Session ID: 
123

Leveraging Local Data for Public Health with “SMART Scatter

11:30am - 12:30pm Wednesday, February 13
Orlando - Orange County Convention Center
W206A

Description

A domestic violence analysis shows how using multiple data sources for an urban community in Virginia identified previously undiscovered populations at-risk to enable improved public health interventions. Based on risk factor estimates, actionable "heat maps" of high risk geographic areas for a given health issue showed patterns that were previously overlooked. Assessments of critical issues relevant to the health of a population are frequently stymied by siloed data sources at different levels of data aggregation (e.g., state/province, county, census block group, postal code, and household). These differences present challenges to communities looking to integrate multiple data sources for public health surveillance. A new open source tool—Simulated Multivariate Adaptive Regression Technique (SMART) Scatter—enables public health staff to leverage local administrative data and open source data to more accurately develop population health models.

Learning Objectives: 

  • Describe how local administrative data can inform public health policy, surveillance and intervention activities by revealing relevant community characteristics
  • Explain how research partnerships between local government, academia and industry can improve population health
  • List different geographic levels of data that may be available to understand a local population
  • Interpret what the areas of high risk on a "heat map" represent for a given health issue

Speaker(s): 

Professor,
Virginia Tech
Principal Data Scientist,
The MITRE Corporation

Audience: 

Clinical Informaticists
Population Health Management Professional
Public Health Practitioner

Level: 

Intermediate