Malaria early warning tool: linking inter-annual climate and malaria variability in northern Guadalcanal, Solomon Islands

Smith, Jason B.; Tahani, Lloyd; Bobogare, Albino; Bugoro, Hugo; Otto, Francis; Fafale, George; Hiriasa, David; Kazazic, Adna; Beard, G. R.; Amjadali, Amanda; Jeanne, Isabelle

doi:10.1186/s12936-017-2120-5

Cited by 14 publications

(20 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study used the auto.arima statement to build the SARIMA model, in which lag = 12. The optimal ARIMA model for Yunnan Province is (0,1,2) × (0,1,1) [12]. Moreover, the seasonal decomposition model was implemented using the stlf statement, and the optimal model is ARIMA (0,1,2).…”

Section: Resultsmentioning

confidence: 99%

“…Moreover, the seasonal decomposition model was implemented using the stlf statement, and the optimal model is ARIMA (0,1,2). In addition, by using the nnetar statement, the BP-ANN model was established, and the optimal parameter set is "NNAR (12,1,3) [12] ". In the LSTM used in this study, the optimizer is RMSprop, the learning rate is 0.001, the loss function is MSE, and the number of hidden layers is 2.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A novel model for malaria prediction based on ensemble algorithms

Wang

et al. 2019

PLoS ONE

View full text Add to dashboard Cite

Background and objectiveMost previous studies adopted single traditional time series models to predict incidences of malaria. A single model cannot effectively capture all the properties of the data structure. However, a stacking architecture can solve this problem by combining distinct algorithms and models. This study compares the performance of traditional time series models and deep learning algorithms in malaria case prediction and explores the application value of stacking methods in the field of infectious disease prediction.MethodsThe ARIMA, STL+ARIMA, BP-ANN and LSTM network models were separately applied in simulations using malaria data and meteorological data in Yunnan Province from 2011 to 2017. We compared the predictive performance of each model through evaluation measures: RMSE, MASE, MAD. In addition, gradient-boosting regression trees (GBRTs) were used to combine the above four models. We also determined whether stacking structure improved the model prediction performance.ResultsThe root mean square errors (RMSEs) of the four sub-models were 13.176, 14.543, 9.571 and 7.208; the mean absolute scaled errors (MASEs) were 0.469, 0.472, 0.296 and 0.266 and the mean absolute deviation (MAD) were 6.403, 7.658, 5.871 and 5.691. After using the stacking architecture combined with the above four models, the RMSE, MASE and MAD values of the ensemble model decreased to 6.810, 0.224 and 4.625, respectively.ConclusionsA novel ensemble model based on the robustness of structured prediction and model combination through stacking was developed. The findings suggest that the predictive performance of the final model is superior to that of the other four sub-models, indicating that stacking architecture may have significant implications in infectious disease prediction.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

A novel model for malaria prediction based on ensemble algorithms

Wang

et al. 2019

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Study results not only revealed clear rainfall thresholds, but significant lag associations between rainfall and increases in malaria incidence such that drier October-December periods are followed by higher malaria transmission periods in January-June. Based on these statistical relationships an experimental early warning system has been proposed for the Guadalcanal region of the Solomon Islands [109]. Chuang et al [110] used cross-wavelet coherence to evaluate the regional El Nino Southern Oscillation (ENSO) and Indian Ocean Dipole (IOD) effects on dengue incidence and local climate variables for Taiwan.…”

Section: Enso and Health Forecastingmentioning

confidence: 99%

“…Armed with this knowledge, they demonstrate how statistical models and geographical information systems are applied by the Colombian health authorities to develop early warning systems for malaria. For the Solomon Islands in the western Pacific, where ENSO has clear impacts on rainfall as a disease sensitive climate variable, Smith et al [109] applied stepwise regression to analyse climate variables and climate-associated malaria transmission at different lag intervals in order to identify rainfall thresholds associated with malaria categorised into three incidence categories. Study results not only revealed clear rainfall thresholds, but significant lag associations between rainfall and increases in malaria incidence such that drier October-December periods are followed by higher malaria transmission periods in January-June.…”

Section: Enso and Health Forecastingmentioning

confidence: 99%

El Niño Southern Oscillation (ENSO) and Health: An Overview for Climate and Health Researchers

McGregor

Ebi

2018

Atmosphere

View full text Add to dashboard Cite

Abstract:The El Niño Southern Oscillation (ENSO) is an important mode of climatic variability that exerts a discernible impact on ecosystems and society through alterations in climate patterns. For this reason, ENSO has attracted much interest in the climate and health science community, with many analysts investigating ENSO health links through considering the degree of dependency of the incidence of a range of climate diseases on the occurrence of El Niño events. Because of the mounting interest in the relationship between ENSO as a major mode of climatic variability and health, this paper presents an overview of the basic characteristics of the ENSO phenomenon and its climate impacts, discusses the use of ENSO indices in climate and health research, and outlines the present understanding of ENSO health associations. Also touched upon are ENSO-based seasonal health forecasting and the possible impacts of climate change on ENSO and the implications this holds for future assessments of ENSO health associations. The review concludes that there is still some way to go before a thorough understanding of the association between ENSO and health is achieved, with a need to move beyond analyses undertaken through a purely statistical lens, with due acknowledgement that ENSO is a complex non-canonical phenomenon, and that simple ENSO health associations should not be expected.

show abstract

“…These are currently not explicitly included in the model as hydrometeorological factors provide a better means of studying temporal variability of mosquito habitats. However, variations in climate variables, such as rainfall, have been known to influence the risk of malaria, including in the Solomon Islands [ 26 , 35 ], and may offer some cost efficiencies to malaria control programmes through early warning systems [ 35 , 36 ].…”

Section: Discussionmentioning

confidence: 99%

Mapping a Plasmodium transmission spatial suitability index in Solomon Islands: a malaria monitoring and control tool

Jeanne

Chambers

Kazazic

et al. 2018

Malar J

Self Cite

View full text Add to dashboard Cite

BackgroundMalaria remains a challenge in Solomon Islands, despite government efforts to implement a coordinated control programme. This programme resulted in a dramatic decrease in the number of cases and mortality however, malaria incidence remains high in the three most populated provinces. Anopheles farauti is the primary malaria vector and a better understanding of the spatial patterns parasite transmission is required in order to implement effective control measures. Previous entomological studies provide information on the ecological preferences of An. farauti but this information has never before been gathered and “translated” in useful tools as maps that provide information at both the national level and at the scale of villages, thus enabling local targeted control measures.MethodsA literature review and consultation with entomology experts were used to determine and select environmental preferences of An. farauti. Remote sensing images were processed to translate these preferences into geolocated information to allow them to be used as the basis for a Transmission Suitability Index (TSI). Validation was developed from independent previous entomological studies with georeferenced locations of An. farauti. Then, TSI was autoscaled to ten classes for mapping.ResultsKey environmental preferences for the An. farauti were: distance to coastline, elevation, and availability of water sources. Based on these variables, a model was developed to provide a TSI. This TSI was developed using GIS and remote sensing image processing, resulting in maps and GIS raster layer for all the eight provinces and Honiara City at a 250 m spatial resolution. For a TSI ranging from 0 as not suitable to 13 as most suitable, all the previous collections of An. farauti had mean TSI value between 9 and 11 and were significantly higher than where the vector was searched for and absent. Resulting maps were provided after autoscaling the TSI into ten classes from 0 to 9 for visual clarity.ConclusionsThe TSI model developed here provides useful predictions of likely malaria transmission larval sources based on the environmental preferences of the mosquito, An. farauti. These predictions can provide sufficient lead-time for agencies to target malaria prevention and control measures and can assist with effective deployment of limited resources. As the model is built on the known environmental preferences of An. farauti, the model should be completed and updated as soon as new information is available. Because the model did not include any other malaria transmission factors such as care availability, diagnostic time, treatment, prevention, and entomological parameters other than the ecological preferences neither, our suitability mapping represents the upper bound of transmission areas. The results of this study can now being used as the basis of a malaria monitoring system which has been jointly implemented by the Solomon Islands National Vector Borne Disease Control Programme, the Solomon Islands Meteorological Services and the Australian B...

show abstract

Malaria early warning tool: linking inter-annual climate and malaria variability in northern Guadalcanal, Solomon Islands

Cited by 14 publications

References 35 publications

A novel model for malaria prediction based on ensemble algorithms

A novel model for malaria prediction based on ensemble algorithms

El Niño Southern Oscillation (ENSO) and Health: An Overview for Climate and Health Researchers

Mapping a Plasmodium transmission spatial suitability index in Solomon Islands: a malaria monitoring and control tool

Contact Info

Product

Resources

About