Model-based application of abbreviated injury scale to police-reported crash injuries

Andrew P. Tarko, Hillel Bar-Gera, Jose Thomaz, Apichai Issariyanukula

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


The evaluation of crash severities and the estimation of crash costs are key elements in evidence-based traffic safety improvement programs. Police records include information on injury severity estimated at the scene either by a police officer or by a medical emergency unit. At a hospital, the accident injuries are examined and documented more thoroughly and thus provide a better basis for cost estimation. Using hospital injury data for priority ranking of transportation projects and in other decision-making processes requires linking medical and crash records. Unfortunately, only a modest portion of crash records can be linked to corresponding medical records, even if a person is hospitalized, because missing data hamper the linking process. This study proposes a new method to overcome these difficulties and to estimate the expected level of injury of individuals included in all police-reported crashes. This method is accomplished by developing statistical models based on the linked medical and crash records and by applying these models to the entire crash data set. A fundamental problem to overcome was the selectivity bias present in the linked data and caused by the injury criteria for directing individuals to hospitals. The concept and the development of the proposed method are presented. The method is illustrated with its components developed with Indiana linked data and applied to Indiana crash data for 2005 to 2006.

Original languageEnglish
Pages (from-to)59-68
Number of pages10
JournalTransportation Research Record
Issue number2148
StatePublished - 12 Jan 2010

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering


Dive into the research topics of 'Model-based application of abbreviated injury scale to police-reported crash injuries'. Together they form a unique fingerprint.

Cite this