Semantic Web Technology For Public Health Surveillance

Semantic Web Technology for Public Health syndromic surveillance, environmental protection, Situation Awareness environmental epidemiology, biosecurity and bioterrorism preparedness, veterinary surveillance, Public health surveillance is the ongoing collection etc.), or as a bird’s eye view to the community and analysis of data to identify and respond to health, for decision and policy purposes. Recently community health problems in a timely manner. we have made significant steps in integrating Frequently, important public health information is biomedical information (e.g. gene expression, distributed among many disparate databases, and proteomics and genomics) in order to project and includes far more than just clinical data. Infectious, identify potential population effects of indicators gastrointestinal or respiratory illnesses may be found in basic science research (translational detected by monitoring emergency room visits, biomedicine). water contaminations and air quality. Also, some helpful correlative data may exist online (e.g. If a new situation arises, SAPPHIRE can be pollens and allergens). As of now, meaningful modeled to dynamically absorb new data feeds, integration of all these disparate data to inform make new interpretations and produce new results public health practice has been the major barrier to accordingly. This dynamic instantiation and their use in public health surveillance systems. configuration of services was demonstrated during hurricane Katrina, when SAPPHIRE was extended As the Semantic Web provides a suite of to accommodate data from a just-in-time PDA technology to enable information representation based questionnaire, a clinical information system and computer reasoning, we have been able to from Katrina shelters and surveillance reports automate many of the most challenging, resource captured by the Houston Department of Health, and intensive and cumbersome aspects of information to support signal detection and reporting on integration in such a way that the system learns diseases and syndromes defined by field from the data itself as to how they should or would epidemiologists. SAPPHIRE was the sole be integrated with other data. surveillance technology to address these needs Using Semantic Web technology, we have within eight hours of the shelters opening, using integrated unstructured text such as doctors’ notes, Internet and Semantic Web technology. and patient complaints into structured electronic medical records. This has enabled retrieval of all information together and through a unified query interface, regardless of how (structured, unstructured) and where (text files, database tables, spreadsheets, etc.) the data is stored. It has not only enabled us to integrate and utilize any relevant dataset regardless of source, structure and format, but has also made it possible to contextualize their use for a variety of different SAPPHIRE Ontology Driven Architecture tasks, by developing abstractions and models on Key Benefits: top of integrated data (called an ontology). For example: we have created models for identifying Use of Semantic Web technology has enabled the Influenza-Like-Illnesses, Neurological, Center for Biosecurity and Public Health Informatics Gastrointestinal and other categories of patients (or Research at the University of Texas Health Science outbreaks), and models for identifying respiratory Center at Houston to design a system architecture distress patients (and outbreaks) based on multi- with the following features: source data collected from 18 different air quality  Distributed collaboration and interoperability: sampling devices and data feeds from 16 clinical disparate and heterogeneous data can be information systems. This enables real-time exchanged, integrated and utilized seamlessly monitoring and notification of Ozone related asthma and dynamically between remote systems. and other respiratory distresses.  Dynamic adaptability: new requirements, data, As a result, our prototype system, code named functions and tasks can be introduced to the SAPPHIRE (Situation Awareness and system without major rewrite or reprogramming Preparedness for Public Health Incidents using to address novel situations or new tasks. Reasoning Engines), is the only instance of an  Multidisciplinary reuse of information: existing Integrated Biosurveillance System where all data in the system can be repurposed to surveillance activities are enabled through a address unprecedented use cases. distributed and collaborative system. SAPPHIRE absorbs data from multiple disparate sources and Human computer interaction: systems interact puts them together as pieces of a larger puzzle that intelligently with human users and more effectively, can be viewed from many different perspectives intuitively and easily (traditional notifiable disease surveillance,