A seven-year surveillance of epidemiology of malaria reveals travel and gender are the key drivers of dispersion of drug resistant genotypes in Kenya

Abstract

Malaria drug resistance is a global public health concern. Though parasite mutations have been associated with resistance, other factors could influence the resistance. A robust surveillance system is required to monitor and help contain the resistance. This study established the role of travel and gender in dispersion of chloroquine resistant genotypes in malaria epidemic zones in Kenya. A total of 1,776 individuals presenting with uncomplicated malaria at hospitals selected from four malaria transmission zones in Kenya between 2008 and 2014 were enrolled in a prospective surveillance study assessing the epidemiology of malaria drug resistance patterns. Demographic and clinical information per individual was obtained using a structured questionnaire. Further, 2 mL of blood was collected for malaria diagnosis, parasitemia quantification and molecular analysis. DNA extracted from dried blood spots collected from each of the individuals was genotyped for polymorphisms in Plasmodium falciparum chloroquine transporter gene (Pfcrt 76), Plasmodium falciparum multidrug resistant gene 1 (Pfmdr1 86 and Pfmdr1 184) regions that are putative drug resistance genes using both conventional polymerase chain reaction (PCR) and real-time PCR. The molecular and demographic data was analyzed using Stata version 13 (College Station, TX: StataCorp LP) while mapping of cases at the selected geographic zones was done in QGIS version 2.18. Chloroquine resistant (CQR) genotypes across gender revealed an association with chloroquine resistance by both univariate model (p = 0.027) and by multivariate model (p = 0.025), female as reference group in both models. Prior treatment with antimalarial drugs within the last 6 weeks before enrollment was associated with carriage of CQR genotype by multivariate model (p = 0.034). Further, a significant relationship was observed between travel and CQR carriage both by univariate model (p = 0.001) and multivariate model (p = 0.002). These findings suggest that gender and travel are significantly associated with chloroquine resistance. From a gender perspective, males are more likely to harbor resistant strains than females hence involved in strain dispersion. On the other hand, travel underscores the role of transport network in introducing spread of resistant genotypes, bringing in to focus the need to monitor gene flow and establish strategies to minimize the introduction of resistance strains by controlling malaria among frequent transporters.

Keywords: Chloroquine; Drug resistance; Gender; Malaria; Plasmodium falciparum; Travel.

Figure 1. Map of Kenya showing the different malaria endemicity zones and locations of various surveillance hospitals.

Lake endemic region: Kisumu East and Kisumu West District Hospitals in Kisumu county, Semi-Arid, seasonal: Marigat District hospital in Baringo county and Isiolo District Hospital in Isiolo county. Coast endemic: Malindi District Hospital, Kilifi County. High land Epidemic: Kisii teaching and referral Hospital and Kericho District Hospital (QGIS version 2.18).

Figure 2. Comparison of parasite density by malaria epidemic zones.

Parasite density (natural log transformation). Dots represent outliers. P value < 0.05 was considered significant.

Figure 3. Comparison of parasite densities by age groups.

Parasite density (natural log transformation). Dots represent outliers. P value < 0.05 was considered significant.

Figure 4. Trends of genotype frequencies of Pfcrt 76T, Pfmdr1 184F and Pfmdr1 86Y polymorphisms between 2008 and 2014.

There was a significant difference (p < 0.0001) for each of the Pfcrt 76T, Pfmdr1 184F and Pfmdr1 86Y SNPs with χ² of 354, 780, 103 respectively from 2008 to 2014. Pfcrt 76 (n = 1,579), Pfmdr1 86 (n = 1,676) and Pfmdr1 184 (1570).

Figure 5. Spatial distribution patterns of (A) Pfcrt 76T, (B) Pfmdr1 184F and (C) Pfmdr1 86Y SNPs by malaria epidemic zones using QGIS version 2.18.

There was a significant difference among the Pfcrt 76T, Pfmdr1 184F and Pfmdr1 86Y SNPs across the epidemic zones (χ2 (6) = 39.5, p < 0.0001), (χ2 (6) = 21.9, p < 0.001) and (χ2 (6) = 17.1, p < 0.009) respectively.