Publicado
2025-08-02

Generalized Dynamic Coefficient Models for Longitudinal Data Analysis in Health: An Application in HIV/AIDS and COVID-19

Modelos de coeficientes dinámicos generalizados para el análisis de datos longitudinales en salud: una aplicación en HIV/AIDS y COVID-19

DOI: https://doi.org/10.15332/23393076.11216
Juan Sosa PhD
Elkin Javier Casadiego Rincón

Resumen (es)

El análisis de datos longitudinales es esencial cuando la variable de respuesta se mide repetidamente en la misma unidad de observación a lo largo del tiempo. Tradicionalmente, se han empleado métodos paramétricos para estimar los coeficientes que definen la relación entre el predictor lineal y la variable de respuesta. Sin embargo, estos métodos fallan cuando no se cumplen las suposiciones sobre la variable de respuesta y los componentes aleatorios del modelo, o cuando el valor esperado de la variable de respuesta (o su transformación mediante una función de enlace) no puede expresarse como una función conocida de los efectos fijos y aleatorios. En tales casos, los modelos paramétricos pueden generar conclusiones que se desvían significativamente de las tendencias promedio del conjunto de datos. Las técnicas de regresión no paramétrica, que reemplazan los parámetros fijos por funciones locales suavizadas dependientes del tiempo, ofrecen una alternativa poderosa para el análisis de datos longitudinales. Estos métodos, conocidos como coeficientes o parámetros dinámicos, nos permiten establecer una relación funcional más flexible entre la variable de respuesta y las covariables. En este estudio, proponemos técnicas de estimación e inferencia para modelos generalizados no paramétricos de coeficientes dinámicos, particularmente para variables de respuesta de conteo. Ilustramos nuestro enfoque mediante su aplicación al análisis del efecto de la carga viral sobre el conteo de células CD4 en pacientes con VIH/SIDA en tratamiento antirretroviral, así como en la predicción de casos de COVID-19.

Palabras clave (es): Longitudinal data analysis, radial basis kernel functions, regression splines, time-varying coefficient models, viral load, CD4 T lymphocyte counts, HIV/AIDS, COVID-19

Resumen (en)

Longitudinal data analysis is essential when the response variable is measured repeatedly on the same observational unit over time. Traditionally, parametric methods have been employed to estimate coefficients that define the relationship between the linear predictor and the response variable. However, these methods fail when the assumptions regarding the response variable and the model's random components are violated, or when the expected value of the response variable (or its transformation via a link function) cannot be expressed as a known function of the fixed and random effects. In such cases, parametric models may yield conclusions that deviate significantly from the dataset's average trends. Non-parametric regression techniques, which replace fixed parameters with time-dependent smoothed local functions, offer a powerful alternative for longitudinal data analysis. These methods, known as dynamic coefficients or parameters, allow us to establish a more flexible functional relationship between the response variable and the covariates. In this study, we propose estimation and inference techniques for generalized non-parametric dynamic coefficient models, particularly for count response variables. We illustrate our approach through its application in analyzing the effect of viral load on CD4 cell count in HIV/AIDS patients undergoing antiretroviral therapy, as well as in predicting COVID-19 cases.

Referencias

Barbosa, I., de Lima, K., & de Almeida Medeiros, A. (2020). COVID-19 in Brazil: Analysis of the pandemic short-term scenario in relation to other countries. International Journal of Development Research, 10(6), 36840–36845.

Batista, M. (2020). Estimation of the final size of the COVID-19 epidemic. medRxiv. https://doi.org/10.1101/2020.02.16.20023606

Cai, Z., Fan, J., & Li, R. (2000). Efficient estimation and inferences for varying-coefficient models. Journal of the American Statistical Association, 95(451), 888–902. https://doi.org/10.1080/01621459.2000.10474248

Cameron, A. C., & Trivedi, P. K. (2013). Regression analysis of count data (2nd ed., Vol. 53). Cambridge University Press.

Clara-Rahola, J. (2020). An empirical model for the spread and reduction of the COVID-19 pandemic. Studies of Applied Economics, 38(2).

de Pereda Sebastián, D., Ramos, A. M., & Ivorr, B. (2010). Modelización matemática de la difusión de una epidemia de peste porcina entre granjas [Tesis de doctorado, Universidad Complutense de Madrid].

Díaz-Narváez, V., San-Martín-Roldán, D., Calzadilla-Núñez, A., San-Martín-Roldán, P., Parody-Muñoz, A., & Robledo-Veloso, G. (2020). Which curve provides the best explanation of the growth in confirmed COVID-19 cases in Chile? Revista Latino-Americana de Enfermagem, 28.

Egger, M., May, M., Chêne, G., Phillips, A. N., Ledergerber, B., Dabis, F., ... & others. (2002). Prognosis of HIV-1-infected patients starting highly active antiretroviral therapy: A collaborative analysis of prospective studies. The Lancet, 360(9327), 119–129.

Ekum, M., & Ogunsanya, A. (2020). Application of hierarchical polynomial regression models to predict transmission of COVID-19 at global level. International Journal of Clinical Biostatistics and Biometrics, 6, 027.

Faraway, J. J. (2016). Extending the linear model with R: Generalized linear, mixed effects and nonparametric regression models (2nd ed.). CRC Press.

Fischl, M. A., Giuliano, M., Vella, S., Ribaudo, H. J., Collier, A. C., Erice, A., ... & Morse, G. D. (2003). A randomized trial of 2 different 4-drug antiretroviral regimens versus a 3-drug regimen, in advanced human immunodeficiency virus disease. The Journal of Infectious Diseases, 188(5), 625–634. https://doi.org/10.1086/377535

Ford, N., Stinson, K., Gale, H., Mills, E. J., Stevens, W., González, M. P., Markby, J., & Hill, A. (2015). CD4 changes among virologically suppressed patients on antiretroviral therapy: A systematic review and meta-analysis. Journal of the International AIDS Society, 18(1), 20061.

Gonzalo-Gil, E., Ikediobi, U., & Sutton, R. E. (2017). Mechanisms of virologic control and clinical characteristics of HIV+ elite/viremic controllers. The Yale Journal of Biology and Medicine, 90(2), 245–259.

Hoover, D. R., Rice, J. A., Wu, C. O., & Yang, L.-P. (1998). Nonparametric smoothing estimates of time-varying coefficient models with longitudinal data. Biometrika, 85(4), 809–822. https://doi.org/10.1093/biomet/85.4.809

Huang, Y., & Lu, T. (2016). Bayesian inference on partially linear mixed-effects joint models for longitudinal data with multiple features. Computational Statistics, 32. https://doi.org/10.1007/s00180-016-0682-9

Huang, Y., Chen, J., & Yan, C. (2012). Mixed-effects joint models with skew-normal distribution for HIV dynamic response with missing and mismeasured time-varying covariate. The International Journal of Biostatistics, 8(1). https://doi.org/10.1515/1557-4679.1364

Hughes, M. D., Johnson, V. A., Hirsch, M. S., Bremer, J. W., Elbeik, T., Erice, A., ... & others. (1997). Monitoring plasma HIV-1 RNA levels in addition to CD4+ lymphocyte count improves assessment of antiretroviral therapeutic response. Annals of Internal Medicine, 126(12), 929–938.

Kasilingam, D., Sathiya Prabhakaran, S. P., Rajendran, D. K., Rajagopal, V., Santhosh Kumar, T., & Soundararaj, A. (2020). Exploring the growth of COVID-19 cases using exponential modelling across 42 countries and predicting signs of early containment using machine learning. Transboundary and Emerging Diseases.

Korenromp, E. L., Williams, B. G., Schmid, G. P., & Dye, C. (2009). Clinical prognostic value of RNA viral load and CD4 cell counts during untreated HIV-1 infection: A quantitative review. PloS One, 4(6), e5950.

Li, Q., Guan, X., Wu, P., Wang, X., Zhou, L., Tong, Y., ... & others. (2020). Early transmission dynamics in Wuhan, China, of novel coronavirus–infected pneumonia. New England Journal of Medicine, 382(13), 1199–1207.

Liang, H., Wu, H., & Carroll, R. J. (2003). The relationship between virologic and immunologic responses in AIDS clinical research using mixed-effects varying-coefficient models with measurement error. Biostatistics, 4(2), 297–312.

Ma, J. (2020). Estimating epidemic exponential growth rate and basic reproduction number. Infectious Disease Modelling, 5, 129–141.

Manrique Abril, F., González-Chordá, V. M., Gutiérrez Lesmes, O. A., Téllez Piñérez, C. F., & Herrera-Amaya, G. M. (2020). Modelo SIR de la pandemia de COVID-19 en Colombia.

Marschner, I. C., Collier, A. C., Coombs, R. W., D'Aquila, R. T., DeGruttola, V., Fischl, M. A., ... & others. (1998). Use of changes in plasma levels of human immunodeficiency virus type 1 RNA to assess the clinical benefit of antiretroviral therapy. Journal of Infectious Diseases, 177(1), 40–47.

Mercker, M., Betzin, U., & Wilken, D. (2020). What influences COVID-19 infection rates: A statistical approach to identify promising factors applied to infection data from Germany.

Ministerio de Salud y Protección Social. (2014). Guía de práctica clínica basada en la evidencia científica para la atención de la infección por VIH/SIDA en adolescentes (con 13 años de edad o más) y adultos. Ministerio de Salud y Protección Social.

Millán-Oñate, J., Rodríguez-Morales, A. J., Camacho-Moreno, G., Mendoza-Ramírez, H., Rodríguez-Sabogal, I. A., & Álvarez-Moreno, C. (2020). A new emerging zoonotic virus of concern: the 2019 novel coronavirus (SARS-CoV-2). Infectio, 24(3), 187–192.

Ramsay, J., Hooker, G., & Graves, S. (2009). Functional data analysis with R and MATLAB. Springer.

Sosa, J., & Buitrago, L. (2022). Time-varying coefficient model estimation through radial basis functions. Journal of Applied Statistics, 49(10), 2510–2534.

Şentürk, D., & Müller, H.-G. (2008). Generalized varying coefficient models for longitudinal data. Biometrika, 95(3), 653–666. https://doi.org/10.1093/biomet/asn034

Thiebaut, R., Morlat, P., Jacqmin-Gadda, H., Neau, D., Mercié, P., Dabis, F., Chêne, G., & others. (2000). Clinical progression of HIV-1 infection according to the viral response during the first year of antiretroviral treatment. AIDS, 14(8), 971–978.

Trujillo, C. H. S. (2020). Resumen: Consenso colombiano de atención, diagnóstico y manejo de la infección por SARS-CoV-2/COVID-19 en establecimientos de atención de la salud. Infectio, 24(3).

Twisk, J. W. R. (2013). Applied longitudinal data analysis for epidemiology: A practical guide. Cambridge University Press.

Wang, Y. (2007). Varying-coefficient models: New models, inference procedures, and applications. Cambridge University Press.

WHO. (2007). WHO case definitions of HIV for surveillance and revised clinical staging and immunological classification of HIV-related disease in adults and children. World Health Organization.

Wu, C. O., & Tian, X. (2018). Nonparametric models for longitudinal data: With implementation in R. Chapman and Hall/CRC.

Wu, H., & Zhang, J.-T. (2006). Nonparametric regression methods for longitudinal data analysis: Mixed-effects modeling approaches. John Wiley & Sons.

Zeger, S. L., & Diggle, P. J. (1994). Semiparametric models for longitudinal data with application to CD4 cell numbers in HIV seroconverters. Biometrics, 50(3), 689–699. https://doi.org/10.2307/2532807

Dimensions

PlumX

Visitas

143

Descargas

Los datos de descarga aún no están disponibles.

Cómo citar

Sosa, J., & Casadiego Rincón, E. J. (2025). Modelos de coeficientes dinámicos generalizados para el análisis de datos longitudinales en salud: una aplicación en HIV/AIDS y COVID-19. Comunicaciones En Estadística, 18(1). https://doi.org/10.15332/23393076.11216