AI-powered model predicts post-concussion injury risk in college athletes

Apr 16, 2025

3 min


Athletes who suffer a concussion have a serious risk of reinjury after returning to play, but identifying which athletes are most vulnerable has always been a bit of a mystery, until now.


Using artificial intelligence (AI), University of Delaware researchers have developed a novel machine learning model that predicts an athlete’s risk of lower-extremity musculoskeletal (MKS) injury after concussion with 95% accuracy. A recent study published in Sports Medicine details the development of the AI model, which builds on previously published research showing that the risk of post-concussion injury doubles, regardless of the sport. The most common post-concussive injuries include sprains, strains, or even broken bones or torn ACLs.


“This is due to brain changes we see post-concussion,” said Thomas Buckley, professor of kinesiology and applied physiology at the College of Health Sciences.


These brain changes affect athletes’ balance, cognition, and reaction times and can be difficult to detect in standard clinical testing.


“Even a minuscule difference in balance, reaction time, or cognitive processing of what’s happening around you can make the difference between getting hurt and not,” Buckley said.


How AI is changing injury risk assessment


Recognizing the need for enhanced injury reduction risk tools, Buckley collaborated with colleagues in UD’s College of Engineering, Austin Brockmeier, assistant professor of electrical and computer engineering, and César Claros, a fourth-year doctoral student; Wei Qian, associate professor of statistics in the College of Agriculture and Natural Resources; and former KAAP postdoctoral fellow Melissa Anderson, who’s now an assistant professor at Ohio University. To assess injury risk, Brockmeier and Claros developed a comprehensive AI model that analyzes more than 100 variables, including sports and medical histories, concussion type, and pre- and post-concussion cognitive data.


“Every athlete is unique, especially across various sports,” said Brockmeier. “Tracking an athlete’s performance over time, rather than relying on absolute values, helps identify disturbances, deviations, or deficits that, when compared to their baseline, may signal an increased risk of injury.”


While some sports, such as football, carry higher injury risk, the model revealed that individual factors are just as important as the sport played.


“We tested a version of the model that doesn’t have access to the athlete’s sport, and it still accurately predicted injury risk,” Brockmeier said. “This highlights how unique characteristics—not just the inherent risks of a sport—play a critical role in determining the likelihood of future injury,” said Brockmeier.


The research, which tracked athletes over two years, also found that the risk of MSK injury post-concussion extends well into the athlete’s return to play.


“Common sense would suggest that injuries would occur early in an athlete’s return to play, but that’s simply not true,” said Buckley. “Our research shows that the risk of future injury increases over time as athletes compensate and adapt to small deficits they may not even be aware of.”


The next step for Buckey’s Concussion Research Lab is to further collaborate with UD Athletics’ strength and conditioning staff to design real-time interventions that could reduce injury risk.


Beyond sports: AI’s potential in aging research


The implications of the UD-developed machine-learning model extend far beyond sports. Brockmeier believes the algorithm could be used to predict fall risk in patients with Parkinson’s disease.


Claros is also exploring how the injury risk reduction model can be applied to aging research with the Delaware Center for Cognitive Aging.


“We want to use brain measurements to investigate whether baseline lifestyle measurements such as weight, BMI, and smoking history are predictive of future mild cognitive impairment or Alzheimer’s disease,” said Claros.


To arrange an interview with Buckley, email UD's media relations team at MediaRelations@udel.edu

You might also like...

Check out some other posts from University of Delaware

2 min

Aging in context: Why culture matters in discussions on menopause

How do we age? Why do we age? And why are experiences of menopause and midlife so different across cultures? These are the driving questions behind the work of Melissa Melby, a medical anthropologist and professor at the University of Delaware. For more than 25 years, Melby has been exploring how biology and culture intersect to shape the way people experience aging and menopause. Her new book, Reframing Aging: Insights from Biology and Culture of Midlife Japanese, introduces a biocultural framework that goes beyond the “what” of aging to ask both how (the immediate mechanisms) and why (the deeper evolutionary reasons) we age and experience menopause the way we do. By weaving together insights from evolutionary biology, anthropology, medicine and lived experience, Melby challenges what many consider to be the “normal” path of midlife. Her research highlights how cultural expectations, medical practices, social structures and lifestyle habits can profoundly influence not just how symptoms are treated – but how they are perceived in the first place. What may be pathologized in one society could be understood as a natural stage of life in another. As conversations around women’s health, longevity and healthy aging gain overdue attention, Melby’s cross-disciplinary expertise offers journalists a fresh lens for exploring some of the most universal – and misunderstood – aspects of human life. For stories that bridge science, culture and health, Melby provides a rare perspective: one that reframes aging and menopause not as fixed biological destinies, but as experiences shaped by the complex interplay of our bodies, histories, and communities. Reporters interested in speaking to Melby can email mediarelations@udel.edu.

2 min

Study finds widespread duplication of local television news

Viewers of "local" TV news in nearly 40% of markets nationwide are hearing the exact same thing found on a competitor’s channel, according to a new study co-authored by the University of Delaware's Danilo Yanich. This widespread word-for-word duplication could have major implications on local journalism and newscasts, which are a source of critical information for millions of Americans. Yanich and fellow UD researcher Benjamin E. Bagozzi analyzed three months of local TV news broadcasts from 861 stations nationwide — more than 400,000 programs in all. Using a high bar for what counts as duplication (at least half of the content being word-for-word identical, excluding sports, weather and ads), they found widespread story sharing. Other findings: In many cases, two stations in the same city aired nearly identical newscasts night after night. • Duplication is driven by service agreements and the gobbling up of stations by groups such as Nexstar, Gray, News-Press and Gazette and Sinclair. • Stations with service agreements had duplication rates twice as high as those that were simply co-owned. • Smaller markets were more likely to have these overlaps. In some cases, two stations in the same city aired nearly identical newscasts night after night. • The duplication usually happened within the same geographic market (86% of cases) rather than between different regions. On average, these station pairs had identical content 65% of the time. • Local TV remains America’s most trusted news source. Over three-quarters of Americans say they trust it more than newspapers, radio or online news. “In any other context, this would be plagiarism,” said Yanich, noting that he and Bagozzi intentionally examined stations over 91 days to cover a body of content large enough to provide meaningful results. The study’s authors stress that while consolidation may make financial sense for station owners, it raises important questions about the future of local journalism. If more and more markets see their “local” stations airing the same news, communities may lose the independent voices that help keep citizens informed and hold local leaders accountable. To reach Yanich directly and arrange an interview, visit his profile and click on the "contact" button. Email MediaRelations@udel.edu to set up an interview with Bagozzi.

2 min

University of Delaware secures $13.1M grant to transform Alzheimer’s research and prevention

A new five-year $13.1 million grant will greatly expand the ability of University of Delaware researchers to pursue ways to prevent and treat Alzheimer's disease. The gift from the Delaware Community Foundation (DCF) is one of the largest in state history for Alzheimer’s research. UD's Christopher Martens called the grant "transformational," as it will support the expansion of a statewide prevention study, enable the purchase of a state-of-the-art MRI machine and drive discovery of new diagnostic tools and treatments. “It will also help grow the number of researchers in Delaware focused on Alzheimer’s disease, promoting an interdisciplinary approach." said Martens, director of UD's Delaware Center for Cognitive Aging Research (DECCAR) and professor of kinesiology and applied physiology in the College of Health Sciences. Bringing together researchers from multiple fields to collaborate on a critical challenge like Alzheimer’s disease is a key strength of the University of Delaware, said Interim President Laura Carlson. “Every one of us has a family member or friend who has been deeply affected by Alzheimer’s. I’m proud that UD is working better to understand this terrible disease and partnering with others throughout the state to work on its prevention, diagnosis and treatment,” Carlson said. “We are grateful to the Delaware Community Foundation for their support, which allows us to escalate our research and expand our community outreach.” “No one has to look very far afield to witness and understand the tragedy of Alzheimer’s, and the research supported by this grant will help UD researchers come ever-closer to uncovering life-improving and life-saving solutions,” said Stuart Comstock-Gay, President and CEO of the Delaware Community Foundation (DCF). “The grant was provided through the generosity of late Paul H. Boerger, who made a substantial legacy gift to the fund he had established at the DCF in his lifetime, and his foresight will help so many.” The gift is aimed at achieving the following goals: • Tracking Alzheimer’s risk over time – Expanding Delaware’s largest study of brain aging from 100 to 500 participants to uncover who develops dementia and why. • A simple blood test for early detection – Developing a first-of-its-kind test that could diagnose Alzheimer’s years earlier than current methods. • Cutting-edge brain imaging – Installing a $3.2 million MRI machine on UD’s STAR Campus to reveal hidden brain changes linked to memory loss. • Spotting the earliest warning signs – Exploring how subtle shifts in language and menopause-related hormone changes may predict Alzheimer’s risk. • Fueling prevention and cures – Creating powerful data and tools that will accelerate new treatments and bring researchers closer to stopping Alzheimer’s. To reach Martens for an interview, visit his profile and click on the "contact" button. Interviews with DCF officials can be arranged by emailing MediaRelations@udel.edu.

View all posts