New research has found that driving skills measured on a virtual driving assessment (VDA) at the time a teen receives their license aids in predicting crash risk.

“The VDA is designed to take drivers through a variety of low to high risk, uniquely realistic virtual driving scenarios that can determine where skills are weakest,” said study co-author, Michael Elliott, PhD, a professor of Biostatistics at the University of Michigan School of Public Health and research professor at the Institute for Social Research at U-M. “The driving behaviors are tracked in real time using several dozen measures.”

This study, published by Pediatrics and conducted by the Center for Injury Research and Prevention (CIRP) at Children’s Hospital of Philadelphia (CHOP) in conjunction with the University of Pennsylvania and the University of Michigan, highlights how personalized interventions can be developed to improve teen driving skills in order to prevent crashes.

“We know young novice drivers are at higher risk of crashing than more experienced drivers,” Elliott said. “The novel VDA tool uses information about their behaviors, such as virtual braking, accelerating, steering and crashing. That risk profile has now been shown to be predictive of their crash behavior during their first couple of years on the road. What’s crucial to note is that most of these behaviors are amenable with additional driving training.”

Though drivers between the ages of 15-20 make up just 5 percent of all drivers on the road, they are involved in an estimated 12 percent of all vehicle crashes and 8.5 percent of fatal crashes, the study found.

The greatest crash risk is in the months right after teens become licensed drivers.

“The challenge for policymakers, clinicians and families has been identifying which drivers are at increased risk of crashing during the learning phase before they drive on their own,” the article noted.

During the past twenty years, CIRP researchers have determined the primary reason for crashes involving new drivers—inadequate driving skills, like speed management.

The development of the self-guided VDA which measures driving skills in common serious crash scenarios utilizes the Ready-Assess platform developed by Diagnostic Driving, Inc., an AI-driven virtual driving assessment that provides drivers with insights and tools to improve their driving skills.

The study examined the ability of the VDA to predict crash risk in the first year after teens obtained their Ohio state drivers license. The results of the VDA were linked to police-reported crash records for the first year after obtaining a license.

“Our previous research showed that performance on the VDA predicted actual on-road driving performance, as measured by failure on the licensing road test. This new study went further to determine whether VDA performance could identify unsafe driving performance predictive of future crash risk,” said lead study author Elizabeth Walshe, PhD, a cognitive neuroscientist and clinical researcher who directs the Neuroscience of Driving team at CIRP. “We found that drivers categorized by their performance as having major issues with dangerous behavior were at higher risk of crashing than average new drivers.”

The researchers analyzed police-reported crash records in 16,914 first-time newly licensed drivers under the age of 25. The data was collected from teen applicants who completed the VDA between July 2017 and December 2019 on the day they passed the on-road licensing examination in Ohio. Researchers examined crash records up to mid-March 2020.

With the outcome of time-to-first crash after licensure, a Cox proportional hazard model was used to estimate the risk of crash as a function of VDA performance, the researchers explained.

The study found that the best performing novice drivers, described as having “No Issues” based on their pattern of driving performance on the VDA, had a 10 percent lower than average crash risk. However, users of the VDA who had “Major Issues with Dangerous Behavior” had an 11 percent higher than average crash risk.

The results remained stable when adjusting for a variety of variables such as age, sex, and socio-economic status.

“These findings are incredibly important because they provide us with quantitative evidence that we can approach young driver safety in a new way – by predicting crash risk and aiming resources to those who need them most,” said Flaura Winston, MD, PhD, co-scientific director of CIRP at CHOP and co-author of the study. “By providing this information before licensure, we can direct resources to those most at risk, and potentially prevent crashes from occurring when these teens first drive on their own.”

Dr. Winston is an inventor of a VDA. CHOP has licensed this VDA technology to Diagnostic Driving, for use on its Ready-Assess™ platform. Dr. Winston also has an ownership interest in Diagnostic Driving.