Using web search query data to monitor dengue epidemics: a new model for neglected tropical disease surveillance

Background

A variety of obstacles including bureaucracy and lack of resources have interfered with timely detection and reporting of dengue cases in many endemic countries. Surveillance efforts have turned to modern data sources, such as Internet search queries, which have been shown to be effective for monitoring influenza-like illnesses. However, few have evaluated the utility of web search query data for other diseases, especially those of high morbidity and mortality or where a vaccine may not exist. In this study, we aimed to assess whether web search queries are a viable data source for the early detection and monitoring of dengue epidemics.

Methodology/Principal Findings

Bolivia, Brazil, India, Indonesia and Singapore were chosen for analysis based on available data and adequate search volume. For each country, a univariate linear model was then built by fitting a time series of the fraction of Google search query volume for specific dengue-related queries from that country against a time series of official dengue case counts for a time-frame within 2003–2010. The specific combination of queries used was chosen to maximize model fit. Spurious spikes in the data were also removed prior to model fitting. The final models, fit using a training subset of the data, were cross-validated against both the overall dataset and a holdout subset of the data. All models were found to fit the data quite well, with validation correlations ranging from 0.82 to 0.99.

Conclusions/Significance

Web search query data were found to be capable of tracking dengue activity in Bolivia, Brazil, India, Indonesia and Singapore. Whereas traditional dengue data from official sources are often not available until after some substantial delay, web search query data are available in near real-time. These data represent valuable complement to assist with traditional dengue surveillance.     

Prediction of High Incidence of Dengue in the Philippines

Background

Accurate prediction of dengue incidence levels weeks in advance of an outbreak may reduce the morbidity and mortality associated with this neglected disease. Therefore, models were developed to predict high and low dengue incidence in order to provide timely forewarnings in the Philippines.

Methods

Model inputs were chosen based on studies indicating variables that may impact dengue incidence. The method first uses Fuzzy Association Rule Mining techniques to extract association rules from these historical epidemiological, environmental, and socio-economic data, as well as climate data indicating future weather patterns. Selection criteria were used to choose a subset of these rules for a classifier, thereby generating a Prediction Model. The models predicted high or low incidence of dengue in a Philippines province four weeks in advance. The threshold between high and low was determined relative to historical incidence data.

Principal Findings

Model accuracy is described by Positive Predictive Value (PPV), Negative Predictive Value (NPV), Sensitivity, and Specificity computed on test data not previously used to develop the model. Selecting a model using the F_0.5 measure, which gives PPV more importance than Sensitivity, gave these results: PPV = 0.780, NPV = 0.938, Sensitivity = 0.547, Specificity = 0.978. Using the F₃ measure, which gives Sensitivity more importance than PPV, the selected model had PPV = 0.778, NPV = 0.948, Sensitivity = 0.627, Specificity = 0.974. The decision as to which model has greater utility depends on how the predictions will be used in a particular situation.

Conclusions

This method builds prediction models for future dengue incidence in the Philippines and is capable of being modified for use in different situations; for diseases other than dengue; and for regions beyond the Philippines. The Philippines dengue prediction models predicted high or low incidence of dengue four weeks in advance of an outbreak with high accuracy, as measured by PPV, NPV, Sensitivity, and Specificity.     

Predictive Tools for Severe Dengue Conforming to World Health Organization 2009 Criteria

Background

Dengue causes 50 million infections per year, posing a large disease and economic burden in tropical and subtropical regions. Only a proportion of dengue cases require hospitalization, and predictive tools to triage dengue patients at greater risk of complications may optimize usage of limited healthcare resources. For severe dengue (SD), proposed by the World Health Organization (WHO) 2009 dengue guidelines, predictive tools are lacking.

Methods

We undertook a retrospective study of adult dengue patients in Tan Tock Seng Hospital, Singapore, from 2006 to 2008. Demographic, clinical and laboratory variables at presentation from dengue polymerase chain reaction-positive and serology-positive patients were used to predict the development of SD after hospitalization using generalized linear models (GLMs).

Principal findings

Predictive tools compatible with well-resourced and resource-limited settings – not requiring laboratory measurements – performed acceptably with optimism-corrected specificities of 29% and 27% respectively for 90% sensitivity. Higher risk of severe dengue (SD) was associated with female gender, lower than normal hematocrit level, abdominal distension, vomiting and fever on admission. Lower risk of SD was associated with more years of age (in a cohort with an interquartile range of 27–47 years of age), leucopenia and fever duration on admission. Among the warning signs proposed by WHO 2009, we found support for abdominal pain or tenderness and vomiting as predictors of combined forms of SD.

Conclusions

The application of these predictive tools in the clinical setting may reduce unnecessary admissions by 19% allowing the allocation of scarce public health resources to patients according to the severity of outcomes.     

The Effects of Vector Movement and Distribution in a Mathematical Model of Dengue Transmission

Background

Mathematical models have been used to study the dynamics of infectious disease outbreaks and predict the effectiveness of potential mass vaccination campaigns. However, models depend on simplifying assumptions to be tractable, and the consequences of making such assumptions need to be studied. Two assumptions usually incorporated by mathematical models of vector-borne disease transmission is homogeneous mixing among the hosts and vectors and homogeneous distribution of the vectors.

Methodology/Principal Findings

We explored the effects of mosquito movement and distribution in an individual-based model of dengue transmission in which humans and mosquitoes are explicitly represented in a spatial environment. We found that the limited flight range of the vector in the model greatly reduced its ability to transmit dengue among humans. A model that does not assume a limited flight range could yield similar attack rates when transmissibility of dengue was reduced by 39%. A model in which mosquitoes are distributed uniformly across locations behaves similarly to one in which the number of mosquitoes per location is drawn from an exponential distribution with a slightly higher mean number of mosquitoes per location. When the models with different assumptions were calibrated to have similar human infection attack rates, mass vaccination had nearly identical effects.

Conclusions/Significance

Small changes in assumptions in a mathematical model of dengue transmission can greatly change its behavior, but estimates of the effectiveness of mass dengue vaccination are robust to some simplifying assumptions typically made in mathematical models of vector-borne disease.     

Self-Reported Pain Intensity with the Numeric Reporting Scale in Adult Dengue

Background

Pain is a prominent feature of acute dengue as well as a clinical criterion in World Health Organization guidelines in diagnosing dengue. We conducted a prospective cohort study to compare levels of pain during acute dengue between different ethnicities and dengue severity.

Methods

Demographic, clinical and laboratory data were collected. Data on self-reported pain was collected using the 11-point Numerical Rating Scale. Generalized structural equation models were built to predict progression to severe disease.

Results

A total of 499 laboratory confirmed dengue patients were recruited in the Prospective Adult Dengue Study at Tan Tock Seng Hospital, Singapore. We found no statistically significant differences between pain score with age, gender, ethnicity or the presence of co-morbidity. Pain score was not predictive of dengue severity but highly correlated to patients’ day of illness. Prevalence of abdominal pain in our cohort was 19%. There was no difference in abdominal pain score between grades of dengue severity.

Conclusion

Dengue is a painful disease. Patients suffer more pain at the earlier phase of illness. However, pain score cannot be used to predict a patient’s progression to severe disease.     

Molecular prognostic prediction for locally advanced nasopharyngeal carcinoma by support vector machine integrated approach

Background

Accurate prognostication of locally advanced nasopharyngeal carcinoma (NPC) will benefit patients for tailored therapy. Here, we addressed this issue by developing a mathematical algorithm based on support vector machine (SVM) through integrating the expression levels of multi-biomarkers.

Methodology/Principal Findings

Ninety-seven locally advanced NPC patients in a randomized controlled trial (RCT), consisting of 48 cases serving as training set and 49 cases as testing set of SVM models, with 5-year follow-up were studied. We designed SVM models by selecting the variables from 38 tissue molecular biomarkers, which represent 6 tumorigenesis signaling pathways, and 3 EBV-related serological biomarkers. We designed 3 SVM models to refine prognosis of NPC with 5-year follow-up. The SVM1 displayed highly predictive sensitivity (sensitivity, specificity were 88.0% and 81.9%, respectively) by integrating the expression of 7 molecular biomarkers. The SVM2 model showed highly predictive specificity (sensitivity, specificity were 84.0% and 94.5%, respectively) by grouping the expression level of 12 molecular biomarkers and 3 EBV-related serological biomarkers. The SVM3 model, constructed by combination SVM1 with SVM2, displayed a high predictive capacity (sensitivity, specificity were 88.0% and 90.3%, respectively). We found that 3 SVM models had strong power in classification of prognosis. Moreover, Cox multivariate regression analysis confirmed these 3 SVM models were all the significant independent prognostic model for overall survival in testing set and overall patients.

Conclusions/Significance

Our SVM prognostic models designed in the RCT displayed strong power in refining patient prognosis for locally advanced NPC, potentially directing future target therapy against the related signaling pathways.     

Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness

Background

Dengue is re-emerging throughout the tropical world, causing frequent recurrent epidemics. The initial clinical manifestation of dengue often is confused with other febrile states confounding both clinical management and disease surveillance. Evidence-based triage strategies that identify individuals likely to be in the early stages of dengue illness can direct patient stratification for clinical investigations, management, and virological surveillance. Here we report the identification of algorithms that differentiate dengue from other febrile illnesses in the primary care setting and predict severe disease in adults.

Methods and Findings

A total of 1,200 patients presenting in the first 72 hours of acute febrile illness were recruited and followed up for up to a 4-week period prospectively; 1,012 of these were recruited from Singapore and 188 from Vietnam. Of these, 364 were dengue RT-PCR positive; 173 had dengue fever, 171 had dengue hemorrhagic fever, and 20 had dengue shock syndrome as final diagnosis. Using a C4.5 decision tree classifier for analysis of all clinical, haematological, and virological data, we obtained a diagnostic algorithm that differentiates dengue from non-dengue febrile illness with an accuracy of 84.7%. The algorithm can be used differently in different disease prevalence to yield clinically useful positive and negative predictive values. Furthermore, an algorithm using platelet count, crossover threshold value of a real-time RT-PCR for dengue viral RNA, and presence of pre-existing anti-dengue IgG antibodies in sequential order identified cases with sensitivity and specificity of 78.2% and 80.2%, respectively, that eventually developed thrombocytopenia of 50,000 platelet/mm³ or less, a level previously shown to be associated with haemorrhage and shock in adults with dengue fever.

Conclusion

This study shows a proof-of-concept that decision algorithms using simple clinical and haematological parameters can predict diagnosis and prognosis of dengue disease, a finding that could prove useful in disease management and surveillance.     

Elevated levels of cell-free circulating DNA in patients with acute dengue virus infection

Background

Apoptosis is thought to play a role in the pathogenesis of severe dengue and the release of cell-free DNA into the circulatory system in several medical conditions. Therefore, we investigated circulating DNA as a potential biomarker for severe dengue.

Methods and Findings

A direct fluorometric degradation assay using PicoGreen was performed to quantify cell-free DNA from patient plasma. Circulating DNA levels were significantly higher in patients with dengue virus infection than with other febrile illnesses and healthy controls. Remarkably, the increase of DNA levels correlated with the severity of dengue. Additionally, multivariate logistic regression analysis showed that circulating DNA levels independently correlated with dengue shock syndrome.

Conclusions

Circulating DNA levels were increased in dengue patients and correlated with dengue severity. Additional studies are required to show the benefits of this biomarker in early dengue diagnosis and for the prognosis of shock complication.     

Economic impact of dengue illness and the cost-effectiveness of future vaccination programs in Singapore

Background

Dengue illness causes 50–100 million infections worldwide and threatens 2.5 billion people in the tropical and subtropical regions. Little is known about the disease burden and economic impact of dengue in higher resourced countries or the cost-effectiveness of potential dengue vaccines in such settings.

Methods and Findings

We estimate the direct and indirect costs of dengue from hospitalized and ambulatory cases in Singapore. We consider inter alia the impacts of dengue on the economy using the human-capital and the friction cost methods. Disease burden was estimated using disability-adjusted life years (DALYs) and the cost-effectiveness of a potential vaccine program was evaluated. The average economic impact of dengue illness in Singapore from 2000 to 2009 in constant 2010 US$ ranged between $0.85 billion and $1.15 billion, of which control costs constitute 42%–59%. Using empirically derived disability weights, we estimated an annual average disease burden of 9–14 DALYs per 100 000 habitants, making it comparable to diseases such as hepatitis B or syphilis. The proportion of symptomatic dengue cases detected by the national surveillance system was estimated to be low, and to decrease with age. Under population projections by the United Nations, the price per dose threshold for which vaccines stop being more cost-effective than the current vector control program ranged from $50 for mass vaccination requiring 3 doses and only conferring 10 years of immunity to $300 for vaccination requiring 2 doses and conferring lifetime immunity. The thresholds for these vaccine programs to not be cost-effective for Singapore were $100 and $500 per dose respectively.

Conclusions

Dengue illness presents a serious economic and disease burden in Singapore. Dengue vaccines are expected to be cost-effective if reasonably low prices are adopted and will help to reduce the economic and disease burden of dengue in Singapore substantially.     

Quantifying the emergence of dengue in Hanoi, Vietnam: 1998-2009

Background

An estimated 2.4 billion people live in areas at risk of dengue transmission, therefore the factors determining the establishment of endemic dengue in areas where transmission suitability is marginal is of considerable importance. Hanoi, Vietnam is such an area, and following a large dengue outbreak in 2009, we set out to determine if dengue is emerging in Hanoi.

Methods and Principal Findings

We undertook a temporal and spatial analysis of 25,983 dengue cases notified in Hanoi between 1998 and 2009. Age standardized incidence rates, standardized age of infection, and Standardized Morbidity Ratios (SMR) were calculated. A quasi-Poisson regression model was used to determine if dengue incidence was increasing over time. Wavelet analysis was used to explore the periodicity of dengue transmission and the association with climate variables. After excluding the two major outbreak years of 1998 and 2009 and correcting for changes in population age structure, we identified a significant annual increase in the incidence of dengue cases over the period 1999–2008 (incidence rate ratio  = 1.38, 95% confidence interval  = 1.20–1.58, p value  = 0.002). The age of notified dengue cases in Hanoi is high, with a median age of 23 years (mean 26.3 years). After adjusting for changes in population age structure, there was no statistically significant change in the median or mean age of dengue cases over the period studied. Districts in the central, highly urban, area of Hanoi have the highest incidence of dengue (SMR>3).

Conclusions

Hanoi is a low dengue transmission setting where dengue incidence has been increasing year on year since 1999. This trend needs to be confirmed with serological surveys, followed by studies to determine the underlying drivers of this emergence. Such studies can provide insights into the biological, demographic, and environmental changes associated with vulnerability to the establishment of endemic dengue.     

The Role of Imported Cases and Favorable Meteorological Conditions in the Onset of Dengue Epidemics

Background

Travelers who acquire dengue infection are often routes for virus transmission to other regions. Nevertheless, the interplay between infected travelers, climate, vectors, and indigenous dengue incidence remains unclear. The role of foreign-origin cases on local dengue epidemics thus has been largely neglected by research. This study investigated the effect of both imported dengue and local meteorological factors on the occurrence of indigenous dengue in Taiwan.

Methods and Principal Findings

Using logistic and Poisson regression models, we analyzed bi-weekly, laboratory-confirmed dengue cases at their onset dates of illness from 1998 to 2007 to identify correlations between indigenous dengue and imported dengue cases (in the context of local meteorological factors) across different time lags. Our results revealed that the occurrence of indigenous dengue was significantly correlated with temporally-lagged cases of imported dengue (2–14 weeks), higher temperatures (6–14 weeks), and lower relative humidity (6–20 weeks). In addition, imported and indigenous dengue cases had a significant quantitative relationship in the onset of local epidemics. However, this relationship became less significant once indigenous epidemics progressed past the initial stage.

Conclusions

These findings imply that imported dengue cases are able to initiate indigenous epidemics when appropriate weather conditions are present. Early detection and case management of imported cases through rapid diagnosis may avert large-scale epidemics of dengue/dengue hemorrhagic fever. The deployment of an early-warning surveillance system, with the capacity to integrate meteorological data, will be an invaluable tool for successful prevention and control of dengue, particularly in non-endemic countries.     

Dengue infection in children in Ratchaburi, Thailand: a cohort study. II. Clinical manifestations

Background

Dengue infection is one of the most important mosquito-borne diseases. More data regarding the disease burden and the prevalence of each clinical spectrum among symptomatic infections and the clinical manifestations are needed. This study aims to describe the incidence and clinical manifestations of symptomatic dengue infection in Thai children during 2006 through 2008.

Study Design

This study is a school-based prospective open cohort study with a 9,448 person-year follow-up in children aged 3–14 years. Active surveillance for febrile illnesses was done in the studied subjects. Subjects who had febrile illness were asked to visit the study hospital for clinical and laboratory evaluation, treatment, and serological tests for dengue infection. The clinical data from medical records, diary cards, and data collection forms were collected and analyzed.

Results

Dengue infections were the causes of 12.1% of febrile illnesses attending the hospital, including undifferentiated fever (UF) (49.8%), dengue fever (DF) (39.3%) and dengue hemorrhagic fever (DHF) (10.9%). Headache, anorexia, nausea/vomiting and myalgia were common symptoms occurring in more than half of the patients. The more severe dengue spectrum (i.e., DHF) had higher temperature, higher prevalence of nausea/vomiting, abdominal pain, rash, diarrhea, petechiae, hepatomegaly and lower platelet count. DHF cases also had significantly higher prevalence of anorexia, nausea/vomiting and abdominal pain during day 3–6 and diarrhea during day 4–6 of illness. The absence of nausea/vomiting, abdominal pain, diarrhea, petechiae, hepatomegaly and positive tourniquet test may predict non-DHF.

Conclusion

Among symptomatic dengue infection, UF is most common followed by DF and DHF. Some clinical manifestations may be useful to predict the more severe disease (i.e., DHF). This study presents additional information in the clinical spectra of symptomatic dengue infection.     

The Effects of Weather and Climate Change on Dengue

Background

There is much uncertainty about the future impact of climate change on vector-borne diseases. Such uncertainty reflects the difficulties in modelling the complex interactions between disease, climatic and socioeconomic determinants. We used a comprehensive panel dataset from Mexico covering 23 years of province-specific dengue reports across nine climatic regions to estimate the impact of weather on dengue, accounting for the effects of non-climatic factors.

Methods and Findings

Using a Generalized Additive Model, we estimated statistically significant effects of weather and access to piped water on dengue. The effects of weather were highly nonlinear. Minimum temperature (Tmin) had almost no effect on dengue incidence below 5°C, but Tmin values above 18°C showed a rapidly increasing effect. Maximum temperature above 20°C also showed an increasing effect on dengue incidence with a peak around 32°C, after which the effect declined. There is also an increasing effect of precipitation as it rose to about 550 mm, beyond which such effect declines. Rising access to piped water was related to increasing dengue incidence. We used our model estimations to project the potential impact of climate change on dengue incidence under three emission scenarios by 2030, 2050, and 2080. An increase of up to 40% in dengue incidence by 2080 was estimated under climate change while holding the other driving factors constant.

Conclusions

Our results indicate that weather significantly influences dengue incidence in Mexico and that such relationships are highly nonlinear. These findings highlight the importance of using flexible model specifications when analysing weather–health interactions. Climate change may contribute to an increase in dengue incidence. Rising access to piped water may aggravate dengue incidence if it leads to increased domestic water storage. Climate change may therefore influence the success or failure of future efforts against dengue.     

Optimal Lead Time for Dengue Forecast

Background

A dengue early warning system aims to prevent a dengue outbreak by providing an accurate prediction of a rise in dengue cases and sufficient time to allow timely decisions and preventive measures to be taken by local authorities. This study seeks to identify the optimal lead time for warning of dengue cases in Singapore given the duration required by a local authority to curb an outbreak.

Methodology and Findings

We developed a Poisson regression model to analyze relative risks of dengue cases as functions of weekly mean temperature and cumulative rainfall with lag times of 1–5 months using spline functions. We examined the duration of vector control and cluster management in dengue clusters > = 10 cases from 2000 to 2010 and used the information as an indicative window of the time required to mitigate an outbreak. Finally, we assessed the gap between forecast and successful control to determine the optimal timing for issuing an early warning in the study area. Our findings show that increasing weekly mean temperature and cumulative rainfall precede risks of increasing dengue cases by 4–20 and 8–20 weeks, respectively. These lag times provided a forecast window of 1–5 months based on the observed weather data. Based on previous vector control operations, the time needed to curb dengue outbreaks ranged from 1–3 months with a median duration of 2 months. Thus, a dengue early warning forecast given 3 months ahead of the onset of a probable epidemic would give local authorities sufficient time to mitigate an outbreak.

Conclusions

Optimal timing of a dengue forecast increases the functional value of an early warning system and enhances cost-effectiveness of vector control operations in response to forecasted risks. We emphasize the importance of considering the forecast-mitigation gaps in respective study areas when developing a dengue forecasting model.     

The Prevalence and Endemic Nature of Dengue Infections in Guangdong,South China: An Epidemiological,Serological, and Etiological Study from 2005–2011

Objectives

Frequent outbreaks of dengue are considered to be associated with an increased risk for endemicity of the disease. The occurrence of a large number of indigenous dengue cases in consecutive years indicates the possibility of a changing dengue epidemic pattern in Guangdong, China.

Methods

To have a clear understanding of the current dengue epidemic, a retrospective study of epidemiological profile, serological response, and virological features of dengue infections from 2005–2011 was conducted. Case data were collected from the National Notifiable Infectious Diseases Reporting Network. Serum samples were collected and prepared for serological verification and etiological confirmation. Incidence, temporal and spatial distribution, and the clinical manifestation of dengue infections were analyzed. Pearson''s Chi-Square test was used to compare incidences between different age groups. A seroprevalence survey was implemented in local healthy inhabitants to obtain the overall positive rate for the specific immunoglobulin (Ig) G antibody against dengue virus (DENV).

Results

The overall annual incidence rate was 1.87/100000. A significant difference was found in age-specific incidence (Pearson''s Chi-Square value 498.008, P<0.001). Children under 5 years of age had the lowest incidence of 0.28/100000. The vast majority of cases presented with a mild manifestation typical to dengue fever. The overall seroprevalence of dengue IgG antibody in local populations was 2.43% (range 0.28%–5.42%). DENV-1 was the predominant serotype in circulation through the years, while all 4 serotypes were identified in indigenous patients from different outbreak localities since 2009.

Conclusions

A gradual change in the epidemic pattern of dengue infection has been observed in recent years in Guangdong. With the endemic nature of dengue infections, the transition from a monotypic to a multitypic circulation of dengue virus in the last several years will have an important bearing on the prevention and control of dengue in the province and in the neighboring districts.     

The Application of the Grey Disaster Model to Forecast Epidemic Peaks of Typhoid and Paratyphoid Fever in China

Objective

The objectives of this study were to forecast epidemic peaks of typhoid and paratyphoid fever in China using the grey disaster model, to evaluate its feasibility of predicting the epidemic tendency of notifiable diseases.

Methods

According to epidemiological features, the GM(1,1) model and DGM model were used to build the grey disaster model based on the incidence data of typhoid and paratyphoid fever collected from the China Health Statistical Yearbook. Model fitting accuracy test was used to evaluate the performance of these two models. Then, the next catastrophe date was predicted by the better model.

Results

The simulation results showed that DGM model was better than GM(1,1) model in our data set. Using the DGM model, we predicted the next epidemic peak time will occur between 2023 to 2025.

Conclusion

The grey disaster model can predict the typhoid and paratyphoid fever epidemic time precisely, which may provide valuable information for disease prevention and control.     

Classification of Dengue Fever Patients Based on Gene Expression Data Using Support Vector Machines

Background

Symptomatic infection by dengue virus (DENV) can range from dengue fever (DF) to dengue haemorrhagic fever (DHF), however, the determinants of DF or DHF progression are not completely understood. It is hypothesised that host innate immune response factors are involved in modulating the disease outcome and the expression levels of genes involved in this response could be used as early prognostic markers for disease severity.

Methodology/Principal Findings

mRNA expression levels of genes involved in DENV innate immune responses were measured using quantitative real time PCR (qPCR). Here, we present a novel application of the support vector machines (SVM) algorithm to analyze the expression pattern of 12 genes in peripheral blood mononuclear cells (PBMCs) of 28 dengue patients (13 DHF and 15 DF) during acute viral infection. The SVM model was trained using gene expression data of these genes and achieved the highest accuracy of ∼85% with leave-one-out cross-validation. Through selective removal of gene expression data from the SVM model, we have identified seven genes (MYD88, TLR7, TLR3, MDA5, IRF3, IFN-α and CLEC5A) that may be central in differentiating DF patients from DHF, with MYD88 and TLR7 observed to be the most important. Though the individual removal of expression data of five other genes had no impact on the overall accuracy, a significant combined role was observed when the SVM model of the two main genes (MYD88 and TLR7) was re-trained to include the five genes, increasing the overall accuracy to ∼96%.

Conclusions/Significance

Here, we present a novel use of the SVM algorithm to classify DF and DHF patients, as well as to elucidate the significance of the various genes involved. It was observed that seven genes are critical in classifying DF and DHF patients: TLR3, MDA5, IRF3, IFN-α, CLEC5A, and the two most important MYD88 and TLR7. While these preliminary results are promising, further experimental investigation is necessary to validate their specific roles in dengue disease.     

Comparisons of Prediction Models of Quality of Life after Laparoscopic Cholecystectomy: A Longitudinal Prospective Study

Background

Few studies of laparoscopic cholecystectomy (LC) outcome have used longitudinal data for more than two years. Moreover, no studies have considered group differences in factors other than outcome such as age and nonsurgical treatment. Additionally, almost all published articles agree that the essential issue of the internal validity (reproducibility) of the artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR) and multiple linear regression (MLR) models has not been adequately addressed. This study proposed to validate the use of these models for predicting quality of life (QOL) after LC and to compare the predictive capability of ANNs with that of SVM, GPR and MLR.

Methodology/Principal Findings

A total of 400 LC patients completed the SF-36 and the Gastrointestinal Quality of Life Index at baseline and at 2 years postoperatively. The criteria for evaluating the accuracy of the system models were mean square error (MSE) and mean absolute percentage error (MAPE). A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the variables in order of importance. Compared to SVM, GPR and MLR models, the ANN model generally had smaller MSE and MAPE values in the training data set and test data set. Most ANN models had MAPE values ranging from 4.20% to 8.60%, and most had high prediction accuracy. The global sensitivity analysis also showed that preoperative functional status was the best parameter for predicting QOL after LC.

Conclusions/Significance

Compared with SVM, GPR and MLR models, the ANN model in this study was more accurate in predicting patient-reported QOL and had higher overall performance indices. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.     

Search Query Data to Monitor Interest in Behavior Change: Application for Public Health

There is a need for effective interventions and policies that target the leading preventable causes of death in the U.S. (e.g., smoking, overweight/obesity, physical inactivity). Such efforts could be aided by the use of publicly available, real-time search query data that illustrate times and locations of high and low public interest in behaviors related to preventable causes of death.

Objectives

This study explored patterns of search query activity for the terms ‘weight’, ‘diet’, ‘fitness’, and ‘smoking’ using Google Insights for Search.

Methods

Search activity for ‘weight’, ‘diet’, ‘fitness’, and ‘smoking’ conducted within the United States via Google between January 4^th, 2004 (first date data was available) and November 28^th, 2011 (date of data download and analysis) were analyzed. Using a generalized linear model, we explored the effects of time (month) on mean relative search volume for all four terms.

Results

Models suggest a significant effect of month on mean search volume for all four terms. Search activity for all four terms was highest in January with observable declines throughout the remainder of the year.

Conclusions

These findings demonstrate discernable temporal patterns of search activity for four areas of behavior change. These findings could be used to inform the timing, location and messaging of interventions, campaigns and policies targeting these behaviors.