Holodniy Mark

Many methods to detect outbreaks currently exist, although most are ineffective in the face of real data, resulting in high false positivity. More complicated methods have better precision, but can be difficult to interpret and justify. Praedico™ is a next generation biosurveillance application built on top of a Hadoop High Performance Cluster that incorporates multiple syndromic surveillance methods of alerting, and a machine-learning (ML) model using a decision tree classifier  evaluating over 100 different signals simultaneously, within a user friendly interface.

Objective

To compare syndromic surveillance alerting in VA using Praedico™ and ESSENCE.

The Joint Incentive Fund (JIF) Authorization creates innovative DoD/VA sharing initiatives. In 2009, DoD and VA commenced a biosurveillance JIF project whose principle objectives include improved situational awareness of combined VA/ DoD populations 1 and determining the optimal business model allowing both agency biosurveillance programs to operate more efficiently by: 1) consolidating information technology assets; 2) targeting enhanced collaboration for improved public health outcomes; and 3) improving buying power, and return on investment. We analyzed various interoperability models aimed at biosurveillance data sharing, asset consolidation and enhanced collaboration. Potential end states to be evaluated include maintaining separate Departmental systems, bidirectional exchange of data to separately managed systems, consolidation of data within one Department and shared access to a common system, consolidation of data in a neutral repository accessed by separately run legacy systems, or a custom developed biosurveillance solution utilizing a common data repository.

Objective

Determine an optimal course of action for achieving a more mission and cost-effective model for implementing combined or collaborative biosurveillance across the Departments of Veterans Affairs (VA) and Defense (DoD).

It is estimated that in the United States (US), unintentional non-fire related CO poisoning causes an average of 439 deaths annually, and in 2007 confirmed CO poisoning cases resulted in 21,304 ED visits and 2,302 hospitalizations (71 per million and 8 per million population, respectively)1 . Despite the significant risk of morbidity and mortality associated with CO poisoning, existing surveillance systems in the United States are limited. This study is the first to focus specifically on CO poisoning trends within the VHA population.

Objective

To describe characteristics of Veterans Health Administration (VHA) patients with ICD 9/10 CM inpatient discharge and/or emergency department (ED)/urgent care outpatient encounter codes for carbon monoxide (CO) poisoning.

Firearm violence is an issue of public health concern leading to more than 30,000 deaths and 80,000 nonfatal injuries in the United States annually. To date, firearm-related studies among Veterans have focused primarily on suicide and attempted suicide. Herein, we examine firearm violence among VHA enrollees for all manners/ intents, including assault, unintentional, self-inflicted, undetermined and other firearm-related injury encounters in both the inpatient and outpatient settings.