Related Experiment Video
Updated: Apr 12, 2026
07:30
A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact
Published on: September 21, 2017
9.5K
On scene injury severity prediction (OSISP) algorithm for car occupants
Ruben Buendia1, Stefan Candefjord1, Helen Fagerlind2
1Department of Signals and Systems, Chalmers University of Technology, 412 96 Gothenburg, Sweden; SAFER Vehicle and Traffic Safety Centre at Chalmers, Sweden; MedTech West, Sahlgrenska University Hospital, Röda Stråket 10 B, 413 45 Gothenburg, Sweden.
Accident; Analysis and Prevention
|May 26, 2015
Summary
Accident characteristics like seatbelt use and crash type can predict injury severity in traffic accidents. This can improve early medical care and reduce undertriage for crash victims.
Area of Science:
- Trauma research
- Road safety
- Emergency medicine
Background:
- Optimal trauma care is hindered by delayed recognition of injury severity.
- Current triage protocols rely on physiological, anatomical, and injury mechanism criteria.
- Accurate field triage is crucial to minimize undertriage of severely injured traffic accident victims.
Purpose of the Study:
- To evaluate the utility of accident characteristics for field triage.
- To develop an on-scene injury severity prediction (OSISP) algorithm using readily available accident data.
- To enhance early identification of severely injured individuals in traffic accidents.
Main Methods:
- A multivariate logistic regression model was developed using the Swedish Traffic Accident Data Acquisition (STRADA) database (2003-2013).
- The model predicted severe injury (Injury Severity Score [ISS] > 8 or > 15) based on accident characteristics.
- Data included 29,128 adult occupants from 22,607 accidents, with variables like belt use, airbag deployment, speed limit, accident type, location, age, sex, and seat position.
Main Results:
- The OSISP algorithm achieved an Area Under the Curve (AUC) of 0.78 for ISS>8 and 0.83 for ISS>15.
- Seatbelt use was the strongest predictor of injury severity, followed by accident type.
- Posted speed limit, occupant age, and accident location significantly improved prediction accuracy.
Conclusions:
- Accident characteristics are valuable predictors of injury severity in traffic crashes.
- The developed OSISP algorithm can refine existing field triage protocols.
- Findings have implications for improving trauma care in Sweden and similar traffic environments.
