Lymelight: forecasting Lyme disease risk using web search data.
Ontology highlight
ABSTRACT:
SUBMITTER: Sadilek A
PROVIDER: S-EPMC7000681 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Lymelight: forecasting Lyme disease risk using web search data.
Sadilek Adam A Hswen Yulin Y Bavadekar Shailesh S Shekel Tomer T Brownstein John S JS Gabrilovich Evgeniy E
NPJ digital medicine 20200204
Lyme disease is the most common tick-borne disease in the Northern Hemisphere. Existing estimates of Lyme disease spread are delayed a year or more. We introduce Lymelight-a new method for monitoring the incidence of Lyme disease in real-time. We use a machine-learned classifier of web search sessions to estimate the number of individuals who search for possible Lyme disease symptoms in a given geographical area for two years, 2014 and 2015. We evaluate Lymelight using the official case count da ...[more]
Similar Datasets
Project description:Accurate demand forecasting for new technology products is a key factor in the success of a business. We propose a way to forecasting a new product's diffusion through technology diffusion and interest diffusion. Technology diffusion and interest diffusion are measured by the volume of patent citations and web search traffic, respectively. We apply the proposed method to forecast the sales of hybrid cars and industrial robots in the US market. The results show that that technology diffusion, as represented by patent citations, can explain long-term sales for hybrid cars and industrial robots. On the other hand, interest diffusion, as represented by web search traffic, can help to improve the predictability of market sales of hybrid cars in the short-term. However, interest diffusion is difficult to explain the sales of industrial robots due to the different market characteristics. Finding indicates our proposed model can relatively well explain the diffusion of consumer goods.
| S-EPMC5890978 | biostudies-literature
Project description:We propose the use of Google online search data for nowcasting and forecasting the number of food stamps recipients. We perform a large out-of-sample forecasting exercise with almost 3000 competing models with forecast horizons up to 2 years ahead, and we show that models including Google search data statistically outperform the competing models at all considered horizons. These results hold also with several robustness checks, considering alternative keywords, a falsification test, different out-of-samples, directional accuracy and forecasts at the state-level.
| S-EPMC4219814 | biostudies-literature
Project description:BackgroundA 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 findingsBolivia, 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/significanceWeb 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.
| S-EPMC3104029 | biostudies-literature
Project description:[This retracts the article DOI: 10.1155/2015/462782.].
| S-EPMC5534311 | biostudies-other
Project description:BackgroundAccurate forecasting of seasonal influenza epidemics is of great concern to healthcare providers in temperate climates, as these epidemics vary substantially in their size, timing and duration from year to year, making it a challenge to deliver timely and proportionate responses. Previous studies have shown that Bayesian estimation techniques can accurately predict when an influenza epidemic will peak many weeks in advance, using existing surveillance data, but these methods must be tailored both to the target population and to the surveillance system.ObjectivesOur aim was to evaluate whether forecasts of similar accuracy could be obtained for metropolitan Melbourne (Australia).MethodsWe used the bootstrap particle filter and a mechanistic infection model to generate epidemic forecasts for metropolitan Melbourne (Australia) from weekly Internet search query surveillance data reported by Google Flu Trends for 2006-14.Results and conclusionsOptimal observation models were selected from hundreds of candidates using a novel approach that treats forecasts akin to receiver operating characteristic (ROC) curves. We show that the timing of the epidemic peak can be accurately predicted 4-6 weeks in advance, but that the magnitude of the epidemic peak and the overall burden are much harder to predict. We then discuss how the infection and observation models and the filtering process may be refined to improve forecast robustness, thereby improving the utility of these methods for healthcare decision support.
| S-EPMC4910172 | biostudies-literature
Project description:BackgroundLittle is known about risk factors for early (e.g., erythema migrans) and disseminated Lyme disease manifestations, such as arthritis, neurological complications, and carditis. No study has used both diagnoses and free text to classify Lyme disease by disease stage and manifestation.MethodsWe identified Lyme disease cases in 2012-2016 in the electronic health record (EHR) of a large, integrated health system in Pennsylvania. We developed a rule-based text-matching algorithm using regular expressions to extract clinical data from free text. Lyme disease cases were then classified by stage and manifestation using data from both diagnoses and free text. Among cases classified by stage, we evaluated individual, community, and health care variables as predictors of disseminated stage (vs. early) disease using Poisson regression models with robust errors. Final models adjusted for sociodemographic factors, receipt of Medical Assistance (i.e., Medicaid, a proxy for low socioeconomic status), primary care contact, setting of diagnosis, season of diagnosis, and urban/rural status.ResultsAmong 7310 cases of Lyme disease, we classified 62% by stage. Overall, 23% were classified using both diagnoses and text, 26% were classified using diagnoses only, and 13% were classified using text only. Among the staged diagnoses (n = 4530), 30% were disseminated stage (762 arthritis, 426 neurological manifestations, 76 carditis, 95 secondary erythema migrans, and 76 other manifestations). In adjusted models, we found that persons on Medical Assistance at least 50% of time under observation, compared to never users, had a higher risk (risk ratio [95% confidence interval]) of disseminated Lyme disease (1.20 [1.05, 1.37]). Primary care contact (0.59 [0.54, 0.64]) and diagnosis in the urgent care (0.22 [0.17, 0.29]), compared to the outpatient setting, were associated with lower risk of disseminated Lyme disease.ConclusionsThe associations between insurance payor, primary care status, and diagnostic setting with disseminated Lyme disease suggest that lower socioeconomic status and less health care access could be linked with disseminated stage Lyme disease. Intervening on these factors could reduce the individual and health care burden of disseminated Lyme disease. Our findings demonstrate the value of both diagnostic and narrative text data to identify Lyme disease manifestations in the EHR.
| S-EPMC8686252 | biostudies-literature
Project description:A set of new data types emerged from functional genomic assays, including ChIP-seq, DNase-seq, FAIRE-seq and others. The results are typically stored as genome-wide intensities (WIG/bigWig files) or functional genomic regions (peak/BED files). These data types present new challenges to big data science. Here, we present GeNemo, a web-based search engine for functional genomic data. GeNemo searches user-input data against online functional genomic datasets, including the entire collection of ENCODE and mouse ENCODE datasets. Unlike text-based search engines, GeNemo's searches are based on pattern matching of functional genomic regions. This distinguishes GeNemo from text or DNA sequence searches. The user can input any complete or partial functional genomic dataset, for example, a binding intensity file (bigWig) or a peak file. GeNemo reports any genomic regions, ranging from hundred bases to hundred thousand bases, from any of the online ENCODE datasets that share similar functional (binding, modification, accessibility) patterns. This is enabled by a Markov Chain Monte Carlo-based maximization process, executed on up to 24 parallel computing threads. By clicking on a search result, the user can visually compare her/his data with the found datasets and navigate the identified genomic regions. GeNemo is available at www.genemo.org.
| S-EPMC4987887 | biostudies-other
Project description:BackgroundAccurate influenza activity forecasting helps public health officials prepare and allocate resources for unusual influenza activity. Traditional flu surveillance systems, such as the Centers for Disease Control and Prevention's (CDC) influenza-like illnesses reports, lag behind real-time by one to 2 weeks, whereas information contained in cloud-based electronic health records (EHR) and in Internet users' search activity is typically available in near real-time. We present a method that combines the information from these two data sources with historical flu activity to produce national flu forecasts for the United States up to 4 weeks ahead of the publication of CDC's flu reports.MethodsWe extend a method originally designed to track flu using Google searches, named ARGO, to combine information from EHR and Internet searches with historical flu activities. Our regularized multivariate regression model dynamically selects the most appropriate variables for flu prediction every week. The model is assessed for the flu seasons within the time period 2013-2016 using multiple metrics including root mean squared error (RMSE).ResultsOur method reduces the RMSE of the publicly available alternative (Healthmap flutrends) method by 33, 20, 17 and 21%, for the four time horizons: real-time, one, two, and 3 weeks ahead, respectively. Such accuracy improvements are statistically significant at the 5% level. Our real-time estimates correctly identified the peak timing and magnitude of the studied flu seasons.ConclusionsOur method significantly reduces the prediction error when compared to historical publicly available Internet-based prediction systems, demonstrating that: (1) the method to combine data sources is as important as data quality; (2) effectively extracting information from a cloud-based EHR and Internet search activity leads to accurate forecast of flu.
| S-EPMC5423019 | biostudies-literature
Project description:Approximately 10% to 20% of patients optimally treated for early Lyme disease develop persistent symptoms of unknown pathophysiology termed posttreatment Lyme disease syndrome (PTLDS). The objective of this study was to investigate associations between PTLDS and immune mediator levels during acute illness and at several time points following treatment. Seventy-six participants with physician-documented erythema migrans and 26 healthy controls with no history of Lyme disease were enrolled. Sixty-four cytokines, chemokines, and inflammatory markers were measured at each visit for a total of 6 visits over 1 year. An operationalized definition of PTLDS incorporating symptoms and functional impact was applied at 6 months and 1 year following treatment completion, and clinical outcome groups were defined as the return-to-health, symptoms-only, and PTLDS groups. Significance analysis of microarrays identified 7 of the 64 immune mediators to be differentially regulated by group. Generalized logit regressions controlling for potential confounders identified posttreatment levels of the T-cell chemokine CCL19 to be independently associated with clinical outcome group. Receiver operating characteristic analysis identified a CCL19 cutoff of >111.67 pg/ml at 1 month following treatment completion to be 82% sensitive and 83% specific for later PTLDS. We speculate that persistently elevated CCL19 levels among participants with PTLDS may reflect ongoing, immune-driven reactions at sites distal to secondary lymphoid tissue. Our findings suggest the relevance of CCL19 both during acute infection and as an immunologic risk factor for PTLDS during the posttreatment phase. Identification of a potential biomarker predictor for PTLDS provides the opportunity to better understand its pathophysiology and to develop early interventions in the context of appropriate and specific clinical information.
2016-07-20 | GSE84479 | GEO
Project description:Estimation of disease prevalence at sub-city neighborhood scale allows early and targeted interventions that can help save lives and reduce public health burdens. However, the cost-prohibitive nature of highly localized data collection and sparsity of representative signals, has made it challenging to identify neighborhood scale prevalence of disease. To overcome this challenge, we utilize alternative data sources, which are both less sparse and representative of localized disease prevalence: using query data from a large commercial search engine, we identify the prevalence of respiratory illness in the United States, localized to census tract geographic granularity. Focusing on asthma and Chronic Obstructive Pulmonary Disease (COPD), we construct a set of features based on searches for symptoms, medications, and disease-related information, and use these to identify illness rates in more than 23 thousand tracts in 500 cities across the United States. Out of sample model estimates from search data alone correlate with ground truth illness rate estimates from the CDC at 0.69 to 0.76, with simple additions to these models raising those correlations to as high as 0.84. We then show that in practice search query data can be added to other relevant data such as census or land cover data to boost results, with models that incorporate all data sources correlating with ground truth data at 0.91 for asthma and 0.88 for COPD.
| S-EPMC8189491 | biostudies-literature