ARBOALVO: A Bayesian spatiotemporal learning and predictive model for dengue cases in the endemic Northeast city of Natal, Rio Grande do Norte, Brazil

Abstract

Background: Urban arbovirus transmission is spatially and temporally heterogeneous. Estimating the risk of dengue through statistical models that consider simultaneous variability in space and time provides more realistic estimates of transmission dynamics, facilitating the identification of priority areas for intervention focused on surveillance and control. These models also enable predictions to support timely interventions for arboviruses like dengue, chikungunya, and Zika.

Methodology/principal findings: We analyzed dengue case reports by epidemiological week and neighborhood in Natal, RN from 2015 to 2018. Temporal conditional autoregressive models were fitted using the Integrated Nested Laplace Approximation method. The predictors included a set of entomological, climatic and sociosanitary indicators with temporal lags, along with structures of temporal and spatial dependence. Additionally, we used an offset term to represent the expected number of dengue cases per neighborhood at each epidemiological week, under the hypothesis of homogeneity in the occurrence of cases across the municipality. We forecasted dengue case counts for the subsequent four weeks, addressing both zero occurrences and fluctuations during non-zero periods. Weekly risk dynamics were visualized through predictive maps, enabling the timely identification of neighborhoods with high and persistent dengue risk, that is, areas consistently exhibiting a high number of dengue cases that remained concentrated in the same location for several weeks. The optimal model revealed a significant rise in dengue occurrence probability during the observation week, associated with increased cases in the previous week, the Aedes egg positivity index from the prior four weeks, and the mean daytime temperature 6-8 weeks earlier. Dengue risk also rose with a one-standard-deviation increase in the density of the impoverished population per occupied area and the mean Aedes egg density index from the preceding 3-5 weeks.

Conclusions/significance: The proposed Bayesian space-time analysis can contribute to the operational control of dengue and Aedes aegypti by identifying priority areas and forecasting dengue cases for the next four weeks. It also quantifies the effects of entomological, sociosanitary, climatic and demographic indicators on both the likelihood of dengue occurrence and the intensity of outbreaks.

Fig 1. Map of the city of Natal by administrative regions.

Source: Figure created by the authors. Shapefile of the neighborhoods in the city of Natal: https://www.natal.rn.gov.br/semurb/geoinformacoes. Shapefile of the municipalities in the state of Rio Grande do Norte and shapefile of the Brazilian states: https://www.ibge.gov.br/geociencias/organizacao-do-territorio/malhas-territoriais/15774-malhas.html.

Fig 2. Time series of dengue cases, between the 45th epidemiological week of 2015 and the 16th week of 2018, for each neighborhood, according to administrative region, city of Natal, RN.

Fig 3. Boxplots of the egg density index across neighborhoods between the 45th epidemiological week of 2015 and 16th week of 2018, according to administrative region, city of Natal, RN. The solid lines represent the moving average of the egg density index in a temporal window of four epidemiological weeks.

Fig 4. Boxplots of the egg positivity index across neighborhoods between the 45th epidemiological week of 2015 and 16th week of 2018, according to administrative region, city of Natal, RN. The solid lines represent the moving average of the egg positivity index in a temporal window of four epidemiological weeks.

Fig 5. Boxplots of daytime temperature across neighborhoods between the 45th epidemiological week of 2015 and 16th week of 2018, according to administrative region, city of Natal, RN. The solid lines represent the moving average of daytime temperatures in a temporal window of four epidemiological weeks.

Fig 6. Stratification map by neighborhood of the poor population density indicator, by occupied area, city of Natal, RN.

Source: Figure created by the authors. Shapefile of the neighborhoods in the city of Natal: https://www.natal.rn.gov.br/semurb/geoinformacoes

Fig 7. Fit and prediction of the average number of dengue cases for the selected neighborhoods in periodt1, which starts at the 45th epidemiological week of 2015.

Prediction for the epidemiological weeks of 2017, city of Natal, RN. Solid line: Point adjustment/forecast. Gray region: Credibility interval at the 95% credibility level for the adjustment /forecast. Red dots: Reported dengue case counts.

Fig 8. Fit and prediction of the average number of dengue cases for the selected neighborhoods in periodt2, which starts in the 45th epidemiological week of 2015.

Prediction for the 5th to 8th epidemiological weeks of 2018, city of Natal, RN. Solid line: Point adjustment/forecast. Gray region: Credibility interval at the 95% credibility level for the adjustment /forecast. Red dots: Reported dengue case counts.

Fig 9. Fit and prediction of the average number of dengue cases for the selected neighborhoods in period t3, which starts in the 45th epidemiological week of 2015.

Prediction for the 9th to 12th epidemiological weeks of 2018, city of Natal, RN. Solid line: Point adjustment/forecast. Gray region: Credibility interval at the 95% credibility level for the adjustment /forecast. Red dots: Reported dengue case counts.

Fig 10. Fit and prediction of the average number of dengue cases for the selected neighborhoods in period t4, which starts in the 45th epidemiological week of 2015.

Prediction for the 13th to 16th epidemiological weeks of 2018, city of Natal, RN. Solid line: Point adjustment/forecast. Gray region: Credibility interval at the 95% credibility level for the adjustment /forecast. Red dots: Reported dengue case counts.

Fig 11. Fit and prediction of the average number of dengue cases for the Pajuçara neighborhood in period t4, which starts at the 45th epidemiological week of 2015.

Forecasts one week ahead, in the period between the 13th and 16th epidemiological weeks of 2018, city of Natal, RN. Solid line: Point adjustment/forecast. Gray region: Credibility interval at the 95% credibility level for the adjustment /forecast. Red dots: Reported dengue case counts.

Fig 12. Stratification maps of observed and predicted dengue case counts for four epidemiological weeks ahead (between the 13th and 16th epidemiological weeks of 2018), city of Natal, RN.