int. J. Stat. Distrib. Appl. 2023, 9(3), 68-80. doi: 10.11648/j.ijsd.20230903.11

    Copy | Download

    AMA Style

    Anna Nanjala Muricho, Thomas Mageto, Samuel Mwalili. Modelling Count Data for HIV-Positive Patients on Antiretroviral Treatment in Kenya. Int J Stat Distrib Appl. 2023;9(3):68-80. doi: 10.11648/j.ijsd.20230903.11

    Copy | Download

  • @article{10.11648/j.ijsd.20230903.11,
      author = {Anna Nanjala Muricho and Thomas Mageto and Samuel Mwalili},
      title = {Modelling Count Data for HIV-Positive Patients on Antiretroviral Treatment in Kenya},
      journal = {International Journal of Statistical Distributions and Applications},
      volume = {9},
      number = {3},
      pages = {68-80},
      doi = {10.11648/j.ijsd.20230903.11},
      url = {https://doi.org/10.11648/j.ijsd.20230903.11},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijsd.20230903.11},
      abstract = {The Acquired Immunodeficiency Syndrome (AIDS), caused by the Human Immunodeficiency Virus (HIV), is a lentivirus that weakens a person's resistance to infection. The National AIDS Control Programme (NASCOP) guidelines advise patients to begin antiretroviral therapy (ART) when an individual`s CD4+ cell count is below 350 cells/ml or when they begin to exhibit symptoms of HIV infection, as defined by WHO stages I through IV. To achieve HIV viral suppression, antiretroviral drug adherence is essential. Measurements on a variable are gathered for each individual at several points in longitudinal research. Although variables with repeated measurements within an individual are correlated, the between individuals are typically presumed to pose independence, and this is a major characteristic of such longitudinal data. A Retrospective Longitudinal study of HIV-Positive patients enrolled on ART from 2018 to 2021 those above 9 years when they sign up for ART. In total, 1489 individuals were involved during research. Data was examined by descriptive statistics. A generalized linear mixed effect model was fitted which took into account the within and between variations due to its flexibility. The number of patients enrolled on ART increases by Age and Gender over the four years. In 2018, 2019, 2020, and 2021 ART coverage was 22.4%, 24.2%, 26.1%, and 27.3% respectively. The variables age, gender and year were found to be the significant predictors. The GLMM with negative binomial distribution was used to analyze the data due to overdispersion in the data and the fact that there was a random factor. The AIC was used as the model selection approach. A model considered as the baseline was built with all possible interactions and major effects, and the best fitting model was defined as the one with the lowest AIC.
    },
     year = {2023}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Modelling Count Data for HIV-Positive Patients on Antiretroviral Treatment in Kenya
    AU  - Anna Nanjala Muricho
    AU  - Thomas Mageto
    AU  - Samuel Mwalili
    Y1  - 2023/10/31
    PY  - 2023
    N1  - https://doi.org/10.11648/j.ijsd.20230903.11
    DO  - 10.11648/j.ijsd.20230903.11
    T2  - International Journal of Statistical Distributions and Applications
    JF  - International Journal of Statistical Distributions and Applications
    JO  - International Journal of Statistical Distributions and Applications
    SP  - 68
    EP  - 80
    PB  - Science Publishing Group
    SN  - 2472-3509
    UR  - https://doi.org/10.11648/j.ijsd.20230903.11
    AB  - The Acquired Immunodeficiency Syndrome (AIDS), caused by the Human Immunodeficiency Virus (HIV), is a lentivirus that weakens a person's resistance to infection. The National AIDS Control Programme (NASCOP) guidelines advise patients to begin antiretroviral therapy (ART) when an individual`s CD4+ cell count is below 350 cells/ml or when they begin to exhibit symptoms of HIV infection, as defined by WHO stages I through IV. To achieve HIV viral suppression, antiretroviral drug adherence is essential. Measurements on a variable are gathered for each individual at several points in longitudinal research. Although variables with repeated measurements within an individual are correlated, the between individuals are typically presumed to pose independence, and this is a major characteristic of such longitudinal data. A Retrospective Longitudinal study of HIV-Positive patients enrolled on ART from 2018 to 2021 those above 9 years when they sign up for ART. In total, 1489 individuals were involved during research. Data was examined by descriptive statistics. A generalized linear mixed effect model was fitted which took into account the within and between variations due to its flexibility. The number of patients enrolled on ART increases by Age and Gender over the four years. In 2018, 2019, 2020, and 2021 ART coverage was 22.4%, 24.2%, 26.1%, and 27.3% respectively. The variables age, gender and year were found to be the significant predictors. The GLMM with negative binomial distribution was used to analyze the data due to overdispersion in the data and the fact that there was a random factor. The AIC was used as the model selection approach. A model considered as the baseline was built with all possible interactions and major effects, and the best fitting model was defined as the one with the lowest AIC.
    
    VL  - 9
    IS  - 3
    ER  - 

    Copy | Download

Author Information
  • Department of Statistics and Actuarial Science, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya

  • Department of Statistics and Actuarial Science, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya

  • Department of Statistics and Actuarial Science, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya

  • Sections