Negative binomial mixed models for analyzing longitudinal CD4 count data

Ashenafi A Yirga,Sileshi F Melesse,Henry G Mwambi,Dawit G Ayele

doi:10.1038/s41598-020-73883-7

Ashenafi A Yirga, Sileshi F Melesse + Show 2 more

Open Access

https://doi.org/10.1038/s41598-020-73883-7

Copy DOI

Abstract

It is of great interest for a biomedical analyst or an investigator to correctly model the CD4 cell count or disease biomarkers of a patient in the presence of covariates or factors determining the disease progression over time. The Poisson mixed-effects models (PMM) can be an appropriate choice for repeated count data. However, this model is not realistic because of the restriction that the mean and variance are equal. Therefore, the PMM is replaced by the negative binomial mixed-effects model (NBMM). The later model effectively manages the over-dispersion of the longitudinal data. We evaluate and compare the proposed models and their application to the number of CD4 cells of HIV-Infected patients recruited in the CAPRISA 002 Acute Infection Study. The results display that the NBMM has appropriate properties and outperforms the PMM in terms of handling over-dispersion of the data. Multiple imputation techniques are also used to handle missing values in the dataset to get valid inferences for parameter estimates. In addition, the results imply that the effect of baseline BMI, HAART initiation, baseline viral load, and the number of sexual partners were significantly associated with the patient’s CD4 count in both fitted models. Comparison, discussion, and conclusion of the results of the fitted models complete the study.

Highlights

It is of great interest for a biomedical analyst or an investigator to correctly model the CD4 cell count or disease biomarkers of a patient in the presence of covariates or factors determining the disease progression over time
Abbreviations AI Acute Infection acquired immunodeficiency syndrome (AIDS) Acquired immune deficiency syndrome ART Antiretroviral therapy ARV Antiretroviral CAPRISA Centre of the AIDS Programme of Research in South Africa CD4 Cluster of difference 4 cell (T-lymphocyte cell) generalized linear models (GLM) Generalized linear model GLMM Generalized linear mixed model HAART Highly active antiretroviral therapy human immunodeficiency virus (HIV) Human immunodeficiency virus Multiple Imputation (MI) Multiple imputations negative binomial mixed-effects model (NBMM) Negative binomial mixed-effects model; Poisson mixed-effects models (PMM) Poisson mixed-effects model SE Standard error STD Sexually transmitted disease VL Viral load refers to the number of HIV copies in a milliliter of blood
After it is identified by scientists as the human immunodeficiency virus (HIV) and the cause of acquired immunodeficiency syndrome (AIDS) in 1983, HIV has spread persistently, triggering one of the most severe pandemics ever documented in human history

Summary

Introduction

It is of great interest for a biomedical analyst or an investigator to correctly model the CD4 cell count or disease biomarkers of a patient in the presence of covariates or factors determining the disease progression over time. Abbreviations AI Acute Infection AIDS Acquired immune deficiency syndrome ART Antiretroviral therapy ARV Antiretroviral (drug) CAPRISA Centre of the AIDS Programme of Research in South Africa CD4 Cluster of difference 4 cell (T-lymphocyte cell) GLM Generalized linear model GLMM Generalized linear mixed model HAART Highly active antiretroviral therapy HIV Human immunodeficiency virus MI Multiple imputations NBMM Negative binomial mixed-effects model; PMM Poisson mixed-effects model SE Standard error STD Sexually transmitted disease VL Viral load refers to the number of HIV copies in a milliliter of blood (copies/ml).

Objectives

Methods

Results

Conclusion