Study Confirms Value of OnStar’s Injury Prediction
Emergency response agencies can use the additional information to fine-tune how they dispatch first responders to the scene of a crash.
by Staff
June 11, 2015
OnStar’s “injury severity prediction” (ISP) service analyzes crash data, such as force of impact, to determine the probability of severe injury to the vehicle occupants. OnStar advisors then relay the ISP rating to 9-1-1 centers. Photo courtesy of GM.
3 min to read
OnStar’s “injury severity prediction” (ISP) service analyzes crash data, such as force of impact, to determine the probability of severe injury to the vehicle occupants. OnStar advisors then relay the ISP rating to 9-1-1 centers. Photo courtesy of GM.
OnStar’s “injury severity prediction” service is accurately predicting the severity of crash victims’ injuries, fostering better on-scene treatment, a new study has found.
Injury severity prediction (ISP) is an algorithm that OnStar uses in properly equipped Chevrolet, Buick, GMC and Cadillac vehicles in the U.S. and Canada to provide additional information to first responders following a vehicle crash. The algorithm analyzes crash information, such as force of impact and direction of impact, to determine the probability of severe injury to the vehicle occupants. OnStar advisors then relay the ISP rating to 9-1-1 centers, which may choose to adjust the level and priority of response dispatched to a crash scene.
Ad Loading...
“This past April we added injury severity prediction criteria to our trauma transport protocols,” said Cory Richter, battalion chief for Indian River County (Fla.) Fire Rescue. “It has been proven that crash victims with a severe injury have a better chance of survival when they’re transported to a trauma center instead of a local hospital. Resources like OnStar’s Injury Severity Prediction give us a better chance of identifying those victims early on.”
Over the past four years, General Motors, OnStar and the University of Michigan’s International Center for Automotive Medicine (ICAM) have studied how crash data can assist first responders. Dr. Stewart Wang has led the ICAM team. This was the first known study to match real-life injury outcomes with crash telemetry data.
“Only a subset of all people who have been involved in a crash require the most urgent attention,” Wang said. “This subset consists of those individuals who have sustained serious, life- or limb-threatening injuries. With this data, we are able to much more accurately predict which people might be in this critical subset so that the proper resources can be deployed to rescue them and transport them to the right level of care.”
As part of the research for each crash incident, Wang and his team matched each ISP rating with the corresponding police report, medical records, EMS data and computerized tomography (CT) scan data. The goal was to see if the predicted injury rating accurately matched the occupants’ confirmed injuries.
(The study’s data include no personal information that compromises medical confidentiality; injured occupants remain anonymous.)
Ad Loading...
This study confirmed that under real-world field conditions, occupant injury severity can be predicted using vehicle data.
“This service enables first responders to better treat injuries today, and in the long run, it will allow us to prevent certain injuries from occurring,” said Jeff Boyer, vice president of GM global vehicle safety. “With access to this information, our engineers can analyze today’s safety systems to identify those features most effective in preventing severe injuries in the future.”
Now that the algorithm for predicting severe injuries has been validated, the next step is educating the emergency response community so it can adjust training and protocols, OnStar said.
Recently, the National Highway Traffic Safety Administration (NHTSA), in conjunction with the American College of Emergency Physicians (ACEP) and National Association of EMS Physicians (NAEMSP), awarded a grant to develop online training to familiarize first responders and medical directors with crash data and the associated injury severity prediction. Pilot programs will be held in early summer.
Taking input from the pilot sessions, the training will be adjusted and rolled out to all first responders in the fall.
Ad Loading...
OnStar injury severity prediction is part of OnStar’s automatic crash response service, available as part of the OnStar protection, security and guidance plans. OnStar responds to more than 5,000 vehicle crashes every month. OnStar emergency advisors are certified by the International Academies of Emergency Dispatch, allowing them to provide medical guidance to vehicle occupants while they wait for first responders.
OnStar is a wholly owned subsidiary of GM Holdings.
Distracted driving remains one of the most persistent risks in fleet operations. New approaches focus on removing mobile device use entirely while adding real-time safety support.
As distraction risks evolve, fleets are turning to smarter, more connected technologies to better understand what’s happening behind the wheel. Part 2 explores how these tools are helping identify risky behaviors and improve visibility across operations.
Distracted driving is often measured by what we can see—phones in hand, eyes off the road. But what about the distractions we can’t? A recent incident raises a bigger question about awareness, attention, and why subtle risks so often go unnoticed.
Fleets have more driver data than ever, so why isn't behavior changing? Training requires more than reports and coaching — it requires real-world practice.
A two-part conversation with Stefan Heck on how AI is transforming the fight against distracted driving. As fleets adopt smarter tools, the focus shifts from reacting to preventing risk. In Part 1, we look at where AI is making an impact for fleets today.
An 11% drop in pedestrian fatalities in early 2025 signals progress in U.S. road safety, but elevated death rates and ongoing risks underscore the need for continued action from fleets and policymakers.
