Maternal ART throughout gestation prevents caudate volume reductions in neonates who are HIV exposed but uninfected

Abstract

Introduction: Successful programmes for prevention of vertical HIV transmission have reduced the risk of infant HIV infection in South Africa from 8% in 2008 to below 1% in 2018/2019, resulting in an increasing population of children exposed to HIV perinatally but who are uninfected (HEU). However, the long-term effects of HIV and antiretroviral treatment (ART) exposure on the developing brain are not well understood. Whereas children who are HEU perform better than their HIV-infected counterparts, they demonstrate greater neurodevelopmental delay than children who are HIV unexposed and uninfected (HUU), especially in resource-poor settings. Here we investigate subcortical volumetric differences related to HIV and ART exposure in neonates.

Methods: We included 120 infants (59 girls; 79 HEU) born to healthy women with and without HIV infection in Cape Town, South Africa, where HIV sero-prevalence approaches 30%. Of the 79 HEU infants, 40 were exposed to ART throughout gestation (i.e., mothers initiated ART pre conception; HEU-pre), and 39 were exposed to ART for part of gestation (i.e., mothers initiated ART post conception; HEU-post). Post-conception mothers had a mean (± SD) gestational age (GA) of 15.4 (± 5.7) weeks at ART initiation. Mothers with HIV received standard care fixed drug combination ART (Tenofovir/Efavirenz/Emtricitabine). Infants were imaged unsedated on a 3T Skyra (Siemens, Erlangen, Germany) at mean GA equivalent of 41.5 (± 1.0) weeks. Selected regions (caudate, putamen, pallidum, thalamus, cerebellar hemispheres and vermis, and corpus callosum) were manually traced on T1-weighted images using Freeview.

Results: HEU neonates had smaller left putamen volumes than HUU [β (SE) = -90.3 (45.3), p = 0.05] and caudate volume reductions that depended on ART exposure duration in utero. While the HEU-pre group demonstrated no caudate volume reductions compared to HUU, the HEU-post group had smaller caudate volumes bilaterally [β (SE) = -145.5 (45.1), p = 0.002, and -135.7 (49.7), p = 0.008 for left and right caudate, respectively].

Discussion: These findings from the first postnatal month suggest that maternal ART throughout gestation is protective to the caudate nuclei. In contrast, left putamens were smaller across all HEU newborns, despite maternal ART.

Keywords: HIV exposure; antiretroviral therapy; brain structure; magnetic resonance imaging; neonate; neurodevelopment.

FIGURE 1

Flow diagram showing maternal and infant participant and exclusion numbers at each stage of the study.

FIGURE 2

Representative T1-weighted brain MR images from one neonate without HIV exposure or infection (HUU), showing the manually segmented structures of the basal ganglia [caudate (sky blue), putamen (magenta), pallidum (dark blue)], thalamus (green), cerebellar hemispheres (yellow), and cerebellar vermis (purple). Images are in coronal view (slices 80-96 and 112-124).

FIGURE 3

Comparison of regional volumes by group. The HEU group comprised infants who were HIV-exposed but uninfected born to mothers who had either initiated ART pre-conception (HEU-pre) or during gestation (post-conception; HEU-post); HUU are infants who were not HIV-exposed or infected. Hourglasses show median and interquartile ranges; whiskers are upper and lower extremes. Values above and below the whiskers are outliers, defined as data points more than 1.5 times the interquartile range above (or below) the upper (or lower) quartile. p values from independent one-tail student t-tests.

FIGURE 4

Plots showing associations of regional volumes with maternal clinical and treatment variables among infants who were HIV-exposed but uninfected. All associations shown remained significant after control for potential confounding variables.