Vitamin D status is associated with mortality, morbidity, and growth failure among a prospective cohort of HIV-infected and HIV-exposed Tanzanian infants

Abstract

Background: Vitamin D is a potent immunomodulator, but its impact on morbidity and mortality among infants remains unclear.

Objective: The objective of the study was to prospectively assess the association of vitamin D status with mortality, morbidity, and growth during the first 2 y of life.

Methods: A prospective cohort of 253 HIV-infected and 948 HIV-exposed Tanzanian infants enrolled in a randomized trial of multivitamins (not including vitamin D) was studied. Serum 25-hydroxyvitamin D [25(OH)D] concentrations were measured at 5-7 wk of age and infants were followed at monthly clinic visits until 24 mo. Physicians performed a clinical exam every 3 mo or when an illness was noted.

Results: Serum 25(OH)D concentrations were (means ± SDs) 18.6 ± 10.3 ng/mL and 18.1 ± 9.2 ng/mL for HIV-infected and HIV-exposed infants, respectively. Unexpectedly, serum 25(OH)D concentrations ≥30 ng/mL were significantly associated with higher mortality as compared to the 20-29.9 ng/mL reference for HIV-infected (HR: 2.47; 95% CI: 1.13, 5.44; P = 0.02) and HIV-exposed (HR: 4.00; 95% CI: 1.67, 9.58; P < 0.01) infants after multivariate adjustment. We found no statistically significant association between 25(OH)D concentrations <10 ng/mL and mortality for HIV-infected (HR: 1.43; 95% CI: 0.74, 2.78; P = 0.29) and HIV-exposed (HR: 1.56; 95% CI: 0.60, 4.03; P = 0.36) infants. Among HIV-exposed infants, 25(OH)D concentrations ≥30 ng/mL were significantly associated with clinical [incidence ratio rate (IRR): 1.34; 95% CI: 1.06,1.70; P = 0.02] and confirmed (IRR: 1.71; 95% CI: 1.71; 1.15, 2.54; P < 0.01) malaria diagnoses, whereas concentrations of <10 ng/mL were associated with oral candidiasis (IRR: 1.47; 95% CI: 1.00-2.15; P = 0.046) and wasting (HR: 1.71; 95% CI: 1.20, 2.43; P < 0.01).

Conclusion: The observational design of this study does not allow for causal interpretation; however, the results indicate a strong need for additional studies of vitamin D among HIV-infected and -exposed children, particularly in malaria-endemic settings. The parent trial was registered at clinicaltrials.gov as NCT00197730.

Keywords: HIV; child nutrition sciences; cohort studies; infant; malaria; micronutrients; vitamin D.

FIGURE 1

Adjusted nonlinear relation between 25(OH)D concentrations and mortality, with 25 ng/mL as the reference for HIV-infected children (n = 253). The solid line shows the estimated HR for 25(OH)D concentrations relative to the reference concentration of 25 ng/mL, with the horizontal dotted line designating an HR of 1.0. The 95% CIs for the HR are represented by the dashed lines. The P value for the nonlinear relation is <0.01. 25(OH)D, 25-hydroxyvitamin D.

FIGURE 2

Mean LAZ (A), WLZ (B), and WAZ (C) by age in weeks among HIV-exposed uninfected infants (n = 948) stratified by 25(OH)D concentration group. LAZ, length-for-age z score; WAZ, weight-for-age z score; WLZ, weight-for-length z score; 25(OH)D, 25-hydroxyvitamin D.