Surveillance Sans Frontières: Internet-based emerging infectious disease intelligence and the HealthMap project.

Children's Hospital Informatics Program at the Harvard-MIT Division of Health Sciences and Technology, Boston, Massachusetts, United States of America.
PLoS Medicine (Impact Factor: 14). 08/2008; 5(7):e151. DOI: 10.1371/journal.pmed.0050151
Source: PubMed

ABSTRACT John Brownstein and colleagues discuss HealthMap, an automated real-time system that monitors and disseminates online information about emerging infectious diseases.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Developed under the Intelligence Advanced Research Project Activity Open Source Indicators program, Early Model Based Event Recognition using Surrogates (EMBERS) is a large-scale big data analytics system for forecasting significant societal events, such as civil unrest events on the basis of continuous, automated analysis of large volumes of publicly available data. It has been operational since November 2012 and delivers approximately 50 predictions each day for countries of Latin America. EMBERS is built on a streaming, scalable, loosely coupled, shared-nothing architecture using ZeroMQ as its messaging backbone and JSON as its wire data format. It is deployed on Amazon Web Services using an entirely automated deployment process. We describe the architecture of the system, some of the design tradeoffs encountered during development, and specifics of the machine learning models underlying EMBERS. We also present a detailed prospective evaluation of EMBERS in forecasting significant societal events in the past 2 years.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: It is generally difficult to estimate disease prevalence or true infection probabilities because these are not observable quantities. However, these parameters can be estimated from available data sources that can provide partial indications of the true incidence of infected cases or prevalence rates. However, building a construct capable of incorporating data from these various sources in a coherent manner is not trivial. In addition, the prevalence of an infectious strain must be estimated in a timely manner. For instance, in an epidemic, this estimate must be obtained within a day or so. We propose to use dynamic Bayesian networks from the class of probabilistic graphical models in order to identify probabilistic relationships between different data streams. This is an initial step towards building a framework that can support data integration and real-time estimation of disease prevalence. Our preliminary results on data sources related to H1N1 pandemic show that the proposed models generalize well.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Electronic event-based biosurveillance systems (EEBS's) that use near real-time information from the internet are an increasingly important source of epidemiologic intelligence. However, there has not been a systematic assessment of EEBS evaluations, which could identify key uncertainties about current systems and guide EEBS development to most effectively exploit web-based information for biosurveillance. To conduct this assessment, we searched PubMed and Google Scholar to identify peer-reviewed evaluations of EEBS's. We included EEBS's that use publicly available internet information sources, cover events that are relevant to human health, and have global scope. To assess the publications using a common framework, we constructed a list of 17 EEBS attributes from published guidelines for evaluating health surveillance systems. We identified 11 EEBS's and 20 evaluations of these EEBS's. The number of published evaluations per EEBS ranged from 1 (Gen-Db, GODsN, MiTAP) to 8 (GPHIN, HealthMap). The median number of evaluation variables assessed per EEBS was 8 (range, 3-15). Ten published evaluations contained quantitative assessments of at least one key variable. No evaluations examined usefulness by identifying specific public health decisions, actions, or outcomes resulting from EEBS outputs. Future EEBS assessments should identify and discuss critical indicators of public health utility, especially the impact of EEBS's on public health response.
    PLoS ONE 10/2014; 9(10):e111222. DOI:10.1371/journal.pone.0111222 · 3.53 Impact Factor

Full-text (3 Sources)

Available from
May 16, 2014