Bayes Hack 2016 |
Department of Transportation Brief.

How can data stop accidents before they happen?

The Federal Highway Administration (FHWA) has developed a Freight Analysis Framework that shows historical freight movement estimates.1 No organization has ever used government permit data or related indicators to develp models that can project future increases in freight traffic.

By creating models from empirical data, we can reduce casualties due to crashes and other safety incidents among all transportation users and minimize risks due to the transportation of hazardous materials. Models could predict which areas are likely to see increased transportation of oil and liquid natural gas leverage existing liquid natural gas (LNG) and oil development models to predict future transportation safety risks or anticipate development and transportation of oil and natural gas in a way that hasn't yet been explored.



How can data help us heal communities at high risk for suicide?

A person or vehicle is hit by a train about once every three hours.2 This results in approximately 700 deaths per year, by accident and by suicide.

By creating descriptive models that examine empiric data on train fatalities and predictive models that can anticipate accidents and suicide attempts, we can decrease the number of deaths that occur and focus on communities that are at disproportinately high risk. Good data can be a focus national efforts to heal areas impacted by suicide, and to promote smart planning and routing to prevent accidents.



How can data optimize emergency services?

In 2014 there were more than 6 million traffic crashes in the United States, resulting in 32,675 deaths and 2.3 million injuries. Based on incident and traffic conditions, emergency responders have a number of options for transportation (including helicopter ambulance transport in lieu of ground ambulance). There aren't standardized methods or technologies designed for emergency medical services personnel to predict and optimize transport times by selecting the right response to every incident.

Can rich EMS response data coupled with incident state—including weather conditions, road and traffic conditions, and hospital locations—be used to develop a real-time tool for paramedics and dispatchers?



Resources

Transportation of hazardous materials:

Suicide prevention:

Emergency services:

  • The Bayes Impact starter kit, an exploration of this prompt's key datasets.
  • 2014 National EMS Dataset: coordinating download logistics. Will be available before event.
  • State of Illinois EMS Dataset: ditto.
  • The American Trauma Society hosts a comprehensive index of trauma centers in the United States that incorporates service information.
  • The National Highway Traffic Safety Administration's National Center for Statistics and Analysis open data portal with troves of high-level statistics. They also run the Fatality Analysis Reporting System, which can be queried year-by-year for individual traffic accident conditions and outcomes.
  • HIFLD geospatial data on emergency services jurisdictions. Of particular interest for this prompt are State Emergency Operations Centers (EOCs). Esri ArcGIS comin' through in the clutch!
  1. FHWA Freight Analysis Framework

  2. Operation Lifesaver