Improving Syndromic Surveillance by Data Integration

Boston University Medical Campus, Boston MA

Investigators

Linked publications & trials

Abstract

The term "syndromic surveillance" is a generic term applied to a variety of newly developed methods in[unreadable] public health practice. For our purposes, syndromic surveillance refers to the automated collection and[unreadable] analysis in near-real-time of electronic health outcome data. Used in this way, syndromic surveillance sits[unreadable] within a broader category of "biosurveillance", the routine collection and analysis of electronic data falling[unreadable] outside of the classical surveillance paradigm.[unreadable] We propose a research program to improve the performance of aberration detection methods for syndromic[unreadable] surveillance using statistical methods of data integration. Our program focuses on three main areas of[unreadable] potential improvement: temporal modeling, spatio-temporal clustering, and integration of multiple data[unreadable] streams. We also include a research translation component, in order to ensure that the results of research[unreadable] will be of practical use to health departments and other practitioners of syndromic surveillance.[unreadable] Our three specific aims are: 1) To develop and improve temporal modeling for syndromic surveillance, using[unreadable] improved seasonal models and Hidden Markov Models (HMMs); 2) To investigate and evaluate data[unreadable] integration methods, including spatio-temporal clustering and multiple data source integration; 3) To develop[unreadable] PHIN-compliant software for use by local health departments and syndromic surveillance practitioners.