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

Powered by

You might also like...

Check out some other posts from University of Delaware

Survey says: Senior leaders are using AI, but they could use more direction featured image

4 min

Survey says: Senior leaders are using AI, but they could use more direction

Over the years, study upon study has shown that senior leaders are slower to adapt to new technology – email, the Internet and social media – than younger employees. That’s not necessarily so with AI, according to the University of Delaware’s Saleem Mistry. Mistry, associate professor of management at UD's Alfred Lerner College of Business & Economics, recently conducted a survey of more than 200 university alumni, 75% of which had more than 16 years of professional experience. He found that senior leaders are actively adopting AI to solve their biggest challenges. However, they are doing so largely without structured support or guidance. Here are four findings from Mistry's survey that shows how AI is actually being used at the top. Senior Leaders Are Overwhelmingly Self-Taught Mistry said his most glaring finding is the gap between high AI adoption among senior leaders and the near-total absence of formal corporate support. Although a majority use these tools, they are almost entirely self-taught, which highlights visible opportunity that organizations aren’t really steering the AI conversation for leaders: • High usage. 62% of all senior leaders surveyed use AI tools "regularly" or "occasionally" in their work. • Training gap. Of those users, an overwhelming 80% report their organization provides "Never" or only "Sometimes" (mostly never) adequate training. Mistry said this shows that leaders from VP level down are using tools like ChatGPT and Copilot informally to keep up with heavy workloads, without any real organizational guidance. The stakes are high. In the survey, a vice president of legal was using AI for compliance tasks and a manager of three was using it for performance reviews, both with no formal training. “These are senior leaders handling sensitive work while essentially figuring it out on their own,” Mistry said. There is a clear ladder of AI use Leaders are not using AI randomly. There is a clear progression in how they use it, moving through three levels. • Tier 1 (The Drafters) This is the most common starting point. Leaders use AI to improve writing and communication. They draft emails, shape documents, and refine tone. As one Director of Product put it, it helps him "polish phrasing" and adjust tone and voice. • Tier 2 (The Synthesizers) At this stage, leaders use AI to manage information overload. They summarize meetings, condense documents, and pull together research so they can keep up with large volumes of input. As one leader managing a team of 200 said, "Being a leader requires attention in a variety of areas. AI helps me manage the vast amounts of information I need to consume." • Tier 3 (The Architects) Here, leaders move beyond writing and summarizing. They use AI to automate parts of their work. This includes building agents, creating custom GPTs, or designing tools that track work and performance. One leader managing 300 people said, "It will eliminate half or more of my overhead." Managers and individual contributors use AI for different reasons People managers and individual contributors (IC) are using AI for very different reasons based on their roles. • For people managers, their main challenge is scale. They are overloaded with communication and administration, so they use AI to reduce noise and keep up. They lean heavily on summarization and tone adjustment tools. • For project leads and ICs, their focus is output. They use AI to produce work faster, including drafting content, building decks, writing code, or generating ideas. This difference reflects their jobs. One group is trying to keep up, the other is trying to produce more. It also shows that AI is not a single-use tool. Its value depends on the problem it is being used to solve. This difference reflects their jobs. One group is trying to keep up, the other is trying to produce more. It also shows that AI is not a single-use tool. Its value depends on the problem it is being used to solve. Resistance to AI is mostly intentional Among the 38 percent of leaders who do not use AI, resistance is usually not based on lack of awareness. It falls into three groups: • The Ethical Objectors. Some avoid AI due to concerns about its broader impact. • The Quality Skeptics. Some do not trust the output and feel it is not reliable enough for important work. • The Blocked. Some are not allowed to use AI due to company policy. Mistry concludes that there is a clear overall pattern: Leaders are using AI in practical ways, but mostly without structured support or guidance. “If it feels like you are figuring this out as you go without much help from your organization, that is consistent with what most leaders are experiencing,” Mistry said. To connect directly with Mistry and arrange an interview, visit his profile page and click on the "connect" button. Interested reporters can also email MediaRelations@udel.edu.

UD experts break down the 2026 World Cup featured image

2 min

UD experts break down the 2026 World Cup

As the world gears up for the 2026 FIFA World Cup, experts from the University of Delaware are available to provide timely insight on the science, business, and human impact behind the global tournament. Player Safety, Concussions and the Future of the Game Tom Kaminski, professor of kinesiology and applied physiology, is a leading authority on player safety and head injuries. As the sole U.S. representative on FIFA’s Heading Expert Group, Kaminski is helping shape international guidelines around heading in soccer—particularly for youth athletes. He can speak to concussion risks, prevention strategies, and how evolving safety standards are influencing the modern game. Joining him is Tom Buckley, who also specializes in concussion research and athlete health, offering additional perspective on injury trends and recovery in elite competition. The Business of the World Cup: Tourism and Global Impact Matt Robinson from UD’s Lerner College of Business and Economics explores how mega-events like the World Cup drive tourism, economic growth, and global connection. Robinson can discuss how host cities benefit, the long-term economic ripple effects, and how sports act as a powerful unifier across cultures. Youth, Development and the Next Generation of Fans Sara Goldstein brings expertise in adolescent development, offering insight into how traditions with family shape youth identity, social development, and engagement with physical activity. Her perspective is especially relevant for younger audiences experiencing the World Cup through schools and community programs, including UD’s Lab School initiatives. Inside the Game: Sports Analytics in Action With the rise of data-driven performance, UD’s new Sports Performance Analytics major is preparing students to analyze gameplay at the highest level. Martin Heintzelman, department chair, can connect media with program leaders and practitioners including Jack Davis and Christina Rasnake, who are helping students apply real-time analytics to global competitions like the World Cup. The Science Beneath the Game: Playing Surfaces World Cup matches are required to be played on natural grass—a costly and complex requirement, especially for indoor stadiums. Erik Ervin can discuss how turfgrass systems have evolved, the science behind maintaining elite playing surfaces, and the massive investment required to meet international standards. Why Watching Together Matters Amit Kumar studies the psychology of happiness and shared experiences. He can speak to why gathering to watch World Cup matches—whether in stadiums, bars, or living rooms—boosts well-being and strengthens social bonds, making the tournament as meaningful off the field as it is on it. Connect with UD experts to explore every angle of the 2026 World Cup – from the pitch to the people. Email mediarelations@udel.edu to connect with these experts. 

Hantavirus cruise ship outbreak: Epidemiologist discusses causes and challenges featured image

1 min

Hantavirus cruise ship outbreak: Epidemiologist discusses causes and challenges

A deadly outbreak of hantavirus on a cruise ship currently stuck off Cape Verde, Africa, has put the virus on the national radar for the first time since 1993. University of Delaware epidemiologist Jennifer Horney can talk about the potential for a larger outbreak and the challenges associated with responding to the emergency. There have been nearly 1,000 cases of hantavirus in the U.S. since surveillance began in 1993. That year, an outbreak of the severe respiratory disease in the four corners area of the U.S. Southwest was linked to domestic exposure to rodents, Horney said. Horney can discuss the following points in reference to the Dutch vessel M/V Hondius, which has seen three people die since departing from Argentina on April 1. • The response to this global public health emergency will be challenging given the cuts to U.S. public health and extensive leadership turnover at the Centers for Disease Control and Prevention. • Climate change and global transit likely contributed to the new cases, as rodent populations thrive during certain weather conditions. • When humans inhale rodent feces, urine or saliva, often when dust is aerosolized through cleaning, they can become infected. While symptoms may develop up to two months after exposure, the disease has a mortality rate of up to 50%. To reach Horney directly and arrange an interview, visit her profile and click on the "contact" button. Interested media can also send an email to MediaRelations@udel.edu.

View all posts