A Randomized Clinical Trial to Compare Plasmodium falciparum Gametocytemia and Infectivity After Blood-Stage or Mosquito Bite-Induced Controlled Malaria Infection

Abstract

Background: For malaria elimination efforts, it is important to better understand parasite transmission to mosquitoes and develop models for early-clinical evaluation of transmission-blocking interventions.

Methods: In a randomized open-label trial, 24 participants were infected by bites from Plasmodium falciparum 3D7-infected mosquitoes (mosquito bite [MB]; n = 12) or by induced blood-stage malaria (IBSM) with the same parasite line (n = 12). After subcurative piperaquine treatment, asexual parasite and gametocytes kinetics were assessed, and mosquito feeding experiments were performed.

Results: Study procedures were well tolerated. The median peak gametocyte density was 1304/mL (interquartile range, 308-1607/mL) after IBSM, compared with 14/mL (10-64/mL) after MB inoculation (P < .001), despite similar peak asexual parasite densities (P = .48). Peak gametocyte density was correlated with preceding pfap2-g transcripts, indicative of gametocyte commitment (ρ = 0.62; P = .002). Direct feeding assays resulted in mosquito infections from 9 of 12 participants after IBSM versus 0 of 12 after MB inoculation (P < .001).

Conclusions: We observed a striking effect of inoculation method on gametocyte production, suggesting higher gametocyte commitment after IBSM. Our direct comparison of MB and IBSM establishes the controlled human malaria infection transmission model, using intravenous administration of P. falciparum-infected erythrocytes as a model for early-clinical evaluation of interventions that aim to interrupt malaria transmission.

Clinical trial registration: NCT03454048.

Keywords: Plasmodium falciparum; anopheles; controlled infection; gametocyte.

Figure 1.

Trial flow chart. Forty-one individuals were screened for eligibility, of whom 24 were included and divided over 4 study arms. All participants received low-dose piperaquine (LD-PQP) (480 mg) on day 8 (IBSM group) or when parasitemia reached a parasite count of 5000/mL (MB group) (first subcurative treatment [T1]. Participants received a second treatment with LD-PQP (second subcurative treatment [T2]) on recrudescence (parasites, 1500/mL) and a single, high-dose treatment (T3) on second recrudescence (1500/mL). Owing to thrombocytopenia, 1 participant in arm 1 received T1 7.5 days after inoculation and T3 on day 12.5. Because recrudescence occurred 15 days later, the final treatment (T4) with atovaquone-proguanil was initiated on day 27. Asexual recrudescence occurred in 2 IBSM participants after T1, and both received T3 directly (20.5 days after inoculation). All remaining participants of both cohorts received high-dose PQP (960 mg) or sulfadoxine-pyrimethamine (SP) (1000 mg/50 mg) (T3) on day 21 and final treatment with atovaquone-proguanil (T4) 36 days after inoculation. MB; mosquito bite. IBSM; induced blood-stage malaria. Abbreviations: BMI, body mass index; CV, cardiovascular; LFT, liver function test; UTIs, urinary tract infections.

Figure 2.

Asexual parasitemia and gametocytemia after mosquito bite (A, C) or blood-stage (B, D) inoculation. A, B, Black lines represent median asexual parasite densities as shown by 18S quantitative polymerase chain reaction (qPCR); gray lines, individual participant data; red lines, median gametocyte densities; pink lines, individual participant data (sum of ccp4 and pfmget quantitative reverse-transcription polymerase chain reaction [qRT-PCR] results). C, D, Dark pink lines represent median female gametocyte densities (ccp4 qRT-PCR); light pink lines, individual participant data; dark blue lines, median male gametocyte densities (pfmget qRT-PCR); light blue lines, individual participant data.

Figure 3.

Association between asexual parasite density, transcripts indicative of sexual commitment, and subsequent gametocyte density. Blue dots represent data from mosquito bite inoculation; green dots, data from blood-stage inoculation. A, Correlation between peak asexual parasitemia and peak gametocytemia after mosquito bite (n = 12) (Spearman ρ = 0.64; P = .02); or blood-stage inoculation (n = 12) (ρ 0.77; P = .003). B, Correlation between peak gametocytemia and the ratio of pfap2-g transcripts to ring-stage asexual sbp1 transcripts (n = 17) (Spearman ρ = 0.66; P = .001).

Figure 4.

Transmission to Anopheles mosquitoes by direct skin feeding or by membrane feeding of venous blood samples. A total of 71 direct feeding assays (DFAs) were conducted (median, 31 examined mosquitoes per experiment; interquartile range [IQR], 28–32), alongside 71 direct membrane feeding assays (DMFAs) (exactly 25 examined mosquitoes per experiment) and 71 DMFA experiments after gametocyte concentration by magnetic-activated cell sorting (DMFA-MACS; median: 18 mosquitoes examined per experiment; IQR, 16–19). For 1 participant in arm 1, feeding experiments at the first time point were not performed owing to undetectable gametocytemia. A, Total proportion of individuals infectious to mosquitoes by DFA, DMFA, and DMFA-MACS, during the study. B, Number of oocysts per mosquito in DFA, DMFA, and DMFA-MACS feeding experiments. C, D, Proportion of infected mosquitoes per individual per time point by treatment 3 (T3) treatment group (high-dose piperaquine [PQP; arm 3] or sulfadoxine-pyrimethamine [SP; arm 4], day 21) in DFA or DMFA-MACS. T3 was initiated immediately after the feeding experiments on day 21, feeding experiments on days 24 and 29 are after T3.

Figure 5.

Sample size requirements to use the current model to examine the efficacy of transmission-blocking interventions (TBIs). Sample size calculations were performed using the data from arm 3 of the current study (n = 6) and the controlled human malaria infection transmission trial conducted in Brisbane (n = 12) [10]. Three mosquito feeding time points per person were assumed. Power estimates are based on 4000 simulations per trial design, accounting for uncertainty in estimated transmission probability (log-odds, −3.64, 95% bayesian credible interval, −4.35 to −3.08) and interindividual variability (standard deviation on log-odds scale of 1.12; 95% bayesian credible interval, .59–1.93). Lines indicate TBI efficacies of 80%, 90%, and 95%, and power was calculated for comparisons of whether people were infectious (B; infecting ≥1 mosquito) and the proportion of mosquitoes they infected (A). Detecting a statistically significant difference in the proportion of infected mosquitoes between vaccinated and nonvaccinated participants with TBI efficacy of 95%, 90%, or 80% required 7, 10, or 15 volunteers per arm, respectively (80% power; P < .05).