Resisting and tolerating P. falciparum in pregnancy under different malaria transmission intensities

Abstract

Background: Resistance and tolerance to Plasmodium falciparum can determine the progression of malaria disease. However, quantitative evidence of tolerance is still limited. We investigated variations in the adverse impact of P. falciparum infections among African pregnant women under different intensities of malaria transmission.

Methods: P. falciparum at delivery was assessed by microscopy, quantitative PCR (qPCR) and placental histology in 946 HIV-uninfected and 768 HIV-infected pregnant women from Benin, Gabon, Kenya and Mozambique. Resistance was defined by the proportion of submicroscopic infections and the levels of anti-parasite antibodies quantified by Luminex, and tolerance by the relationship of pregnancy outcomes with parasite densities at delivery.

Results: P. falciparum prevalence by qPCR in peripheral and/or placental blood of HIV-uninfected Mozambican, Gabonese and Beninese women at delivery was 6% (21/340), 11% (28/257) and 41% (143/349), respectively. The proportion of peripheral submicroscopic infections was higher in Benin (83%) than in Mozambique (60%) and Gabon (55%; P = 0.033). Past or chronic placental P. falciparum infection was associated with an increased risk of preterm birth in Mozambican newborns (OR = 7.05, 95% CI 1.79 to 27.82). Microscopic infections were associated with reductions in haemoglobin levels at delivery among Mozambican women (-1.17 g/dL, 95% CI -2.09 to -0.24) as well as with larger drops in haemoglobin levels from recruitment to delivery in Mozambican (-1.66 g/dL, 95% CI -2.68 to -0.64) and Gabonese (-0.91 g/dL, 95% CI -1.79 to -0.02) women. Doubling qPCR-peripheral parasite densities in Mozambican women were associated with decreases in haemoglobin levels at delivery (-0.16 g/dL, 95% CI -0.29 to -0.02) and increases in the drop of haemoglobin levels (-0.29 g/dL, 95% CI -0.44 to -0.14). Beninese women had higher anti-parasite IgGs than Mozambican women (P < 0.001). No difference was found in the proportion of submicroscopic infections nor in the adverse impact of P. falciparum infections in HIV-infected women from Kenya (P. falciparum prevalence by qPCR: 9%, 32/351) and Mozambique (4%, 15/417).

Conclusions: The lowest levels of resistance and tolerance in pregnant women from areas of low malaria transmission were accompanied by the largest adverse impact of P. falciparum infections. Exposure-dependent mechanisms developed by pregnant women to resist the infection and minimise pathology can reduce malaria-related adverse outcomes. Distinguishing both types of defences is important to understand how reductions in transmission can affect malaria disease.

Trial registration: ClinicalTrials.gov NCT00811421 . Registered 18 December 2008.

Keywords: Immunity; Malaria; Pregnancy; Resistance; Tolerance.

Fig. 1

Prevalence of P. falciparum maternal infection according to study area. Prevalence of P. falciparum at delivery in peripheral and/or placental blood as detected by qPCR (a) and microscopy (b). P value according to the multivariate analysis adjusted for type of IPTp drug, season, age, gravidity, gestational age, anaemia, literacy, RPR result and MUAC at recruitment, as well as CD4 + T cell count in the case of HIV-infected women. T bars represent standard errors. B Benin, G Gabon, M Mozambique, K Kenya

Fig. 2

Impact of microscopic malaria infections at delivery on pregnancy outcomes. Maternal microscopic infections were considered present if P. falciparum parasites were observed in peripheral blood at delivery and/or in the placenta either by microscopy or histology. The dot and T bar represents the mean difference and 95% confidence interval in haemoglobin levels at delivery (a, b), the difference of haemoglobin levels from recruitment to delivery (c, d), or birth weight (e, f) between malaria infected and uninfected women in the multivariate regression analysis adjusted for type of IPTp drug, season, age, gravidity, gestational age, anaemia, literacy, RPR result and MUAC at recruitment, plus CD4 + T cell count at recruitment in the case of HIV-infected women (b, d, f). Modification of the associations by study area (B Benin, G Gabon, K Kenya, M Mozambique) was determined through the inclusion of an interaction term in the regression models, and combination of the coefficients plus the interaction and the standard error was estimated by the delta method

Fig. 3

Proportion of P. falciparum submicroscopic infections, PfHRP2 concentrations and antibody responses against P. falciparum antigens according to study area. Proportion of infections that are submicroscopic in peripheral (a) and placental (b) blood. P value according to the multivariate analysis adjusted for type of IPTp drug, season, age, gravidity, gestational age, anaemia, literacy, RPR result and MUAC at recruitment, as well as CD4 + T cell count in the case of HIV-infected women. T bars represent standard errors. B Benin, G Gabon, M Mozambique, K Kenya. c PfHRP2 concentrations, indicative of overall parasite biomass, among women with a peripheral qPCR-detected infection in Mozambique (M; n = 13) and Benin (B; n = 42). d Levels of IgG antibodies against MSP1 and DBL3X in Beninese (n = 170) and Mozambican (n = 170) women. e Levels of IgG antibodies against MSP1 and DBL3X by parity (primigravidae (PG) versus multigravidae (MG)), with the proportional increase (Δ) of the antibody levels plus 95% confidence interval in multigravidae versus primigravidae women. P values obtained from regression analysis adjusted for type of IPTp drug, season, gravidity, gestational age, anaemia, literacy, RPR result and MUAC at recruitment, as well as CD4 + T cell count in the case of HIV-infected women. MFI mean fluorescence intensity

Fig. 4

Relationship of qPCR-detected parasite densities in peripheral blood with pregnancy outcomes. The dot and T bar represent the effect and 95% confidence interval on haemoglobin levels at delivery (a, b), the difference of haemoglobin levels from recruitment to delivery (c, d), or birth weight (e, f) due to a two-fold increase in the parasitemia levels in its natural scale. Modification of the associations by study area (B Benin, G Gabon, K Kenya, M Mozambique) was determined through the inclusion of an interaction term in the regression models, and combination of the coefficients plus the interaction and the standard error was estimated by the delta method. Analyses were adjusted for type of IPTp drug, season, age, gravidity, gestational age, anaemia, literacy, RPR result and MUAC at recruitment, as well as CD4 + T cell count in the case of HIV-infected women (b, d, f)