Advanced Automatic Collision Notification Research Report

Lee, E.; Wu, J.; Enriquez, J.; Martin, J.; Craig, M. · 2019 · ROSA P / United States. Department of Transportation. National Highway Traffic Safety Administration

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

This report by the National Highway Traffic Safety Administration (NHTSA) evaluates the safety potential, technical considerations, and testing procedures for post-crash notification technologies, specifically Automatic Collision Notification (ACN) and Advanced Automatic Collision Notification (AACN). ACN systems automatically transmit vehicle location and identification data to emergency services upon crash detection, while AACN systems add injury severity prediction to guide triage decisions, such as transporting patients directly to trauma centers. The research was motivated by the need to quantify the lives potentially saved by these technologies and to assess the efficacy of current injury prediction algorithms, particularly given that voluntary adoption rates remain low in the U.S. despite mandatory implementation in the European Union. The study utilized multiple datasets, including the Fatality Analysis Reporting System (FARS) and the National Automotive Sampling System-Crashworthiness Data System (NASS-CDS), to analyze survival rates and develop predictive models. Researchers employed Kaplan-Meier survival analysis and Cox Proportional Hazard models to determine the impact of EMS response time and treatment facility type on occupant survival. Additionally, the authors developed a logistic regression model using CDS data from 1999–2015 to evaluate injury prediction algorithms. This model used predictors such as delta-V, seat belt usage, direction of force, and vehicle body type to estimate the probability of severe injury (defined as an Injury Severity Score of 16 or greater). The performance of these algorithms was assessed against American College of Surgeons (ACS) guidelines for undertriage and overtriage rates. Key findings indicate that faster notification significantly improves survival outcomes. Analysis of FARS data showed that notification within two minutes increased survival rates by 2%, potentially saving 177–244 lives annually. Furthermore, transport to a trauma center rather than a non-trauma hospital was associated with a 24% reduction in mortality. However, the study found that current injury prediction thresholds recommended by the CDC (20% risk threshold) are insufficiently sensitive, resulting in high undertriage rates where severely injured occupants are not identified. The NHTSA-developed logistic regression model demonstrated that lowering the risk threshold to approximately 1–2% could achieve sensitivity rates closer to ACS recommendations, though this would increase overtriage. The report also confirmed the feasibility of developing repeatable test procedures for AACN systems by detecting communication signals without accessing proprietary data contents. The significance of this research lies in its demonstration that AACN technologies offer substantial safety benefits beyond basic ACN, primarily through improved triage and faster EMS response. The findings suggest that to maximize lives saved, AACN systems must employ more sensitive injury prediction algorithms than currently recommended. The report provides a technical foundation for future regulatory considerations and system development, highlighting that while post-crash technologies have the potential to enhance light vehicle safety, optimizing algorithm sensitivity is critical to ensuring severely injured occupants receive appropriate care.

Key finding

Lowering the AACN injury prediction risk threshold from the CDC-recommended 20% to approximately 1-2% significantly increases sensitivity for identifying severely injured occupants, reducing under-triage from 74% to near 5-10%, although this increase in sensitivity also raises the over-triage rate above American College of Surgeons recommendations.

Methodology

dataset

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• post crash care delays
• telematics crash prediction
• incidence prevalence
• adas effectiveness
• naturalistic crash near crash

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: crash risk outcomes