The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level data) and department level in Colombia to predict weekly dengue cases for 12-weeks ahead. A pooled national model based on artificial neural networks (ANN) was also developed and used as a comparator to the RF models. The various predictors included historic dengue cases, satellite-derived estimates for vegetation, precipitation, and air temperature, as well as population counts, income inequality, and education. Our RF model trained on the pooled national data was more accurate for department-specific weekly dengue cases estimation compared to a local model trained only on the department's data. Additionally, the forecast errors of the national RF model were smaller to those of the national pooled ANN model and were increased with the forecast horizon increasing from one-week-ahead (mean absolute error, MAE: 9.32) to 12-weeks ahead (MAE: 24.56). There was considerable variation in the relative importance of predictors dependent on forecast horizon. The environmental and meteorological predictors were relatively important for short-term dengue forecast horizons while socio-demographic predictors were relevant for longer-term forecast horizons. This study demonstrates the potential of RF in dengue forecasting with a feasible approach of using a national pooled model to forecast at finer spatial PLOS NEGLECTED TROPICAL DISEASES

Background Colombia has one of the highest burdens of arboviruses in South America. The country was in a state of hyperendemicity between 2014 and 2016, with co-circulation of several Aedes-borne viruses, including a syndemic of dengue, chikungunya, and Zika in 2015. Methodology/Principal findings We analyzed the cases of dengue, chikungunya, and Zika notified in Colombia from January 2014 to December 2018 by municipality and week. The trajectory and velocity of spread was studied using trend surface analysis, and spatio-temporal high-risk clusters for each disease in separate and for the three diseases simultaneously (multivariate) were identified using Kulldorff’s scan statistics. During the study period, there were 366,628, 77,345 and 74,793 cases of dengue, chikungunya, and Zika, respectively, in Colombia. The spread patterns for chikungunya and Zika were similar, although Zika’s spread was accelerated. Both chikungunya and Zika mainly spread from the regions on the Atlantic coast and the south-west to the rest of the country. We identified 21, 16, and 13 spatio-temporal clusters of dengue, chikungunya and Zika, respectively, and, from the multivariate analysis, 20 spatio-temporal clusters, among which 7 were simultaneous for the three diseases. For all disease-specific analyses and the multivariate analysis, the most-likely cluster was identified in the south-western region of Colombia, including the Valle del Cauca department. Conclusions/Significance The results further our understanding of emerging Aedes-borne diseases in Colombia by providing useful evidence on their potential site of entry and spread trajectory within the country, and identifying spatio-temporal disease-specific and multivariate high-risk clusters of dengue, chikungunya, and Zika, information that can be used to target interventions.

Background Colombia has one of the highest burdens of arboviruses in South America. The country was in a state of hyperendemicity between 2014 and 2016, with co-circulation of several Aedes -borne viruses, including a syndemic of dengue, chikungunya, and Zika in 2015. Methodology/Principal Findings We analyzed the cases of dengue, chikungunya, and Zika notified in Colombia from January 2014 to December 2018 by municipality and week. The trajectory and velocity of spread was studied using trend surface analysis, and spatio-temporal high-risk clusters for each disease in separate and for the three diseases simultaneously (multivariate) were identified using Kulldorff's scan statistics. During the study period, there were 66,628, 77,345 and 74,793 cases of dengue, chikungunya, and Zika, respectively, in Colombia. The spread patterns for chikungunya and Zika were similar, although Zika's spread was accelerated. Both chikungunya and Zika mainly spread from the regions on the Atlantic coast and the south-west to the rest of the country. We identified 21, 16, and 13 spatio-temporal clusters of dengue, chikungunya and Zika, respectively, and, from the multivariate analysis, 20 spatio-temporal clusters, among which 7 were simultaneous for the three diseases. For all disease-specific analyses and the multivariate analysis, the most-likely cluster was identified in the south-western region of Colombia, including the Valle del Cauca department. Conclusions/Significance The results further our understanding of emerging Aedes- borne diseases’ trajectory in Colombia and provide useful information on the identified spatio-temporal disease-specific and multivariate clusters of dengue, chikungunya, and Zika, that can be used to target interventions. To our knowledge, this is the first time that the co-occurrence of all three diseases in Colombia was explored using multivariate scan statistics.

29 30 31 32 33 34 35 36 2 37 Abstract:38 The robust estimate and forecast capability of random forests (RF) has been widely recognized, 39 however this ensemble machine learning method has not been widely used in mosquito-borne 40 disease forecasting. In this study, two sets of RF models were developed for the national and 41 departmental levels in Colombia to predict weekly dengue cases at 12-weeks ahead. A national 42 model based on artificial neural networks (ANN) was also developed and used as a comparator 43 to the RF models. The various predictors included historic dengue cases, satellite-derived 44 estimates for vegetation, precipitation, and air temperature, population counts, income inequality, 45 and education. Our RF model trained on the national data was more accurate for department-46 specific weekly dengue cases estimation compared to a local model trained only on the 47 department's data. Additionally, the forecast errors of the national RF model were smaller to 48 those of the national ANN model and were increased with the forecast horizon increasing from 49 one-week ahead (mean absolute error, MAE: 5.80; root mean squared error, RMSE: 11.10) to 50 12-weeks ahead (MAE: 13.38; RMSE: 26.82). There was considerable variation in the relative 51 importance of predictors dependent on forecast horizon. The environmental and meteorological 52 predictors were relatively important for short-term dengue forecast horizons while socio-53 demographic predictors were relevant for longer-term forecast horizons. This study showed the 54 potential of RF in dengue forecasting with also demonstrating the feasibility of using a national 55 model to forecast at finer spatial scales. Furthermore, sociodemographic predictors are important 56 to include to capture longer-term trends in dengue. 57 58 59 3 60 Author summary:61 Dengue virus has the highest disease burden of all mosquito-borne viral diseases, infecting 390 62 million people annually in 128 countries. Forecasting is an important warning mechanism that 63 can help with proactive planning and response for clinical and public health services. In this 64 study, we compare two different machine learning approaches to dengue forecasting: random 65 forest (RF) and neural networks (NN). National and local (departmental-level) models were 66 compared and used to predict dengue cases in the future. The results showed that the counts of 67 future dengue cases were more accurately estimated by RF than by NN. It was also shown that 68 environmental and meteorological predictors were more important for forecast accuracy for 69 shorter-term forecasts while socio-demographic predictors were more important for longer-term 70 forecasts. Finally, the national model applied to local data was more accurate in dengue 71 forecasting compared to the local model. This research contributes to the field of disease 72 forecasting and highlights different considerations for future forecasting studies. 73 74 75 76 77 78 79 80 81 4 82 Introduction83 Dengue virus is most prevalent of the mos...

Se realizó un estudio de corte transversal descriptivo en la sede central de la Universidad Cooperativa de Colombia en Villavicencio, Meta, Colombia, en el primer semestre de 2008, para conocer las características de la situación de salud de los estudiantes; se tomó una muestra de 172 estudiantes mediante muestreo aleatorio por conglomerados y se aplicó cuestionario autoadministrado. La edad promedio fue de 20 años, 91,7% solteros, 6,5% casados o en unión libre, 36,3% estudian y trabajan, 11,3% tiene hijos a cargo, el 60,9% estuvo enfermo en el último año; las enfermedades respiratorias y digestivas son las primeras causas de consulta; el 61,2% fue al médico en el último año, el 44,6% acudió a las Empresas Promotoras de Salud del Sistema de Seguridad Social, el 39,8% al médico particular y el 14,5% al servicio médico universitario; 15,5% usó tratamientos caseros; el 70,8% consume alcohol y el 45,5% lo hace semanalmente. Se recomienda realizar estrategias de bienestar estudiantil dirigidas a la población trabajadora y al buen uso del tiempo libre de la población universitaria.