Influence of injury risk thresholds on the performance of an algorithm to predict crashes with serious injuries

George Bahouth, Kennerly Digges, Carl I Schulman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

This paper presents methods to estimate crash injury risk based on crash characteristics captured by some passenger vehicles equipped with Advanced Automatic Crash Notification technology. The resulting injury risk estimates could be used within an algorithm to optimize rescue care. Regression analysis was applied to the National Automotive Sampling System / Crashworthiness Data System (NASS/CDS) to determine how variations in a specific injury risk threshold would influence the accuracy of predicting crashes with serious injuries. The recommended thresholds for classifying crashes with severe injuries are 0.10 for frontal crashes and 0.05 for side crashes. The regression analysis of NASS/CDS indicates that these thresholds will provide sensitivity above 0.67 while maintaining a positive predictive value in the range of 0.20.

Original languageEnglish (US)
Title of host publicationAnnals of Advances in Automotive Medicine
Pages223-230
Number of pages8
Volume56
StatePublished - 2012
Event56th Annual Scientific Conference of the Association for the Advancement of Automotive Medicine - Seattle, WA, United States
Duration: Oct 14 2012Oct 17 2012

Other

Other56th Annual Scientific Conference of the Association for the Advancement of Automotive Medicine
CountryUnited States
CitySeattle, WA
Period10/14/1210/17/12

Fingerprint

Crashworthiness
Regression analysis
Wounds and Injuries
Sampling
Information Systems
Regression Analysis
Technology

ASJC Scopus subject areas

  • Automotive Engineering
  • Biomedical Engineering
  • Safety, Risk, Reliability and Quality
  • Medicine(all)

Cite this

Bahouth, G., Digges, K., & Schulman, C. I. (2012). Influence of injury risk thresholds on the performance of an algorithm to predict crashes with serious injuries. In Annals of Advances in Automotive Medicine (Vol. 56, pp. 223-230)

Influence of injury risk thresholds on the performance of an algorithm to predict crashes with serious injuries. / Bahouth, George; Digges, Kennerly; Schulman, Carl I.

Annals of Advances in Automotive Medicine. Vol. 56 2012. p. 223-230.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bahouth, G, Digges, K & Schulman, CI 2012, Influence of injury risk thresholds on the performance of an algorithm to predict crashes with serious injuries. in Annals of Advances in Automotive Medicine. vol. 56, pp. 223-230, 56th Annual Scientific Conference of the Association for the Advancement of Automotive Medicine, Seattle, WA, United States, 10/14/12.
Bahouth G, Digges K, Schulman CI. Influence of injury risk thresholds on the performance of an algorithm to predict crashes with serious injuries. In Annals of Advances in Automotive Medicine. Vol. 56. 2012. p. 223-230
Bahouth, George ; Digges, Kennerly ; Schulman, Carl I. / Influence of injury risk thresholds on the performance of an algorithm to predict crashes with serious injuries. Annals of Advances in Automotive Medicine. Vol. 56 2012. pp. 223-230
@inproceedings{8bf7214639ee459595ffc0f6109905ce,
title = "Influence of injury risk thresholds on the performance of an algorithm to predict crashes with serious injuries",
abstract = "This paper presents methods to estimate crash injury risk based on crash characteristics captured by some passenger vehicles equipped with Advanced Automatic Crash Notification technology. The resulting injury risk estimates could be used within an algorithm to optimize rescue care. Regression analysis was applied to the National Automotive Sampling System / Crashworthiness Data System (NASS/CDS) to determine how variations in a specific injury risk threshold would influence the accuracy of predicting crashes with serious injuries. The recommended thresholds for classifying crashes with severe injuries are 0.10 for frontal crashes and 0.05 for side crashes. The regression analysis of NASS/CDS indicates that these thresholds will provide sensitivity above 0.67 while maintaining a positive predictive value in the range of 0.20.",
author = "George Bahouth and Kennerly Digges and Schulman, {Carl I}",
year = "2012",
language = "English (US)",
volume = "56",
pages = "223--230",
booktitle = "Annals of Advances in Automotive Medicine",

}

TY - GEN

T1 - Influence of injury risk thresholds on the performance of an algorithm to predict crashes with serious injuries

AU - Bahouth, George

AU - Digges, Kennerly

AU - Schulman, Carl I

PY - 2012

Y1 - 2012

N2 - This paper presents methods to estimate crash injury risk based on crash characteristics captured by some passenger vehicles equipped with Advanced Automatic Crash Notification technology. The resulting injury risk estimates could be used within an algorithm to optimize rescue care. Regression analysis was applied to the National Automotive Sampling System / Crashworthiness Data System (NASS/CDS) to determine how variations in a specific injury risk threshold would influence the accuracy of predicting crashes with serious injuries. The recommended thresholds for classifying crashes with severe injuries are 0.10 for frontal crashes and 0.05 for side crashes. The regression analysis of NASS/CDS indicates that these thresholds will provide sensitivity above 0.67 while maintaining a positive predictive value in the range of 0.20.

AB - This paper presents methods to estimate crash injury risk based on crash characteristics captured by some passenger vehicles equipped with Advanced Automatic Crash Notification technology. The resulting injury risk estimates could be used within an algorithm to optimize rescue care. Regression analysis was applied to the National Automotive Sampling System / Crashworthiness Data System (NASS/CDS) to determine how variations in a specific injury risk threshold would influence the accuracy of predicting crashes with serious injuries. The recommended thresholds for classifying crashes with severe injuries are 0.10 for frontal crashes and 0.05 for side crashes. The regression analysis of NASS/CDS indicates that these thresholds will provide sensitivity above 0.67 while maintaining a positive predictive value in the range of 0.20.

UR - http://www.scopus.com/inward/record.url?scp=84876708220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876708220&partnerID=8YFLogxK

M3 - Conference contribution

C2 - 23169132

AN - SCOPUS:84876708220

VL - 56

SP - 223

EP - 230

BT - Annals of Advances in Automotive Medicine

ER -