Data Analytics

We describe an automated system that can detect multiple outbreaks of infectious diseases from emergency department reports. A case detection system obtains data from electronic medical records, extracts features using natural language processing, then infers a probability distribution over the diseases each patient may have. Then, a multiple outbreak detection system (MODS) searches for models of multiple outbreaks to explain the data. MODS detects outbreaks of influenza and non-influenza influenza-like illnesses (NI-ILI).

Timely monitoring and prediction of the trajectory of seasonal influenza epidemics allows hospitals and medical centers to prepare for, and provide better service to, patients with influenza. The CDC’s ILINet system collects data on influenza-like illnesses from over 3,300 health care providers, and uses this data to produce accurate indicators of current influenza epidemic severity. However, ILINet indicators are typically reported at a lag of 1-2 weeks. Another source of severity data, Google Flu Trends, is calculated by aggregating Google searches for certain influenza related terms. Google Flu Trends data is provided in near-real time, but is a less direct measurement of severity than ILINet indicators, and is likely to suffer from bias. We create a hierarchical model to estimate epidemic severity for the 2014 - 2015 epidemic season which incorporates current and historical data from both ILINet and Google Flu Trends, allowing our model to benefit both from the recency of Google Flu Trends data and the accuracy of ILINet data.

Objective

To use multiple data sources of influenza epidemic severity to inform a model which can estimate and forecast severity for the current influenza epidemic season by accounting for the bias from each source.

Stillbirth remained a neglected issue absent from mention in Millennium Development Goals. An estimated 2.6 million babies are stillborn every year with highest rate in Pakistan, 43.1 stillbirths/1000 births. There is lack of good quality prospective population based data in Pakistan regarding burden, timing and causes of stillbirths.

Objective

To determine burden, timing and causes of stillbirths in a prospective cohort of pregnant from a low income community setting in peri urban Karachi

NBIC collects, analyzes, and shares key biosurveillance information to support the nation’s response to biological events of concern. Integration of this information enables early warning and shared situational awareness to inform critical decision making, and direct response and recovery efforts.

DTRA J9 CB leads DoD S&T to anticipate, defend, and safeguard against chemical and biological threats for the warfighter and the nation.

These agencies have partnered to meet the evolving needs of the biosurveillance community and address gaps in technology and data sharing capabilities. High-profile events such as the 2009 H1N1 pandemic, the West African Ebola outbreak, and the recent emergence of Zika virus disease have underscored the need for integration of disparate biosurveillance systems to provide a more functional infrastructure. This allows analysts and others in the community to collect, analyze, and share relevant data across organizations securely and efficiently. Leveraging existing biosurveillance efforts provides the federal public health community, and its partners, with a comprehensive interagency platform that enables engagement and data sharing. 

Objective

The National Biosurveillance Integration Center (NBIC) and the Defense Threat Reduction Agency’s Chemical and Biological Technologies Department (DTRA J9 CB) have partnered to co- develop the Biosurveillance Ecosystem (BSVE), an emerging capability that aims to provide a virtual, customizable analyst workbench that integrates health and non-health data. This partnership promotes engagement between diverse health surveillance entities to increase awareness and improve decision-making capabilities. 

To develop a spatially accurate biosurveillance synthetic data generator for the testing, evaluation, and comparison of new outbreak detection techniques.