Dataset Information

Adaptive nowcasting of influenza outbreaks using Google searches.

ABSTRACT: Seasonal influenza outbreaks and pandemics of new strains of the influenza virus affect humans around the globe. However, traditional systems for measuring the spread of flu infections deliver results with one or two weeks delay. Recent research suggests that data on queries made to the search engine Google can be used to address this problem, providing real-time estimates of levels of influenza-like illness in a population. Others have however argued that equally good estimates of current flu levels can be forecast using historic flu measurements. Here, we build dynamic 'nowcasting' models; in other words, forecasting models that estimate current levels of influenza, before the release of official data one week later. We find that when using Google Flu Trends data in combination with historic flu levels, the mean absolute error (MAE) of in-sample 'nowcasts' can be significantly reduced by 14.4%, compared with a baseline model that uses historic data on flu levels only. We further demonstrate that the MAE of out-of-sample nowcasts can also be significantly reduced by between 16.0% and 52.7%, depending on the length of the sliding training interval. We conclude that, using adaptive models, Google Flu Trends data can indeed be used to improve real-time influenza monitoring, even when official reports of flu infections are available with only one week's delay.

SUBMITTER: Preis T

PROVIDER: S-EPMC4448892 | biostudies-literature | 2014 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Adaptive nowcasting of influenza outbreaks using Google searches.

Preis Tobias T Moat Helen Susannah HS

Royal Society open science 20141029 2

Seasonal influenza outbreaks and pandemics of new strains of the influenza virus affect humans around the globe. However, traditional systems for measuring the spread of flu infections deliver results with one or two weeks delay. Recent research suggests that data on queries made to the search engine Google can be used to address this problem, providing real-time estimates of levels of influenza-like illness in a population. Others have however argued that equally good estimates of current flu l ...[more]

PMID: 26064532

Similar Datasets

Project description:BackgroundSexually transmitted infections (STIs) pose a significant public health challenge in the United States. Traditional surveillance systems are adversely affected by data quality issues, underreporting of cases, and reporting delays, resulting in missed prevention opportunities to respond to trends in disease prevalence. Search engine data can potentially facilitate an efficient and economical enhancement to surveillance reporting systems established for STIs.ObjectiveWe aimed to develop and train a predictive model using reported STI case data from Chicago, Illinois, and to investigate the model's predictive capacity, timeliness, and ability to target interventions to subpopulations using Google Trends data.MethodsDeidentified STI case data for chlamydia, gonorrhea, and primary and secondary syphilis from 2011-2017 were obtained from the Chicago Department of Public Health. The data set included race/ethnicity, age, and birth sex. Google Correlate was used to identify the top 100 correlated search terms with "STD symptoms," and an autocrawler was established using Google Health Application Programming Interface to collect the search volume for each term. Elastic net regression was used to evaluate prediction accuracy, and cross-correlation analysis was used to identify timeliness of prediction. Subgroup elastic net regression analysis was performed for race, sex, and age.ResultsFor gonorrhea and chlamydia, actual and predicted STI values correlated moderately in 2011 (chlamydia: r=0.65; gonorrhea: r=0.72) but correlated highly (chlamydia: r=0.90; gonorrhea: r=0.94) from 2012 to 2017. However, for primary and secondary syphilis, the high correlation was observed only for 2012 (r=0.79), 2013 (r=0.77), 2016 (0.80), and 2017 (r=0.84), with 2011, 2014, and 2015 showing moderate correlations (r=0.55-0.70). Model performance was the most accurate (highest correlation and lowest mean absolute error) for gonorrhea. Subgroup analyses improved model fit across disease and year. Regression models using search terms selected from the cross-correlation analysis improved the prediction accuracy and timeliness across diseases and years.ConclusionsIntegrating nowcasting with Google Trends in surveillance activities can potentially enhance the prediction and timeliness of outbreak detection and response as well as target interventions to subpopulations. Future studies should prospectively examine the utility of Google Trends applied to STI surveillance and response.

Project description:PurposeEpidemic and seasonal infectious conjunctivitis outbreaks can impact education, workforce, and economy adversely. Yet conjunctivitis typically is not a reportable disease, potentially delaying mitigating intervention. Our study objective was to determine if conjunctivitis epidemics could be identified using Google Trends search data.DesignSearch data for conjunctivitis-related and control search terms from 5 years and countries worldwide were obtained. Country and term were masked. Temporal scan statistics were applied to identify candidate epidemics. Candidates then were assessed for geotemporal concordance with an a priori defined collection of known reported conjunctivitis outbreaks, as a measure of sensitivity.ParticipantsPopulations by country that searched Google's search engine using our study terms.Main outcome measuresPercent of known conjunctivitis outbreaks also found in the same country and period by our candidate epidemics, identified from conjunctivitis-related searches.ResultsWe identified 135 candidate conjunctivitis epidemic periods from 77 countries. Compared with our a priori defined collection of known reported outbreaks, candidate conjunctivitis epidemics identified 18 of 26 (69% sensitivity) of the reported country-wide or island nationwide outbreaks, or both; 9 of 20 (45% sensitivity) of the reported region or district-wide outbreaks, or both; but far fewer nosocomial and reported smaller outbreaks. Similar overall and individual sensitivity, as well as specificity, were found on a country-level basis. We also found that 83% of our candidate epidemics had start dates before (of those, 20% were more than 12 weeks before) their concurrent reported outbreak's report issuance date. Permutation tests provided evidence that on average, conjunctivitis candidate epidemics occurred geotemporally closer to outbreak reports than chance alone suggests (P < 0.001) unlike control term candidates (P = 0.40).ConclusionsConjunctivitis outbreaks can be detected using temporal scan analysis of Google search data alone, with more than 80% detected before an outbreak report's issuance date, some as early as the reported outbreak's start date. Future approaches using data from smaller regions, social media, and more search terms may improve sensitivity further and cross-validate detected candidates, allowing identification of candidate conjunctivitis epidemics from Internet search data potentially to complementarily benefit traditional reporting and detection systems to improve epidemic awareness.

Project description:BackgroundColorectal cancer (CRC) is the third most prevalent and second most lethal form of cancer in the world. Consequently, CRC cancer prevalence projections are essential for assessing the future burden of the disease, planning resource allocation, and developing service delivery strategies, as well as for grasping the shifting environment of cancer risk factors. However, unlike cancer incidence and mortality rates, national and international agencies do not routinely issue projections for cancer prevalence. Moreover, the limited or even nonexistent cancer statistics for large portions of the world, along with the high heterogeneity among world nations, further complicate the task of producing timely and accurate CRC prevalence projections. In this situation, population interest, as shown by Internet searches, can be very important for improving cancer statistics and, in the long run, for helping cancer research.MethodsThis study aims to model, nowcast and forecast the CRC prevalence at the global level using a three-step framework that incorporates three well-established univariate statistical and machine-learning models. First, data mining is performed to evaluate the relevancy of Google Trends (GT) data as a surrogate for the number of CRC survivors. The results demonstrate that population web-search interest in the term "colonoscopy" is the most reliable indicator to nowcast CRC disease prevalence. Then, various statistical and machine-learning models, including ARIMA, ETS, and FNNAR, are trained and tested using relevant GT time series. Finally, the updated monthly query series spanning 2004-2022 and the best forecasting model in terms of out-of-sample forecasting ability (i.e., the neural network autoregression) are utilized to generate point forecasts up to 2025.ResultsResults show that the number of people with colorectal cancer will continue to rise over the next 24 months. This in turn emphasizes the urgency for public policies aimed at reducing the population's exposure to the principal modifiable risk factors, such as lifestyle and nutrition. In addition, given the major drop in population interest in CRC during the first wave of the COVID-19 pandemic, the findings suggest that public health authorities should implement measures to increase cancer screening rates during pandemics. This in turn would deliver positive externalities, including the mitigation of the global burden and the enhancement of the quality of official statistics.

Dataset Information

Adaptive nowcasting of influenza outbreaks using Google searches.

Publications

Adaptive nowcasting of influenza outbreaks using Google searches.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets