doi: 10.1371/journal.pntd.0007838.
eCollection 2019 Oct.
Village-scale persistence and elimination of gambiense human African trypanosomiasis
Affiliations
- PMID: 31658269
- PMCID: PMC6837580
- DOI: 10.1371/journal.pntd.0007838
Item in Clipboard
Village-scale persistence and elimination of gambiense human African trypanosomiasis
Christopher N Davis et al.
PLoS Negl Trop Dis.
.
Display options
Format
Display options
Format
Abstract
Gambiense human African trypanosomiasis (gHAT) is one of several neglected tropical diseases that is targeted for elimination by the World Health Organization. Recent years have seen a substantial decline in the number of globally reported cases, largely driven by an intensive process of screening and treatment. However, this infection is highly focal, continuing to persist at low prevalence even in small populations. Regional elimination, and ultimately global eradication, rests on understanding the dynamics and persistence of this infection at the local population scale. Here we develop a stochastic model of gHAT dynamics, which is underpinned by screening and reporting data from one of the highest gHAT incidence regions, Kwilu Province, in the Democratic Republic of Congo. We use this model to explore the persistence of gHAT in villages of different population sizes and subject to different patterns of screening. Our models demonstrate that infection is expected to persist for long periods even in relatively small isolated populations. We further use the model to assess the risk of recrudescence following local elimination and consider how failing to detect cases during active screening events informs the probability of elimination. These quantitative results provide insights for public health policy in the region, particularly highlighting the difficulties in achieving and measuring the 2030 elimination goal.
Conflict of interest statement
The authors have declared that no competing interests exist.
Figures
(A) Map of Africa, showing the DRC (lighter green) with former Bandundu province highlighted in the lightest green. The area containing the health zones Yasa-Bonga and Mosango (presented in more detail in Fig 1C) is covered in a purple box. (B) Histograms of the estimated population sizes of villages in the region for 2012. The inset figure highlights the distribution of population sizes less than 2,000 individuals. Population sizes have a range of 3 to 12,645. (C) Detailed map of locations of settlements within the study region (Fig 1A, purple box), colour and radius of the circle represent population size of the individual settlements. The satellite image shown for the Yasa-Bonga and Mosango health zones is from Landsat-8 accessed through https://earthexplorer.usgs.gov/ from the U.S. Geological Survey. (D) Histogram of the coverage achieved in visits to settlements as part of the active screening programme. When annual screenings are larger than the estimated accessible population (yellow and red bars), this may indicate either multiple screenings in a given year, or misreporting, when individuals are attending from neighbouring settlements.
(A) Histogram by population size of the percentage of active screenings that find no new gHAT cases for both the model and the HAT Atlas data. Each bar represents 100 screenings of simulated results (averaged over 10,000 replicates) from the model that uses the observed pattern of screenings and compares to the data. Values where the model predictions have more zero-detections than the data are in red, while the reverse is shown in yellow. Error bars represent the 95th percentile of model results. (B) Map of populations in Yasa-Bonga and Mosango showing the settlements with significant differences (at the 95% level) in the expected proportion of active screenings with no cases detected. Red circles are where the observed number of active screenings with zero-detections is below the 95th percentile of the model; yellow circles are where the data falls above the 95th percentile; small blue circles are for data that lie within the 95th percentile of predictions and therefore are well described by the model. The satellite image shown is from Landsat-8 accessed through https://earthexplorer.usgs.gov/ from the U.S. Geological Survey.
Simulations are started at the endemic (uncontrolled) equilibrium and iterated forwards (without infectious imports), while the persistence of infection is recorded. This is repeated 100,000 times for settlement population sizes between 50 and 2,000 individuals. The expected number of yearly new infections if the system were at equilibrium is proportional to the population size and is given by the top scale. (A) Impact of active screening on gHAT persistence; annual screening at a fixed coverage per year yields a drop in persistence with increased coverage. (B) Comparison of screening assumptions on the persistence of gHAT. The solid curve shows results where annual screening coverages were randomly sampled from all observed coverages; dots represent the individual settlements recorded in the WHO HAT Atlas for Yasa-Bonga and Mosango health zones [7, 13], where the reported coverage in each year is used. There were sufficient simulations such that confidence intervals are too small to be visible.
(A) Starting with no infected humans but the tsetse population at its endemic equilibrium and a settlement size of 1,000 individuals, the model predicts a dramatic decline in the infected tsetse population, depending on whether subsequent human cases are generated by the infected tsetse. (B) Extending this model further for a range of initial conditions, we examine the probability that at least one human case is generated and the infection persists for a given time, when starting with one infected human and no infected tsetse for both uncontrolled and random screening.
(A) Consecutive zero-detections means consecutive in the observed years of screenings, not necessarily in consecutive years, and with no passive cases detected in between. Each point represents the average from multiple simulations of individual settlements where the reported pattern of screenings is replayed. The points and solid lines assume a reporting rate of 26% [17], while the dashed and dotted lines show reporting rates of 0% and 100%, respectively. Sufficient simulations are used such that the confidence intervals are small (unobservable on the scale of this graph). Lines represent a weighted local regression fit. Active screenings where fewer than 20% of the population are assessed are excluded from our analysis due to the small sample sizes (alternative cut-offs of less than 10% and less than 50% are presented in Fig 13 in S1 Appendix).
(A) By running simulations with different values for the external infection parameter, we find the best fit—to data binned by population size from the WHO HAT Atlas on whether there are any detected cases on the first active screening—is when imports per susceptible individual are equal to 3.4 ×ばつ 10−6 days−1 (solid line). (B) Curves of the expected time for an external importation into a village population using the fitted importation parameter. The importation parameter is assumed to decay at the same rate as total number of cases in time in the DRC (see Fig 5 in S1 Appendix).
References
-
- World Health Organization. Global health observatory data repository; 2018.
-
- World Health Organization. Sustaining the drive to overcome the global impact of neglected tropical diseases. World Health Organization; 2013.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources