Dataset Information

Malaria risk assessment and mapping using satellite imagery and boosted regression trees in the Peruvian Amazon.

ABSTRACT: This is the first study to assess the risk of co-endemic Plasmodium vivax and Plasmodium falciparum transmission in the Peruvian Amazon using boosted regression tree (BRT) models based on social and environmental predictors derived from satellite imagery and data. Yearly cross-validated BRT models were created to discriminate high-risk (annual parasite index API?>?10 cases/1000 people) and very-high-risk for malaria (API?>?50 cases/1000 people) in 2766 georeferenced villages of Loreto department, between 2010-2017 as other parts in the article (graphs, tables, and texts). Predictors were cumulative annual rainfall, forest coverage, annual forest loss, annual mean land surface temperature, normalized difference vegetation index (NDVI), normalized difference water index (NDWI), shortest distance to rivers, time to populated villages, and population density. BRT models built with predictor data of a given year efficiently discriminated the malaria risk for that year in villages (area under the ROC curve (AUC)?>?0.80), and most models also effectively predicted malaria risk in the following year. Cumulative rainfall, population density and time to populated villages were consistently the top three predictors for both P. vivax and P. falciparum incidence. Maps created using the BRT models characterize the spatial distribution of the malaria incidence in Loreto and should contribute to malaria-related decision making in the area.

SUBMITTER: Solano-Villarreal E

PROVIDER: S-EPMC6811674 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Malaria risk assessment and mapping using satellite imagery and boosted regression trees in the Peruvian Amazon.

Solano-Villarreal Elisa E Valdivia Walter W Pearcy Morgan M Linard Catherine C Pasapera-Gonzales José J Moreno-Gutierrez Diamantina D Lejeune Philippe P Llanos-Cuentas Alejandro A Speybroeck Niko N Hayette Marie-Pierre MP Rosas-Aguirre Angel A

Scientific reports 20191023 1

This is the first study to assess the risk of co-endemic Plasmodium vivax and Plasmodium falciparum transmission in the Peruvian Amazon using boosted regression tree (BRT) models based on social and environmental predictors derived from satellite imagery and data. Yearly cross-validated BRT models were created to discriminate high-risk (annual parasite index API > 10 cases/1000 people) and very-high-risk for malaria (API > 50 cases/1000 people) in 2766 georeferenced villages of Loreto department ...[more]

PMID: 31645604

Similar Datasets

Project description:BackgroundWith low and markedly seasonal malaria transmission, increasingly sensitive tools for better stratifying the risk of infection and targeting control interventions are needed. A cross-sectional survey to characterize the current malaria transmission patterns, identify hotspots, and detect recent changes using parasitological and serological measures was conducted in three sites of the Peruvian Amazon.Material and methodsAfter full census of the study population, 651 participants were interviewed, clinically examined and had a blood sample taken for the detection of malaria parasites (microscopy and PCR) and antibodies against P. vivax (PvMSP119, PvAMA1) and P. falciparum (PfGLURP, PfAMA1) antigens by ELISA. Risk factors for malaria infection (positive PCR) and malaria exposure (seropositivity) were assessed by multivariate survey logistic regression models. Age-specific seroprevalence was analyzed using a reversible catalytic conversion model based on maximum likelihood for generating seroconversion rates (SCR, λ). SaTScan was used to detect spatial clusters of serology-positive individuals within each site.ResultsThe overall parasite prevalence by PCR was low, i.e. 3.9% for P. vivax and 6.7% for P. falciparum, while the seroprevalence was substantially higher, 33.6% for P. vivax and 22.0% for P. falciparum, with major differences between study sites. Age and location (site) were significantly associated with P. vivax exposure; while location, age and outdoor occupation were associated with P. falciparum exposure. P. falciparum seroprevalence curves showed a stable transmission throughout time, while for P. vivax transmission was better described by a model with two SCRs. The spatial analysis identified well-defined clusters of P. falciparum seropositive individuals in two sites, while it detected only a very small cluster of P. vivax exposure.ConclusionThe use of a single parasitological and serological malaria survey has proven to be an efficient and accurate method to characterize the species specific heterogeneity in malaria transmission at micro-geographical level as well as to identify recent changes in transmission.

Project description:BackgroundUnderstanding the dynamics of malaria transmission in diverse endemic settings is key for designing and implementing locally adapted and sustainable control and elimination strategies. A parasitological and epidemiological survey was conducted in September-October 2012, as a baseline underlying a 3-year population-based longitudinal cohort study. The aim was to characterize malaria transmission patterns in two contrasting ecological rural sites in the Peruvian Amazon, Lupuna (LUP), a riverine environment, and Cahuide (CAH), associated with road-linked deforestation.MethodsAfter a full population census, 1941 individuals 3 years and older (829 in LUP, 1112 in CAH) were interviewed, clinically examined and had a blood sample taken for the detection of malaria parasites by microscopy and PCR. Species-specific parasite prevalence was estimated overall and by site. Multivariate logistic regression models assessed risk factors for parasite infection by PCR, while SaTScan detected spatial clusters of PCR-positive individuals within each site. In addition, data from routine malaria surveillance in the period 2009-2012 were obtained.ResultsParasite prevalence by PCR was higher in CAH than in LUP for Plasmodium vivax (6.2% vs. 3.9%) and for Plasmodium falciparum (2.6% vs. 1.2%). Among PCR-confirmed infections, asymptomatic (Asy) parasite carriers were always more common than symptomatic (Sy) infections for P. vivax (Asy/Sy ratio: 2/1 in LUP and 3.7/1 in CAH) and for P. falciparum (Asy/Sy ratio: 1.3/1 in LUP and 4/1 in CAH). Sub-patent (Spat) infections also predominated over patent (Pat) infections for both species: P. vivax (Spat/Pat ratio: 2.8/1 in LUP and 3.7/1 in CAH) and P. falciparum malaria (Spat/Pat ratio: 1.9/1 in LUP and 26/0 in CAH). For CAH, age, gender and living in a household without electricity were significantly associated with P. vivax infection, while only age and living in a household with electricity was associated with P. falciparum infection. For LUP, only household overcrowding was associated with P. falciparum infection. The spatial analysis only identified well-defined clusters of P. vivax and P. falciparum infected individuals in CAH. Reported malaria incidence indicated that malaria transmission has long occurred in LUP with primarily seasonal patterns, and confirmed a malaria outbreak in CAH since May 2012.ConclusionsThis parasitological and epidemiological baseline assessment demonstrates that malaria transmission and parasite prevalence is heterogeneous in the Peruvian Amazon, and influenced by local socio-demographics and ecological contexts. Riverine and road construction/deforestation contexts must be taken into account in order to carry out effective anti-malaria control and elimination efforts.

Project description:BackgroundCase management is one of the principal strategies for malaria control. This study aimed to estimate the economic costs of uncomplicated malaria case management and explore the influence of health-seeking behaviours on those costs.MethodsA knowledge, attitudes and practices (KAP) survey was applied to 680 households of fifteen communities in Mazan-Loreto in March 2017, then a socio-economic survey was conducted in September 2017 among 161 individuals with confirmed uncomplicated malaria in the past 3 months. Total costs per episode were estimated from both provider (Ministry of Health, MoH) and patient perspectives. Direct costs were estimated using a standard costing estimation procedure, while the indirect costs considered the loss of incomes among patients, substitute labourers and companions due to illness in terms of the monthly minimum wage. Sensitivity analysis evaluated the uncertainty of the average cost per episode.ResultsThe KAP survey showed that most individuals (79.3%) that had malaria went to a health facility for a diagnosis and treatment, 2.7% received those services from community health workers, and 8% went to a drugstore or were self-treated at home. The average total cost per episode in the Mazan district was US$ 161. The cost from the provider's perspective was US$ 30.85 per episode while from the patient's perspective the estimated cost was US$ 131 per episode. The average costs per Plasmodium falciparum episode (US$ 180) were higher than those per Plasmodium vivax episode (US$ 156) due to longer time lost from work by patients with P. falciparum infections (22.2 days) than by patients with P. vivax infections (17.0 days). The delayed malaria diagnosis (after 48 h of the onset of symptoms) was associated with the time lost from work due to illness (adjusted mean ratio 1.8; 95% CI 1.3, 2.6). The average cost per malaria episode was most sensitive to the uncertainty around the lost productivity cost due to malaria.ConclusionsDespite the provision of free malaria case management by MoH, there is delay in seeking care and the costs of uncomplicated malaria are mainly borne by the families. These costs are not well perceived by the society and the substantial financial impact of the disease can be frequently undervalued in public policy planning.

Project description:BackgroundThe landscape of malaria transmission in the Peruvian Amazon is temporally and spatially heterogeneous, presenting different micro-geographies with particular epidemiologies. Most cases are asymptomatic and escape routine malaria surveillance based on light microscopy (LM). Following the implementation of control programs in this region, new approaches to stratify transmission and direct efforts at an individual and community level are needed. Antibody responses to serological exposure markers (SEM) to Plasmodium vivax have proven diagnostic performance to identify people exposed in the previous 9 months.MethodologyWe measured antibody responses against 8 SEM to identify recently exposed people and determine the transmission dynamics of P. vivax in peri-urban (Iquitos) and riverine (Mazán) communities of Loreto, communities that have seen significant recent reductions in malaria transmission. Socio-demographic, geo-reference, LM and qPCR diagnosis data were collected from two cross-sectional surveys. Spatial and multilevel analyses were implemented to describe the distribution of seropositive cases and the risk factors associated with exposure to P. vivax.Principal findingsLow local transmission was detected by qPCR in both Iquitos (5.3%) and Mazán (2.7%); however, seroprevalence indicated a higher level of (past) exposure to P. vivax in Mazán (56.5%) than Iquitos (38.2%). Age and being male were factors associated with high odds of being seropositive in both sites. Higher antibody levels were found in individuals >15 years old. The persistence of long-lived antibodies in these individuals could overestimate the detection of recent exposure. Antibody levels in younger populations (<15 years old) could be a better indicator of recent exposure to P. vivax.ConclusionsThe large number of current and past infections detected by SEMs allows for detailed local epidemiological analyses, in contrast to data from qPCR prevalence surveys which did not produce statistically significant associations. Serological surveillance will be increasingly important in the Peruvian Amazon as malaria transmission is reduced by continued control and elimination efforts.

Dataset Information

Malaria risk assessment and mapping using satellite imagery and boosted regression trees in the Peruvian Amazon.

Publications

Malaria risk assessment and mapping using satellite imagery and boosted regression trees in the Peruvian Amazon.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets