Injury Severity Prediction Algorithm of SUBARU Fleet Model for Advanced Automatic Collison Notification
2022-01-1005
03/29/2022
- Event
- Content
- Recently, with the evolution of telemetry technology in vehicles, Advanced Automatic Collision Notification (AACN) that detects patients at risk of serious injury in the event of an accident and transports them to the trauma center at an early stage may greatly improve the treatment of patients. An Injury Severity Prediction (ISP) algorithm for AACN was developed using a logistic regression model to predict the probability of sustaining Injury Severity Score (ISS) 15+ injury. National Automotive Sampling System Crashworthiness Data System (NASS-CDS: 1999-2015) and model year 2000 or later were filtered for new case selection criteria, which were based on vehicle body type, to match Subaru’s fleet. This proposed algorithm uses crash direction, change in velocity, multiple impacts, seat belt use, vehicle type, presence of any older occupant, presence of any female occupant, and presence of the right-sided passenger. Variable selection techniques were used to construct the final ISP algorithm with relevant features. In order to evaluate model performance, five-fold cross-validation was performed within the training data (NASS-CDS 1999-2015). Additionally, the ISP algorithm for Subaru fleet model was also externally validated using National Automotive Sampling System Crash Investigation Sampling System (NASS-CISS: 2017-2019). The area under the receiver operator characteristic curve (AUCs) was used as the metric to evaluate model performances, which was 0.86 for cross-validation and 0.82 for external validation, respectively. Delta-V, seat belt use and crash direction were important predictors of serious injury, and moreover, the right-front passenger presence is a significant injury risk modifier especially for side impact crashes.
- Citation
- Ejima, S., Goto, T., Zhang, P., Cunningham, K. et al., "Injury Severity Prediction Algorithm of SUBARU Fleet Model for Advanced Automatic Collison Notification," SAE Technical Paper 2022-01-1005, 2022, .