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

1 min

Will AI undermine or support writing and critical thinking?

As artificial intelligence reshapes the way we write and think, a central question emerges: Is AI helping or hindering our ability to engage in independent, critical thought? Joshua Wilson, professor of education at the University of Delaware, investigates this topic in a new paper that examines the risks of AI dependency and discusses the need for AI literacy in education. Wilson explores how AI impacts cognitive development through writing — highlighting both the promise and peril of AI-powered tools like ChatGPT. His expertise centers on how these tools interact with foundational models of writing and learning and what that means for education, workforce readiness and civic engagement. In his new paper, Wilson warns that while AI can support higher-order thinking by automating basic writing mechanics, it also risks eroding critical thinking if students and professionals come to rely on it uncritically. He is a leading advocate for AI literacy in education – training individuals not just to use AI, but to think with it. Wilson is available for interviews with reporters, particularly those covering the intersection of AI, education and society and investigating the risks of cognitive offloading in an AI-saturated world. To reach Wilson directly, visit his profile and click on the contact button.

1 min

Fast-striking and unpredictable, tornadoes pose major challenges for emergency planners

At least 20 U.S. states have been hit with tornadoes – some of them deadly – over the past week. Experts from the University of Delaware's Disaster Research Center can speak to the difficulty of drawing up plans in advance of tornadoes, which can develop quickly and unexpectedly, as well as a variety of topics related to storm preparedness, evacuations and recovery. Those experts include: Jennifer Horney: Environmental impacts of disasters and potential public health impacts for chronic and infectious diseases. Horney, who co-authored a paper on the increase in tornado outbreaks, can talk about how impacts on the morbidity and mortality that result from tornadoes. Tricia Wachtendorf: Evacuation decision-making, disaster response and coordination, disaster relief (donations) and logistics, volunteer and emergent efforts, social vulnerability. James Kendra: Disaster response, nursing homes and hospitals, volunteers, response coordination. Jennifer Trivedi: Challenges for people with disabilities during disaster, cultural issues and long-term recovery. Sarah DeYoung: Pets in emergencies, infant feeding in disasters and decision-making in evacuation. A.R. Siders: Expert on sea level rise and managed retreat – the concept of planned community movement away from flood-prone areas. To reach these experts directly, visit their profile and click on the contact button.

+1

3 min

UD researchers launch open-source tool to boost global food security and water sustainability

Efficient water usage in agriculture is crucial for sustaining a growing human population. A better understanding of the systems that support agriculture, farmers and farmlands allows for food production to become more efficient and prosperous. That's what makes the Monthly Irrigated and Rainfed Cropped Areas Open Source (MIRCA-OS) dataset so important. MIRCA-OS offers high-resolution data on 23 crop classes — including maize, rice and wheat — and helps researchers, students and farmers examine irrigation, rainfall and croplands and how they interact with global water systems. Co-authored by Endalkachew (Endi) Kebede, a doctoral student in University of Delaware’s Department of Geography and Spatial Sciences, a recent paper focused on MIRCA-OS was published in Nature Scientific Data. Kyle Davis, assistant professor in the Department of Geography and Spatial Sciences and the Department of Plant and Soil Sciences, served as a co-author on the paper and coordinated the study. “We first developed a comprehensive data library of crop-specific irrigated and rainfed harvested areas for all countries,” Kebede said. “This involved two years of gathering data from a wide range of international, national and regional sources. Through this process, we produced a tabulated crop calendar, annual harvested area grids and monthly harvested area grids for all irrigated and rainfed crops.” “The amount of effort that Endi put in to gather, process and harmonize all of this data is truly incredible,” Davis said. “His effort is a very important contribution to the scientific and development communities.” Doctoral student Endalkachew Kebede (left) and Assistant Professor Kyle Davis. (Photo credit: University of Delaware) Cropland accounts for 13% of Earth's total habitable land, and the preservation of cropland is important in feeding the growing global population. “Crop production has been a widespread human activity for a few thousand years, and it has a huge role in global food security,” Kebede said. “But it also has unintended impacts on the environment, such as overutilization of water resources, pollution through rivers or the effects on soil and the environment.” MIRCA-OS can play a crucial role in helping to better understand croplands and agriculture, allowing the global population to be successfully fed while minimizing the agricultural effects on the environment. In addition to the data included on cropland and water resources, MIRCA-OS allows researchers to view social aspects like poverty and unemployment through an agricultural lens, creating a better understanding of the interconnectivity of agriculture and social issues. MIRCA-OS is an updated version of the earlier MIRCA2000 dataset. Kebede said the MIRCA2000 was released nearly two decades ago, so renewing the data gives users more accurate and timely information. Both datasets specialized in examining irrigation and rainfall, but the MIRCA-OS added two new complexities to their data. First, MIRCA-OS is open source, meaning it is publicly available for anyone to use, download, or modify. Kebede said the added accessibility allows the technology to contribute to anyone's work, whether it be a student, a researcher or a farmer. “Anybody can use, update it, or upscale it to the special skill they’re interested in,” Kebede said. “Some might use it for research, some might use it to create policies and some might use it to practice agriculture.” To arrange an interview with Davis, visit his profile and click on the contact button.

View all posts