Featured Post from University of Delaware

Decoding epilepsy, one brainwave at a time

Researchers are using AI to better understand childhood epilepsy

Jun 23, 2026

3 min

Epilepsy isn’t always easy to diagnose. Seizures often don't occur during routine brain-wave recordings, leaving doctors without the direct observation they need to make a clear diagnosis.

In a proof-of-concept study in mice, University of Delaware researchers and collaborators showed that using artificial intelligence to detect early warning signs hidden in the brain's electrical rhythms can identify subtle EEG differences linked to a genetic form of epilepsy, even when no visible seizures occurred. The findings, published in the Journal of Neural Engineering, set the stage for the next phase of the research, which will test the method on EEGs from children being evaluated for epilepsy at Nemours Children's Health.

A dictionary of brain waves

Neurologists often use EEGs to help diagnose epilepsy, but routine recordings offer only about a 20-minute snapshot of brain activity. Without a seizure captured during that window, clinicians must look for far subtler clues that can be difficult to detect visually.

That's where AI comes in.

“Our machine-learning approach lets the algorithm learn the brain’s ‘language’ of waveforms, spotting subtle patterns humans might miss during manual review,” said Austin Brockmeier, assistant professor in electrical and computer engineering and computer and information sciences.

Starting small with a mouse model

When Brockmeier presented his computational neuroscience research at a seminar, he caught the attention of Amanda Hernan, an affiliated associate professor of psychological and brain sciences and biomedical engineering at UD and senior research scientist at Nemours Children’s Health. Hernan studies how variations in brain activity affect thinking and learning in children with epilepsy.

The two decided to put machine learning to the test using EEGs from mice with epilepsy-causing variations in the TSC1 gene. The researchers used a panel of more than 40 mice, including animals with and without the gene variation, across three different genetic backgrounds, or strains. They extracted EEG segments from five days of recordings from each mouse for analysis.

Because the EEG segments contained no seizure activity, the algorithm had to detect differences in the brain's baseline activity alone. It was able to distinguish between the mouse strains and to detect the TSC1 gene variation with high accuracy in two of the three strains.

“These results show that EEG patterns contain measurable signals of neurological differences, even without visible seizures,” Hernan said.

Taking it to the clinic

Now, Brockmeier and Hernan will next apply their approach to EEG recordings from children being evaluated for epilepsy at Nemours Children's Health.

Pediatric EEGs are shorter than the multi-day recordings used in the mouse study, and children present with many different types of epilepsy. But the researchers are optimistic.

“The goal is to identify biomarkers that flag underlying changes in the brain’s electrical activity before seizures occur,” Hernan said. Earlier detection could lead to earlier treatment and less uncertainty for families.

That uncertainty, Hernan said, takes a toll. “Seizures follow natural cycles, but without a way to know where you are in that cycle, the anticipation can be incredibly anxiety-provoking,” she explained.

Better pattern recognition could also improve treatment decisions. For example, if a new medication is introduced during a natural lull in seizure activity, its benefits could be overestimated.

Looking further ahead, the researchers envision a future where wearable EEG devices allow continuous, real-time monitoring for those with high risk of seizures. Similar approaches could eventually be applied to other neurological conditions, including autism and ADHD.

"This is a step toward precision medicine," Brockmeier said. "Brain-wave typing could help identify which interventions will work best for a given patient."

For families navigating the daily uncertainty of epilepsy, that kind of precision could make a huge difference.

To speak with Brockmeier and Hernan, please reach out to mediarelations@udel.edu.

Find Experts

Oct 26, 2026

1 min

Two years after the 2024 election, where does civil discourse stand?

Election season has brought the expected vicious political campaign ads, heated online disagreements and difficult dinner table conversations with family and friends. But the University of Delaware’s Timothy Shaffer says there’s still room for civil discourse. Shaffer, UD’s inaugural Stavros Niarchos Foundation (SNF) Chair of Civil Discourse, studies how people can engage across significant differences while maintaining the relationships and democratic institutions that make disagreement possible. As chair of UD's SNF Ithaca Initiative, Shaffer works with students, educators and civic leaders to develop and practice constructive engagement across differences. He can comment on the following through the lens of the first midterm election since the vitriolic 2024 general elections. • What has changed since 2024: How have the past two years affected the way Americans talk about politics, disagreement and democracy? • Polarization and dialogue: Is political disagreement itself the problem, or is the greater challenge engaging constructively across differences? • The role of disagreement: Why civil discourse doesn't require consensus and how listening to competing perspectives can strengthen democratic engagement. • Politics and personal relationships: How to navigate political differences with family, friends, neighbors and colleagues without letting disagreements become personal. • Social media and the 2026 election: How online environments shape political conversations, what Shaffer expects as Election Day approaches, and how people can engage more constructively across differences. To reach Shaffer and arrange an interview, visit his profile page and click on the "contact" button. Interested reporters can also send an email to MediaRelations@udel.edu.

Oct 21, 2026

1 min

Blood Clots Can Sideline Elite Athletes. Could Microrobots Offer a New Approach?

Blood clots have sidelined or ended the careers of several elite athletes, drawing attention to a potentially life-threatening condition. The University of Delaware's Sambeeta Das is part of a team that has developed tiny, magnetically guided robots that could offer a new approach to removing such blockages. The list of athletes affected by blood clots includes NBA champion Chris Bosh, whose career ended after recurring clots; tennis great Serena Williams, who survived two life-threatening pulmonary embolisms; San Antonio Spurs center Victor Wembanyama, who was shut down in February 2025 when deep vein thrombosis was discovered in his right shoulder; and Philadelphia Eagles quarterback Jalen Hurts, whose recent diagnosis of blood clots in his lungs has drawn national attention. In a published study, Das and her colleagues demonstrated that magnetic microrobots could mechanically break apart clusters of human liver cancer cells and clear them from narrow channels designed to model blood vessels. The robots used mechanical forces rather than drugs or chemicals to disperse the clusters. The research offers an early proof of concept for using microrobots to remove unwanted cellular material in confined spaces. Das can discuss how the technology works, its potential application to blood-clot removal, the challenges of targeting blockages inside the body, and what further research is needed to explore its use in patients. To contact Das and arrange an interview, visit her profile and click the “Contact” button. Reporters can also email MediaRelations@udel.edu.

Oct 20, 2026

2 min

From Baseball to Business: The Science of Team Success

The ingredients that create a World Series team often mirrors how units achieve success in business. How did they get there? The University of Delaware's Kyle Emich says the answer goes beyond assembling a roster of star players. Emich, a professor of management, says that how players combine their strengths, respond to opponents and create opportunities together can be just as important as individual talent. The same is true in business, where a collection of talented employees doesn’t automatically translate into a high-performing team, he said. One example is the approach that the 2026 Milwaukee Brewers’ took during their postseason run. Rather than relying exclusively on home runs and individual star power, the team created opportunities through a combination of speed, patience at the plate, timely hitting and pressure on opposing defenses. A stolen base, a walk or a defensive mistake might seem like a small event on its own, but the effects can build as players’ actions interact. These interactions matter, he says, because teams are not simply collections of individuals; their performance emerges from how people and their activities affect one another within a larger environment. The same is true in business as well as baseball. Businesses may recruit exceptional employees or invest in promising technologies such as artificial intelligence, yet fail to realize their potential if their processes, team structures and working practices don’t support those strengths. Emich can discuss: • Beyond Moneyball: What baseball’s emphasis on statistics and individual talent reveals about the limits of evaluating people in isolation. • Building better teams: How coordination, complementary strengths and the interaction among team members contribute to performance. • Strategy and competition: What baseball teams’ adjustments to opponents can teach business leaders about responding to competitors and changing conditions. • Technology and the future of work: Why adopting artificial intelligence or other new technologies is not enough without considering how people, processes and technology work together. To reach Emich directly and arrange an interview, visit his profile page and click on the "contact" button. Interested reporters can also send an email to MediaRelations@udel.edu.