Schistosoma mansoni infection and socio-behavioural predictors of HIV risk: a cross-sectional study in women from Uganda

Abstract

Background: Schistosoma mansoni infection has been associated with increased risk of HIV transmission in African women. This association might be causal or mediated through shared socio-behavioural factors and associated co-infections. We tested the latter hypothesis in a cross-sectional pilot study in a cohort of women from a S. mansoni endemic region of Uganda. To validate the immunological effects of S. mansoni in this cohort, we additionally assessed known schistosomiasis biomarkers.

Methods: HIV-uninfected non-pregnant adult women using public health services were tested for schistosomiasis using the urine circulating cathodic antigen test, followed by serology and Schistosoma spp.-specific PCR. Blood was obtained for herpes simplex virus (HSV)-2 serology, eosinophil counts and cytokine analysis. Samples collected from the genitourinary tract were used to test for classical sexually transmitted infections (STI), for bacterial vaginosis and to assess recent sexual activity via prostate-specific antigen testing. Questionnaires were used to capture a range of socio-economic and behavioral characteristics.

Results: Among 58 participants, 33 (57%) had schistosomiasis, which was associated with elevated levels of interleukin (IL)-10 (0.32 vs. 0.19 pg/ml; p = 0.038) and a trend toward increased tumour necrosis factor (TNF) (1.73 vs. 1.42 pg/ml; p = 0.081). Eosinophil counts correlated with levels of both cytokines (r = 0.53, p = 0.001 and r = 0.38, p = 0.019, for IL-10 and TNF, respectively); the association of eosinophilia with schistosomiasis was not significant (OR = 2.538, p = 0.282). Further, schistosomiasis was associated with lower age (per-year OR = 0.910, p = 0.047), being unmarried (OR = 0.263, p = 0.030), less frequent hormonal contraceptive (HC) use (OR = 0.121, p = 0.002, dominated by long acting injectable contraceptives) and a trend to longer time since penile-vaginal sex (OR = 0.350, p = 0.064). All women infected by Chlamydia trachomatis (n = 5), were also positive for schistosomiasis (Fisher's exact p = 0.064).

Conclusions: Intestinal schistosomiasis in adult women was associated with systemic immune alterations, suggesting that associations with immunological correlates of HIV susceptibility warrant further investigation. S. mansoni associations with socio-behavioral parameters and C. trachomatis, which may alter both genital immunity and HIV exposure and/or acquisition risk, means that future studies should carefully control for potential confounders. These findings have implications for the design and interpretation of clinical studies on the effects of schistosomiasis on HIV acquisition.

Keywords: HIV risk factors; HIV susceptibility; Injectable hormonal contraceptives; Intestinal schistosomiasis; Schistosoma mansoni; Sexually transmitted infections.

Fig. 1

Distribution of schistosomiasis and the study site location in Uganda. a. Prevalence and distribution of S. mansoni in Uganda; b. Prevalence and distribution of S. haematobium in Uganda; c. Map of Wakiso district and location of the study site (Entebbe). Note that Entebbe is endemic for S. mansoni but not S. haematobium. The maps show the location of schistosomiasis surveys and the reported prevalence of schistosomiasis across Uganda. Scale is given for the maps of Uganda. Map source: The Global Atlas of Helminth Infection [21]

Fig. 2

Systemic immunological differences observed between women with (schisto+) and without schistosomiasis (schisto-). a. Plasma IL-10 levels; b. Plasma TNF levels; c and d. Correlations between eosinophil counts and IL-10 (c) and TNF (d). e. Eosinophil counts, where red dotted line depicts the conventional threshold of eosinophilia (450 cells per μl of whole blood). Multiplex ELISA assays were conducted by a technologist blinded to schistosomiasis status on plasma samples available for 39 women (15 positive and 24 negative for schistosomiasis). Cytokine levels and eosinophil counts were compared by Mann-Whitney test (p = 0.05); plots depict medians and interquartile ranges. Correlations were assessed on LOG-transformed values by Spearman test (p = 0.05)