Estimation of time of HIV seroconversion using a modified CD4 depletion model

Abstract

Introduction: Several methods have been proposed to estimate the time of HIV seroconversion, including those based on CD4 cell depletion models. However, previous models have failed to consider the heterogeneity that exists in CD4 trajectories among different sub-populations. Our objective was to estimate the time from HIV seroconversion relative to the HIV diagnosis date in a population-based cohort of people living with HIV (PLWH) in the province of British Columbia, Canada.

Methods: We used linked administrative and clinical data from the British Columbia Seek and Treat for Optimal Prevention of HIV/AIDS (STOP HIV/AIDS) cohort, which contains longitudinal individual-level data on all PLWH ever diagnosed in the province. Eligible participants were aged ≥18 years and diagnosed with HIV between 1989 and 2013. The outcome was pre-antiretroviral treatment CD4 cell count measurements assessed every six months. Models were stratified by age and stage of HIV infection at diagnosis. Several explanatory variables were considered including longitudinal viral load measurements. Longitudinal CD4, square root transformed, was modeled via a non-linear mixed effects model; time was modeled using an exponential decay function. We assumed a Gaussian distribution (identity link), an AR(1) correlation structure, and a random intercept and slope for the longitudinal viral load measurements. Due to the population variation in CD4 count among uninfected individuals, we assumed 500 to 1500 cells/mm3 as the normal range when estimating the time of HIV seroconversion.

Results: Longitudinal data on 1,253 individuals were analysed: 80% male, 33% White, and the median age at diagnosis was 38 years (25th-75th percentile [Q1-Q3], 31 to 45). CD4 decay differed by stage of infection at diagnosis and age, with those ≥50 years in Stages 1 and 2 experiencing a faster decline in CD4 over time. The median duration of infection from seroconversion until HIV diagnosis was 6.9 (Q1-Q3, 3.9 to 10.1) years.

Conclusions: Considering the heterogeneity that exists in individual CD4 cell trajectories in a population, we presented a methodology that only relies on routinely collected HIV-related data, which can be further extended to estimate other epidemic measures.

Fig 1. Formula to calculate the number of years lost from HIV sero-conversion and HIV diagnosis, and the time of infection, stratified by stage of HIV infection and age at diagnosis, assuming 500 to 1500 cells/mm3 as the normal range among uninfected individuals.

Fig 2. Estimated CD4 cell loss per six months from HIV diagnosis to start of antiretroviral therapy, stratified by stage of HIV infection and age at diagnosis.

Fig 3

Estimates for the year of seroconversion (A-B), age at seroconversion (C-D), and duration of infection from HIV seroconversion until diagnosis (E-F). Note: For each outcome, the counts on the left are for the estimated values based on each CD4 value in the normal range for each individual (i.e., a maximum of 1000 observations per individual). For each outcome, the counts on the right are for the estimated individual-level values summarized as the median and quartiles of the corresponding distribution on the left (i.e., a maximum of 1 observation per individual).

Fig 4. Comparison of the distribution of year of HIV diagnosis and estimated year of HIV seroconversion.