<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=648880075207035&amp;ev=PageView&amp;noscript=1">

Webinar Recording

Predicting Injury Severity from Automatic Collision Notification Data for Triage Optimization

Recorded on February 23, 2018.

 

Webinar Materials

Abstract

It is self-evident that an automatic crash notification system can shorten the time between a vehicle accident and the arrival of first responders. Furthermore, Sánchez-Mangas et al. (2010) have estimated that a 10-minute reduction in the medical response time reduces the fatality risk of accident victims by one third.

In this webinar, we wish to explore how transmitting additional information about the nature of an accident can help dispatchers request rescue services that are adequate for the anticipated severity of injuries. For this purpose, we examine accidents recorded in NHTSA's National Automotive Sampling System (NASS), for which a wide range of accident attributes are available, including the injury severity of passengers of vehicles involved in the accidents.

As it turns out, predicting injury severity is a fairly straightforward task, which can be achieved by a wide range of modeling techniques with good overall classification performance. Much more difficult is determining the degree of confidence one should have in a forecast for a particular accident instance. Needless to say, the incorrect provisioning of rescue services is a matter of life and death.

Modeling this problem domain with Bayesian networks offers many advantages. Most importantly, Bayesian networks are inherently probabilistic, which means that any forecast is in the form of a probability distribution. If, for instance, an individual injury forecast provided an expected value of "minor injury", we would also see a value for the risk of "severe injury." Thus, services could be provisioned on the basis of the risk of a severe injury as opposed to the average of the injury forecast. This allows for a very formal approach of dealing with resource constraints related to overprovisioning and the dangers of underprovisioning.

In this context, another benefit of inference with Bayesian networks becomes apparent: Bayesian networks permit incremental inference. Despite the benefits of automatic collision notification, one would still expect missing data, redundant information, conflicting and uncertain evidence emerge from emergency situations. Bayesian networks can handle any newly-emerging information and compute an updated forecast as often as needed.

BayesiaLab Courses

December 10–12, 2019 New York, NY, USA 3-Day Introductory Course
February 5–7, 2020 Singapore 3-Day Introductory Course
February 10–12, 2020 Sydney, NSW, Australia 3-Day Introductory Course
March 3–5, 2020 Dubai, UAE 3-Day Introductory Course
March 9–11, 2020 Dubai, UAE 3-Day Advanced Course
March 24–26, 2020 Boston, MA, USA 3-Day Introductory Course
April 7–9, 2020 Paris, France 3-Day Introductory Course
May 6–8, 2020 Seattle, WA, USA 3-Day Introductory Course
May 11–13, 2020 Seattle, WA, USA 3-Day Advanced Course
June 15–17, 2020 Paris, France 3-Day Advanced Course
October 5–7, 2020 Toronto, ON, Canada 3-Day Introductory Course
October 13–15, 2020 Toronto, ON, Canada 3-Day Advanced Course

Seminars, Webinars, and Conferences

December 12, 2019
2 p.m. – 5 p.m. (EST, UTC-05)
Free Seminar in New York, NY Artificial Intelligence for Judicial Reasoning
January 21, 2020
2 p.m. – 5 p.m. (EST, UTC-05)
Free Seminar in Washington, DC Artificial Intelligence for Judicial Reasoning
January 28, 2020, 11 a.m. – 12 p.m. (CST, UTC-06) Live Webinar Bayesian Parameter Estimation for Individualized Drug Dosing
January 30, 2020
2 p.m. – 5 p.m. (CST, UTC-06)
Free Seminar in Chicago, IL Artificial Intelligence for Judicial Reasoning
Please check out our archive of recordings of previous events

8th Annual BayesiaLab Conference

October 5–7, 2020 Toronto, ON, Canada 3-Day Introductory Course
October 8–9, 2020 Toronto, ON, Canada 8th Annual BayesiaLab Conference
October 13–15, 2020 Toronto, ON, Canada 3-Day Advanced Course