Data Integration and Predictive Analysis System for Disease Prophylaxis: Incorporating Dengue Fever Forecasts

Freeze, John; Erraguntla, Madhav; Verma, Akshans

doi:10.24251/hicss.2018.114

Cited by 12 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random forests have been used to forecast dengue risk in several countries including Costa Rica [29], Philippines [30,31], Pakistan [32], Peru and Puerto Rico [33]. However, time or seasonal variables were not always included in the models nor were sociodemographic predictors, which have been found to improve forecast accuracy in HIV [34] and Ebola [35] epidemic models.…”

Section: Introductionmentioning

confidence: 99%

Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia

Zhao

Charland²,

Carabalí

et al. 2020

PLoS Negl Trop Dis

View full text Add to dashboard Cite

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

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia

Zhao

Charland²,

Carabalí

et al. 2020

PLoS Negl Trop Dis

View full text Add to dashboard Cite

show abstract

“…Furthermore, most of the participants approached the competition purely from historical perspective. This is evidenced by only one of the six papers published [28] which truly adopted forward looking nowcasting (forecasting the present or into the near future), which Marques-Toledo [33] emphasized is the most practical for situational awareness. [31] adopted nowcasting in one of the sub-model but not at the ensemble model level.…”

Section: Discussionmentioning

confidence: 99%

“…Freeze, Erraguntla and Verma [28] expanded their Data Integration and Predictive Analysis System (IPAS) for Influenza like Illness (ILI) to predict dengue cases in San Juan and Iquitos. Feature engineering was mostly centered on the weekly dengue incidences with normalization of dengue incidence to per hundred thousand of annual population; square and cube of the normalized dengue incidences as nonlinear terms; slope or the change in normalized incidence over 1-4 week horizons for trend analysis.…”

Section: Non-ensemble Modelsmentioning

confidence: 99%

Review on Nowcasting using Least Absolute Shrinkage Selector Operator (LASSO) to Predict Dengue Occurrence in San Juan and Iquitos as Part of Disease Surveillance System

Tang¹,

Subramanian

2019

PEN

View full text Add to dashboard Cite

Dengue which was first detected mainly in South East Asia during 1940s is now a serious public health concern across the subtropical and temperate regions of Americas, Europe and China due to the change in global climate and international travel. Hence, 3.9 billion people in 128 countries are exposed to the danger of potentially fatal dengue infection. This is a review paper of various dengue forecasting methodology to identify suitable models for predicting the disease occurrence in San Juan, Puerto Rico and Iquitos, Peru. Least Absolute Shrinkage Selector Operator (LASSO) model using climatic variables and Google Trends search terms as predictors was proposed to forecast dengue cases four weeks in advance. LASSO's flexibility in incorporating a variety of predictors and its ease of interpretation present LASSO as a compelling case against the general predictive models. Public health regulators could make use of such nowcasting model to facilitate the timing of vector control and public health campaigns along with the medical resource allocation to cope with potential dengue outbreaks.

show abstract

“…However, the clinical significance of 15 such predictions largely depend on the type and quality of data collected. There are studies that 16 assign a probability to the future risk of diabetes using socio-demographic characteristics such 17 as age, ethnicity, body-mass index (BMI) and genealogical information collected through 18 population [5,6]. Due to the unreliable data collection, such techniques can be misleading.…”

mentioning

confidence: 99%

“…The availability of big data in the healthcare sector has made Machine learning (ML) a 39 viable instrument for disease prediction [15,16] develop diagnostic models of diabetes [18]. This approach uses support vector machine (SVM) 45 along with a rule-based explanation to provide a comprehensibility of the results to the making algorithm for the diagnosis of diabetes [19].…”

mentioning

confidence: 99%

Predicting long-term Type 2 Diabetes with Support Vector Machine using Oral Glucose Tolerance Test

Abbas

Alic

Erraguntla

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Diabetes is a large healthcare burden worldwide. There is substantial evidence that lifestyle modifications and drug intervention can prevent diabetes, therefore, an early identification of high risk individuals is important to design targeted prevention strategies. In this paper, we present an automatic tool that uses machine learning techniques to predict the development of type 2 diabetes mellitus (T2DM). Data generated from an oral glucose tolerance test (OGTT) was used to develop a predictive model based on the support vector machine (SVM). We trained and validated the models using the OGTT and demographic data of 1,492 healthy individuals collected during the San Antonio Heart Study. This study collected plasma glucose and insulin concentrations before glucose intake and at three time-points thereafter (30, 60 and 120 min). Furthermore, personal information such as age, ethnicity and body-mass index was also a part of the dataset. Using 11 oral glucose tolerance test (OGTT) measurements, we have deduced 61 features, which are then assigned a rank and the top ten features are shortlisted using Minimum Redundancy Maximum Relevance feature selection algorithm. All possible combinations of the 10 best ranked features were used to generate SVM based prediction models. This research shows that an individual's plasma glucose levels, and the information derived therefrom have the strongest predictive performance for the future development of T2DM. Significantly, insulin and demographic features do not provide additional performance improvement for diabetes prediction. The results of this work identify the parsimonious clinical data needed to be collected for an efficient prediction of T2DM. Our approach shows an average accuracy of 96.80 % and a sensitivity of 80.09 % obtained on a holdout set.

show abstract

Data Integration and Predictive Analysis System for Disease Prophylaxis: Incorporating Dengue Fever Forecasts

Cited by 12 publications

References 11 publications

Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia

Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia

Review on Nowcasting using Least Absolute Shrinkage Selector Operator (LASSO) to Predict Dengue Occurrence in San Juan and Iquitos as Part of Disease Surveillance System

Predicting long-term Type 2 Diabetes with Support Vector Machine using Oral Glucose Tolerance Test

Contact Info

Product

Resources

About