Towards an intelligent malaria outbreak warning model Based Intelligent Malaria Outbreak Warning in Northern part Benin, West Africa

doi:10.21203/rs.3.rs-3097346/v1

Download PDF

Research Article

Towards an intelligent malaria outbreak warning model Based Intelligent Malaria Outbreak Warning in Northern part Benin, West Africa

https://doi.org/10.21203/rs.3.rs-3097346/v1

This work is licensed under a CC BY 4.0 License

Journal Publication

published 12 Feb, 2024

Read the published version in BMC Public Health →

Version 1

posted

You are reading this latest preprint version

Background

Malaria is one of the major vector-borne diseases most sensitive to climatic change in West Africa. The prevention and reduction of malaria are very difficult in Benin due to poverty, economic insatiability the non-control of environmental determinants. This study aims to develop an intelligent outbreak malaria early warning model driven by monthly time series climatic variables in the Northern part of Benin.

Methods

Climate data from nine rain gauge stations and malaria incidence data from 2009 to 2021 were extracted respectively from the National Meteorological Agency (METEO) and the Ministry of Health of Benin. Projected relative humidity and temperature were obtained from the coordinated regional downscaling experiment (CORDEX) simulations of the Rossby Centre Regional Atmospheric regional climate model(RCA4).

A structural equation model was employed to determine the effects of climatic variables on malaria incidence. We developed an intelligent malaria early warning model to predict the prevalence of malaria. using machine learning by applying three machine learning algorithms including Linear regression (LiR), Support Vector Machine (SVM), and Negative Binominal Regression (NBiR).

Results

Two ecological factors affect the incidence of malaria. Support vector machine regression is the best-performing algorithm, predicting 82% of malaria incidence in the Northern part of Benin.

The projection reveals an increase in malaria incidence under RCP4.5 and RCP8.5 over the studied period.

Discussion

These results reveal that the northern part of Benin is at high risk of malaria and specific malaria control programs are urged to reduce the risk of malaria.

Climate change

Malaria

prediction

Northern Benin

The impacts of climate change on human health have attracted more attention in the recent years. There is increasing evidence of adverse effects of climate change on health worldwide, both direct effects and indirect effects mediated by disruption in ecological and socio-economic systems.

The warming of our planet due to the emission of Greenhouse Gases (GHGs) is now a big challenge for worldwide countries. Due to its low adaptive capacity and high sensitivity of socio-economic systems, Africa is the most vulnerable continent to the impacts of climate change (IPCC, 2014; IPCC, 2022).

Malaria is considered one of the major vector-borne diseases most sensitive to changes in environmental conditions such as climate variables and land use change. The Transmission of malaria is linked with changes in temperature, rainfall, humidity as well as the level of immunity in humans (Ayanlade et al., 2013; Olson JAP and SH, 2006). Socio-economic factors influence also the occurrence of malaria either in a rural area or urban area (Adefemi et al., 2015; Lowe et al., 2013). The burden of mortality and morbidity is worse in poor countries, especially in West Africa (Adefemi et al., 2015).

Malaria is a vector-borne disease caused by the infection of red blood cells with protozoan parasites of the genus Plasmodium, where the parasites enter the human body through the bite of an infected species of Plasmodium that infect humans. The driver of malaria in Africa is the mosquito of the Anopheles Plasmodium falciparum which causes most of the severity and deaths attributable to the disease and resists treatment (Ayanlade et al., 2013).

Despite the efforts made over the decades by the Benin government, malaria caused 95% of deaths. The provinces of the Northern have the highest prevalence of malaria in Benin(EBSBV, 2019). The situation will be very harmful if specific action is not taken now to reduce the risk of malaria infection in Benin. Several authors have shown that there is a strong relationship between the prevalence of malaria and the climatic variables ( Donnees et al, 2010; M’Bra et al., 2018; Ayanlade et al. 2020, Diouf et al. 2020; Makinde et al. 2021). In Northern Benin, meteorological factors have a strong link with the incidence or prevalence of malaria(Salako et al., 2018; Djègbè et al., 2020). Rainfall ensures the persistence of larval sites with continuous vector biting rates in Benin (Subtil et al., 2014).

Modelling the links between the climatic factors and the incidence of malaria can help to have a good idea of the relationship between the incidence of malaria and climatic factors. A malaria early warning model can help to control, and reduce the risk of malaria and the impact of malaria on human well-being in Northern Benin.

Different statistical methods were applied to model the risk of malaria infection. Most of the methods lack the capacity to determine the direct and indirect effects of meteorological factors on the incidence or prevalence of malaria (Yuan & Bentler, 2006). The structural Equation Model (SEM) allows for the specification of direct and indirect effects (Austin, 2013). SEM allows for the inclusion of latent variables, such as the concept of ‘‘socio-health characteristics,’’ which is comprised of a number of indicators technically justified by the confirmatory factor analysis incorporated in SEM (Bollen, 1989). In this study, we applied SEM methodology to analyze the causal relationships among meteorological variables and explored their impact on the transmission of malaria.

The study area is located in the Northern part of Benin and covers the provinces of Atacora, Donga, and Borgou (Fig. 1). The climate of the study area is hot and humid(Adam, K.S., and Boko, 1993). It characterized by one dry season and one rainy season. The rainy season lasts from May-October when the ITCZ is in its northern position. Rainfall is maximal (253.61mm) in August and minimal (1.90) in January. The dry season is from November-April when the ‘Harmattan’ winds blow in from the northeast bringing air from the Sahara Desert (World Bank, 2023).

Data collection

Dependent variables

Monthly malaria cases in each district of the provinces of Borgou, Atacora, and Donga were collected from 2009 to 2021, at the Ministry of Health of Benin. This data includes all the population confirmed for being infected by malaria. A patient is declared to have malaria when the disease is confirmed at a laboratory by microscopy or rapid diagnostic (OMS;2021).

Independent variables

Monthly weather data on temperatures (maximum, mean, and minimum), wind speed, and relative humidities (maximum, mean, and minimum) were retrieved over the period 2009 to 2021 from the meteorological stations of Parakou Airport and Natitingou operated by the National Meteorological Agency of Benin. Monthly precipitation data for the period of 2009 to 2021 of seventeen rain gauge stations were extracted from the rain gauge stations and meteorological stations summarized in Table 1.

Table 1

Location of rain gauge and meteorological stations
Station	Latitude DEG°MIN'SEC''	Longitude DEG.FRAG	Longitude DEG°MIN'SEC''	Latitude DEG.FRAG
BIRNI	09°59'24''	1.529987	001°31'48''	9.990087
PENESSOULOU	09°14'24''	1.551297	001°33'05''	9.239867
TANGUIETA	10°37'02''	1.266561	001°16'00''	10.61712
KOUANDE	10°19'55''	1.692409	001°41'33''	10.33185
NATITINGOU	10°19'00''	1.383333	001°23'00''	10.31667
KALALE	10°17'24''	3.381675	003°22'54''	10.29007
BEMBEREKE	10°12'00''	2.666667	002°40'00''	10.2
BOUKOUMBE	10°10'00''	1.1	001°06'00''	10.16667
NIKKI	09°56'00''	3.2	003°12'00''	9.933333
BASSILA	09°01'22''	1.665544	001°39'56''	9.022698
MATERI	10°43'48''	1.012	001°00'43''	10.73
COPARGO	°'''		°'''
PEHUNCO	10°13'48''	2.003	002°00'11''	10.2299
PERERE	°'''		°'''
N'DALI	09°51'00''	2.7	002°42'00''	9.85
PARAKOU_AEROPORT	9°21'00''	2.6	2°36'00''	9.35
NATITINGOU_PEPORIYAKOU	10°22'42''	1.358889	001°21'32''	10.37833

Data processing

Factor analysis

The meteorological data (monthly average) were matched with the monthly average incidence of malaria. The data distribution was assessed using the univariate normality test and multivariate normality through the Henze-Zirkler test and Anderson-Darling test. Correlation, regression, as well as collinearity analysis, was performed by the conventional statistical methods distribution.

Exploratory Factor Analysis (EFA)

To determine confounding latent ecological factors from the set of observed climatic variables affecting the transmission of malaria, we apply Exploratory Factor Analysis (EFA)(Bentler et al., 1980; Ruscio & Roche, 2012).

To establish the relationship between the latent factors and indicators, varimax rotation was used (Table 2). A number of hidden factors affecting the infection of malaria were identified. The initial model is developed by data fitting on the basis of correlation and regression analysis as well as exploratory factor analysis.

Table 2

The Varimax method rotated each indicator in load factor on the two potential factors.
Indicators	Factors	Factor1(F1)	Factor2(F2)
I1	Monthly Average Precipitation
I2	Monthly Average Minimal Temperature		0.98
I3	Monthly Average Maximal Temperature	-0.82
I4	Monthly Average Mean Relative Humidity	0.98
I5	Monthly Average Maximal Relative Humidity	0.94
I6	Monthly Average Wind Speed		0.37
I7	Monthly Average Malaria Incidence	0.48

The model was further screened based on the model fitting indicators within an acceptable range, the model fitting residual distribution reasonable, the correlation coefficient of the equation in the model applicable, and parameter estimates of the model(Duo-quan et al., 2013).

Confirmatory Factor Analysis (CFA)

The primary goal of confirmatory factor analysis is to explain the covariances or correlations between many observed variables by means of a single latent variable(Austin, 2013). Seven observed indicators were analyzed in the prior model. According to the model t rule (t = p * (p + 1)/2 = 7 * 8/2 = 28), the convergence of the parameters was estimated using weighted least squares after 30 iterations(Modu et al., 2017).

Structural Equation Model (SEM)

The confirmatory analyses were accomplished with the structural equation models (SEM) (Bollen, 1989).The distinction between latent and observed variables is secondary to the distinction between dependent variables and independent variables (Bentler et al., 1980).The covariances among the dependent variables or between the dependent variables and the independent variables do not vary freely, instead, they are explained by the model through the free parameters. Correlations among the independent variables were set as zero due to the hypothesized model structure(Yuan & Bentler, 2006).

The following system of Eq. (3) describes the SEM technique in which the observed variables can be expressed as a linear combination of the potential factors plus residual terms. We, therefore, present SEM mathematical representations from Fig. 3 as follows:

Machine learning

Data Processing

A famous quote attributed to George Box is “All models are wrong; some models are useful”(Box, 1979). that will be used to make an accurate prediction of malaria incidence. We have used a random sampling method for defining a training set and test set to train the model and to evaluate the performance of the models to predict. As our number of observations is short, we randomly selected 90% of the data for training and 10% for testing a predictive model. To develop the malaria outbreak warning model, we have applied three different machine learning algorithms, including Support Vector Machine (SVM), Linear Regression (LiR), and Negative Binomial Regression (NBiR) Model.

To find the best predicting algorithm, we calculated the “Mean Absolute Error (MAE)”, “Mean Square Error (MSE)” & “Root Mean Square Error (RMSE)” of proposed models (SVM, LiR and BiRM) on the prediction of malaria incidence(Gupta et al., 2021).

Exploratory Factor analysis (EFA)

Two latent factors were identified, factor 1 (related to Average mean relative humidity, average maximum relative humidity, and Average maximal temperature) and factor 2 (related to Average minimal temperature). The two identified factors accounted for 67% of the total variance, and at α = 5% level of significance, χ2 = 18.56, df = 8, P-value = 0.017. This result provides sufficient evidence to explain malaria incidence in the study area.

To determine the number of factors to be retrieved, we explore Guttman–Kaiser (Guttman, 1954)and Cattell scree plots(Kaiser, 1960). The exact number of factors is equal to the number of Eigenvalues of the population correlation matrix (Table 3) that are greater than unity. Using the correlation matrix, we computed the eigenvalues 2.80, 1.12 0.29, 0.19, -0.04, -0.09, and − 0.20; These values revealed that the number of factors that influenced malaria incidence is two. In the screen plot test, the number of eigenvalues that are especially large supposedly corresponds to the number of factors in the analysis(Cattell, 1966).;

Table 3

Correlation matrix of climatic variables and malaria incidence.
Item	Mean	Std.Dev	Average Precipitation	Average minimal temperature	Average maximal temperature	Average mean relative humidity	Average maximal relative humidity	Average Wind Speed	Average Malaria incidence
Average Precipitation	113.96	71.58	1.00
Average minimal temperature	21.76	1.40	-0.01	1.00
Average maximal temperature	33.53	2.25	-0.14	0.16	1
Average mean relative humidity	65.43	13.03	0.12	0.32	-0.76	1
Average maximal relative humidity	83.38	11.72	0.06	0.39	-0.67	0.96	1
Average Wind Speed	2.03	0.37	-0.18	0.36	-0.01	0.04	0.05	1
Average malaria incidence	28.22	6.10	-0.04	-0.18	-0.48	0.42	0.43	-0.2	1

From the analysis of the matrix table (Table 3), we obtained the scree plot shown in Fig. 4 which represents the relative proportion of variance accounted for by the components. In the scree plot, the eigenvalues of the first two components greater than unity can be seen from the parallel indicator, while the subsequent components below unity also line up beneath the parallel indicator. the scree plot confirmed that the exact number of latent factors is two.

Table 4 displays Pearson’s cross-correlation between ecological variables and the occurrence of malaria incidence at various lag effects from 0 to 3 months. The lag0, Lag2 and lag3(eg: 0Month, 1Month, and 2Months) presented in Table 4 indicate the lagged correlation effects between climate variables and the incidence of malaria in Northern of Benin. At lag effects of 0 month, and 1 month; average precipitation, average mean relative humidity, and average maximum relative humidity have a positive association with the incidence of malaria respectively with (0.05,0.423, 0.431) and (0.015,0.554, 0.576). At lag effects of 2 months, average mean relative humidity, average maximum relative humidity, and wind speed are positively correlated with the incidence of malaria (0.526, 0.524,0.038) respectively.

Table 4

Cross-correlation between climatic variables and malaria incidence
Variables	Lag0	Lag1	Lag2
Average Precipitation	0.05	0.015	-0.073
Average minimal temperature	-0.183	-0.007	0.156
Average maximal temperature	-0.483	-0.456	-0.073
Average mean relative humidity	0.423	0.554	0.526
Average maximal relative humidity	0.431	0.576	0.554
Average Wind Speed	-0.195	-0.119	0.038

These results indicate that the meteorological variables at a lag of 1 month and 2 months would be good for the reproduction of mosquitoes and also the completion of their incubation periods (EIP) to be able to transmit malaria vectors to humans. Particularly, in this study area, at a lag effect of 2 months, the transmission of malaria will be very high and the non-infected neighbor areas(districts) can be infected because of the positive association of wind speed with malaria incidence. At lag effects of 1-month precipitation, and relative humidity are quite enough for the development of breeding sites for mosquitoes and their development to infect a human. On the other hand, average minimum temperature, average maximum relative humidity, average mean relative humidity, and wind speed are very good for the development cycle of mosquitoes and the transmission of the disease at a high scale.

Confirmatory factor Analysis

To confirm the number of factors to extract from the meteorological variables (CFA) was employed. Seven observed indicators were analyzed. In the final model, four observed indicators were retained through two latent factors. After the correction of the initial model (Fig. 2), the fit indices have been significantly improved compared to these initial models, standardized residual distribution was also smaller than the previous models. To validate the CFA model, the recommended cutoff values for TLI and CFI are 0.90, and that for RMSEA is 0.06, CFI > 0.90 or RMSEA < 0.06 implies a good model (Browne, 1993). Fitting process indicators showed that fitting indices like Standardized Root Mean Square Residual (SRMR), Robust Comparative Fit Index (CFI), Robust Tucker-Lewis Index (TLI), and approximate root mean square error (RMSEA) were in the acceptable range and this indicates that the model fits very well the data(TLI = 1, CFI = 1, SRMR = 0.008 and RMSEA = 0). All the latent variables were significant and are above 50% of loading.

Structural equation Model (SEM)

The Henze-Zirkler test revealed the non-normality of the data set (P value = 0). The means, standard deviations, and bi-variate correlations for all variables included in the analysis are shown in the correlation matrix table (3). The analysis of the correlation matrix table revealed the existence of multicollinearity among variables. The magnitude of the relationships demonstrates that many of the predictors are highly correlated, especially among the meteorological indicators. This is one of the necessities of the use of the SEM analytical technique given its superior handling of inter-correlated independent variables through the creation of latent constructs and direct and indirect pathways that circumvents the tendency to bias coefficient estimates(Bollen, 1989).

Figure 3 represents the graphical representation of the model analyzed. Before examining the relationships displayed in the model, it is crucial that recommended cutoff values are confident in an acceptable range. Inspection of the model presented in Fig. 3 reveals that the chi-square (348.113 df = 10, not significant), RMSEA (0.000), TLI (1), CFI (1), and SRMR(0.008). These values show that the model is fitted well the data and can be used to determine the effects of ecological variables on the incidence of malaria.

Effects of climatic variables on the incidence of malaria

The analysis of the model Fig. 3 reveals that the direct effect of factor 1 is 0.84 and factor 2 is -0.58. The direct effect of average maximal temperature, average maximal relative humidity average mean relative humidity, and average minimum temperature on the incidence of malaria are respectively − 0.86, 0.78, and 0.71 and 1. The indirect effects of average mean relative humidity, average maximal temperature and factor 2 are indicated as 1.59, 1, and 0.39 respectively.

0.78, 2.30, 0.14, 1, 0.84, and − 0.19 are the total respective effects of average maximal relative humidity, average mean relative humidity, average maximal temperature, average minimal temperature, factor1(F1), and factor2(F2). Among the two factors identified by EFA, factor1 has the highest direct effect and the highest total effect on the incidence of malaria in the study area. We conclude that Factor 1 is the most influential hidden climatic factor in the incidence of malaria. So average Factor1 can be used to model and predict the incidence of malaria in the Northern part of Benin.

Intelligent Malaria Outbreak Warning Model

The following step is to identify the algorithm which will have the best accuracy the predict the incidence of malaria in the study areas. From the previous section, factor 1 indicated by average maximal relative humidity, average mean relative humidity, and average maximal temperature was identified most influential hidden climatic factor in the incidence of malaria.

To develop the malaria outbreak warning model, we applied three different machine learning algorithms, including Support Vector Machine (SVM), Linear Regression (LiR), and Negative Binominal Regression (BiR) Model. After training and test of the different algorithms (Fig. 5), we assess the performance of each model in other to identify the best algorithm which has good accuracy to predict the incidence of malaria in the Northern part of Benin (Table 5)

Table 5

Assessment of the Model Performance
Item	MAE	MSE	RMSE	Predicted R2
LiR	2.50	11.07	3.33	66%
SVM	1.66	5.89	2.43	82%
NBiR	22.11	504.84	47.22	66%

The Table5 shows the MAE, MSE, and RMSE for SVM, LiRM, and BiRM Models. The analysis of these errors permits us to conclude that SVM Model provides the optimized solution for predicting the other two models. We conclude that Support Vector Machine (SVM) has the best performance to predict the incidence of malaria in Northern Benin.

Prediction of Malaria incidence under scenarios RCP4.5 and RCP8.5

The RCA4 regional climate model used in this study was developed at the Swedish Meteorological and Hydrological Institute and has provided nearly 120 simulations in the CORDEX project (Coordinated Regional Climate Downscaling Experiment). The model considers the physical, chemical, and biological processes by which ecosystems affect climate through various spatial and temporal scales. Projected rainfall and temperature and relative humidity were retrieved from the coordinated regional downscaling experiment (CORDEX) simulations of the Rossby Centre Regional Atmospheric regional climate model (RCA4). The CORDEX-Africa data used in this work were obtained from the Earth System Grid Federation server (https://esgf-data.dkrz.de/search/cordex-dkrz/) driven by the RCA4 model. We have predicted the incidence of malaria with the Intelligent Malaria outbreak model we built (SVM model) by using the downloaded CORDEX data under two representative concentration pathway (RCP) scenarios (RCP4.5 and RCP8.5) in the Northern part of Benin with the RCA4-downscaled driving by the regional climate models RCA4/HadGEM, RCA4/CSIRO, and RCA4/MIROC over the period 2021–2030, 2031–2041 and 2041–2050.

Regional climate models RCA4/HadGEM2, RCA4/CSIRO, and RCA4/MIROC over the period 2021–2030, 2031–2040 and 2041–2050 are associated with an increase in malaria incidence under the scenario RCP4.5(Fig. 6). RCA4/HadGEM2 is associated with a decrease in the incidence of malaria over the period 2041–2050 under the same scenario.

The incidence of malaria will decrease under the scenario RCP8.5 driven by RCA4/CSIRO and RCA4/MIROC over the period 2021–2030(Figs. 6). An increase in malaria incidence is associated with RCA4/HadGEM2 over the same period under RCP8.5 (Fig. 6).

Overall, the findings suggest that malaria incidence will increase over 2021–2050 under scenarios RCP4.5 and RCP8.5 except for the period 2021–2030 where the incidence of malaria will decrease under RCP8.5 due to climate change. With regard to the findings of this study, the Northern part of Benin is at high risk of malaria.

Malaria Early Warning Model can be a good tool in the control of malaria transmission. In the Northern part of Benin, climatic factor indicated by average mean relative humidity, average maximum relative humidity, and average maximal temperature is the most influential meteorological variables of malaria infection. This factor has a positive effect on the incidence of malaria. This result is consistent with the finding of (Modu et al., 2017), where malaria incidence is positively associated with minimum temperature and relative humidity.

The projection revealed that malaria incidence will increase over 2021–2050 under scenario RCP4.5 and will decrease under RCP8.5 under RCP4.5 due to climate change. An increase in malaria incidence will be observed in the Northern part of Benin over the period 2021–2030, 2031–2040 and 2041–2050 under the scenario RCP4.5. Climate change is increasing the risk of malaria infection in the study areas. A study carried out in Northern Benin found that climate change has a real impact on Anopheles’ density and weakens current and future vector control strategies(Spray et al., 2018).

Climate changes or different weather conditions may impact infectious diseases, specifically, those transmitted by insect vectors and contaminated water(Lowe et al., 2013; Sominahouin, Padonou, et al., 2018, Cella et al., 2019).(Afrane et al, 2012) confirmed that temperature increases promote the rapid digestion of blood supply, which in turn promotes a significant increase in fecundity, with the development of better reproductive fitness and a greater ability to produce more offspring.

A study conducted by Salako in the province of Alibori, Northern Benin confirmed that the biting rates of An. Gambiae is higher in rainy season than in dry season(Salako et al., 2018).(Subtil et al., 2014) study in South Benin certified that rainfall ensures the persistence of peri-domestic larval sites in villages with continuous vector biting rates. The risk of malaria infection is very high in rainy season in the Northern part of Benin. These findings confirmed the influence of climate change on the transmission of malaria in the Northern part of Benin.

The study carried out by (Diouf et al., 2021) over West Africa found that the prevalence of malaria is expected to increase in the southern part of the region in the future. This result rhythmed with our study that reveals an increase in the prevalence of malaria under RCP4.5 and RCP8.5.

The use of climatic factors to predict the risk of malaria infection is also agreed with the findings of (Parham et al, 2010) who developed a simple model of climate-related malaria transmission that provides insights into the sensitivity of disease transmission to changes in precipitation and temperature. The consideration of climate variables in surveillance systems, as well as the integration of future climate projections into epidemiological models in order to more effectively predict the prevalence and outbreaks within the context of a changing climate is very important (Olson JAP and SH, 2006; Djohy & Gwimbi, 2013).

The increase in malaria incidence over the period 2021–2050 is supported by the projection of IPCC that predicted that malaria may threaten some previously unexposed regions of South America, and sub-Saharan Africa (SSA) in 2050 under the current climate change associated with the increase of CO2 concentrations and increase in atmospheric temperature(IPCC, 2014).

Continuous monitoring and evaluation of current and future malaria transmission status in Northern Benin is a mainstay for the success of ongoing intervention strategies for malaria control.

In light of the work above, climate factors determine the transmission of malaria in Northern Benin. Relative humidity and temperature have the potential influence on the transmission of malaria in the study areas. An intelligent malaria outbreak warning model developed by employing Support Vector Machine predicts the incidence of malaria at 82% in the study areas. This study reveals an increase in malaria incidence over the periods 2021–2050 under two different scenarios RCP4.5. The incidence of malaria will decrease under the scenario RCP8.5 over the period 2021–2030. The findings of this study are a powerful tool for the stakeholder to take specific preparedness actions to lessen the impacts of climate change on human health by reducing the emission of greenhouse gases in the study area.

Acknowledgements

We are grateful to the West African Science Service Centre on Climate Change and Adapted Land Use (WASCAL) to support the data collection for this study.

Author contributions

Nikita TOPANOU, and Guillaume K. KETOH designed the study. Gouvidé Jean GBAGUIDI collected the data., and analysed and interpreted the data. Nikita TOPANOU and Guillaume K. KETOH verified the public heath and meteorological data collected and validate the statistical methods applied. Gouvidé Jean GBAGUIDI wrote the manuscript. Nikita TOPANOU reviewed the manuscript. All authors had full access to all the data in the study, had the final responsibility for the decision to submit for publication, and approved the final version of this Article to be published.

Funding

This work was supported by the West African Science Service Centre on Climate Change and Adapted Land Use (WASCAL) , Université de Lomé.

Availability of data and materials

Data are available at the West African Science Service Centre on Climate Change and Adapted Land Use (WASCAL) , Université de Lomé.

Declarations Ethics approval and consent to participate

This study was approved bythe West African Science Service Centre on Climate Change and Adapted Land Use (WASCAL), Université de Lomé

Consent for publication

This study was approved by the West African Science Service Centre on Climate Change and Adapted Land Use (WASCAL) , Université de Lomé.

Competing interests

The authors declare no competing interests

Adam, K.S., and Boko, M. (1993). Title:Les Éditions du Flamboyant/EDICEF.
Afrane et al. (2012). The ecology of Anopheles mosquitoes under climate change: Case studies from the effects of deforestation in East African highlands. Acad Sci, 1249(1), 204–210.
Austin, K. F. (2013). Export agriculture is feeding malaria: A cross-national examination of the environmental and social causes of malaria prevalence. Population and Environment, 35(2), 133–158. https://doi.org/10.1007/s11111-013-0187-7
Ayanlade, A., Olugbade Adeoye, N., & Babatimehin, O. (2013). Intra-annual climate variability and malaria transmission in Nigeria. Bulletin of Geography, 21(August), 7–19. https://doi.org/10.2478/bog-2013-0016
Bentler, P.M., W., & D.G. (1980). Linear structural equations with latent variables. Psychometrika , 45, 289–308.
Bollen, K. A. (1989). Structural equations with latent variables. . New York: Wiley.
Box, G. E. P. (1979). Some problems of statistics and everyday life. Journal of the American Statistical Association, 74(365), 1–4. https://doi.org/10.1080/01621459.1979.10481600
Browne, M. W. (1993). Alternative ways of assesing model fit. In K. A. Bollen, & J. S. Long (1993). Testing structural equation models . . . Newbury Park, CA: Sage., 136–162.
Cattell, R. B. (1966). The scree test for the number of factors. Multivariate Behavioral Research, 1, 245–276.
Cella, W., Baia-da-silva, D. C., & Melo, G. C. De. (2019). Mini Review Do climate changes alter the distribution and transmission of malaria ? Evidence assessment and recommendations for future studies. November, 0–2. https://doi.org/10.1590/0037-8682-0308-2019
Djègbè, I., Zinsou, M., Dovonou, E. F., Tchigossou, G., Soglo, M., Adéoti, R., Gbaguidi, B., Atoyebi, S., Chandre, F., Akogbéto, M., & Lines, J. (2020). Minimal tillage and intermittent flooding farming systems show a potential reduction in the proliferation of Anopheles mosquito larvae in a rice field in Malanville , Northern Benin. Malaria Journal, 1–10. https://doi.org/10.1186/s12936-020-03406-2
Djohy, S., & Gwimbi, P. (n.d.). How climate change influences the disease burden: the case of meningitis in northern Benin and malaria in Zimbabwe .
Duo-quan, W., Lin-hua, T., Heng-hui, L., Zhen-cheng, G., & Xiang, Z. (2013). Application of Structural Equation Models for Elucidating the Ecological Drivers of Anopheles sinensis in the Three Gorges Reservoir. PLoS ONE, 8(7). https://doi.org/10.1371/journal.pone.0068766
EBSBV. (2019). EBSBV_5-MALADIES TRANSMISSIBLES PALU &VIH 15 03 2019_Hounto.
Gupta, A. K., Singh, V., Mathur, P., & Travieso-Gonzalez, C. M. (2021). Prediction of COVID-19 pandemic measuring criteria using support vector machine, prophet and linear regression models in Indian scenario. Journal of Interdisciplinary Mathematics, 24(1), 89–108. https://doi.org/10.1080/09720502.2020.1833458
Guttman, L. (1954). Some necessary conditions for common-factor analysis. Psychometrika, 19, 149–161.
IPCC. (2014). Summary for policymakers. In Managing the Risks of Extreme Events and Disasters to Advance Climate Change Adaptation: Special Report of the Intergovernmental Panel on Climate Change (Vol. 9781107025). https://doi.org/10.1017/CBO9781139177245.003
Kaiser, H. F. (1960). The application of electronic computers to factor analysis. Educational and Psychological Measurement, 20, 141–151.
Modu, B., Polovina, N., Lan, Y., Konur, S., Taufiq Asyhari, A., & Peng, Y. (2017). Towards a predictive analytics-based intelligent malaria outbreakwarning system. Applied Sciences (Switzerland), 7(8). https://doi.org/10.3390/app7080836
Ruscio, J., & Roche, B. (2012). Determining the number of factors to retain in an exploratory factor analysis using comparison data of known factorial structure. . Psychol. Assess., 24(282).
Salako, A. S., Ahogni, I., Kpanou, C., Sovi, A., Azondekon, R., Sominahouin, A. A., Tokponnon, F., Gnanguenon, V., Dagnon, F., Iyikirenga, L., & Akogbeto, M. C. (2018). Baseline entomologic data on malaria transmission in prelude to an indoor residual spraying intervention in the regions of Alibori. Malaria Journal, 1–14. https://doi.org/10.1186/s12936-018-2507-y
Spray, R., Africa, W., & Padonou, G. G. (2018). Influence of climatic factors on aggression and infectivity of Anopheles in the districts the Indoor. 1–26.
Subtil, F., Moiroux, N., Dje, A., & Lyon, D. (2014). Modeling the seasonality of Anopheles gambiae s . s . biting rates in a South Benin sanitary zone. February, 237–243. https://doi.org/10.1093/trstmh/tru027
Yuan, K. H., & Bentler, P. M. (2006). 10 Structural Equation Modeling. In Handbook of Statistics (Vol. 26, pp. 297–358). https://doi.org/10.1016/S0169-7161(06)26010-3

No competing interests reported.

Download PDF

Journal Publication

published 12 Feb, 2024

Read the published version in BMC Public Health →

Version 1

posted

You are reading this latest preprint version

Towards an intelligent malaria outbreak warning model Based Intelligent Malaria Outbreak Warning in Northern part Benin, West Africa

Status:

Journal Publication

Version 1

Abstract

Figures

Introduction

Study site, population, and climate

Data collection

Dependent variables

Independent variables

Data processing

Factor analysis

Exploratory Factor Analysis (EFA)

Confirmatory Factor Analysis (CFA)

Structural Equation Model (SEM)

Machine learning

Data Processing

Results

Exploratory Factor analysis (EFA)

Confirmatory factor Analysis

Structural equation Model (SEM)

Effects of climatic variables on the incidence of malaria

Intelligent Malaria Outbreak Warning Model

Prediction of Malaria incidence under scenarios RCP4.5 and RCP8.5

Discussion

Conclusion

Declarations

References

Additional Declarations

Status:

Journal Publication

Version 1