People

Scientist Uses AI, Wearables to Decode Brain Rhythms and Forecast Seizures

The smartwatch technology correctly predicted about 75% of seizures, with few false alarms. 

By: Michael Barbella

Managing Editor

Photo: Chaikom/Shutterstock.

In a Mayo Clinic neurology laboratory, Dr. Benjamin Brinkmann studies the brain’s electrical rhythms across days, weeks and months, searching for patterns that reveal when seizures are most likely to occur. Working with neuroscientists and clinicians, he combines data from brain waves, vital signs and imaging to develop tools that interpret those signals and help guide patient care.  

Epilepsy is a brain disorder that causes recurring seizures—sudden bursts of electrical activity that can interrupt movement, speech or awareness. For many people living with this condition, medication keeps seizures under control. But for those with drug-resistant epilepsy, the episodes can occur without warning, disrupting routines and independence.  

Dr. Brinkmann is a biomedical engineer who has dedicated his career to improving epileptic care. Working with Mayo Clinic’s epilepsy team, he helps identify where seizures begin in the brain; such information is essential for those whose epilepsy is difficult to control. His long-term goal is to move from forecasting seizures to stopping them before they begin.  

A More Clear Picture of Epilepsy, One Signal at a Time

An example of that work is a study Dr. Brinkmann led with international collaborators. The team tested a small implant that sits just under the skin behind the ear, recording brain activity as people go about their day. The device helps provide a more accurate picture than seizure diaries, which can miss or misclassify episodes. Accurate and continuous monitoring helps doctors track seizure patterns and adjust treatment. 

Over 15 months, the team collected more than 72,000 hours of brainwave data from people with epilepsy and recorded 754 seizures—nearly twice as many as were reported in diaries. About half of the study participants wore the device more than 20 hours a day and reported it did not interfere with daily life. The findings suggest that long-term, at-home brain monitoring can uncover seizure patterns missed in short clinic visits.  

Smartwatch Uses AI to Forecast Seizures

Dr. Brinkmann also led a study on wearable technology—specifically, a smartwatch that uses artificial intelligence to help forecast seizures before they happen.  

The watch tracks heart rate, movement, skin conductance and temperature, using machine learning to help clinicians find patterns that may signal a seizure. In findings published in Epilepsia, the team correctly predicted about 75% of seizures, with few false alarms.  

Dr. Brinkmann said the idea is simple: to give people a warning. A few minutes’ notice can mean calling a caregiver, sitting down or avoiding a risky activity. In the future, those alerts could even trigger treatments automatically, using medication or gentle brain stimulation when seizure risk is high.  

Together, the implant and smartwatch studies show the potential in controlling seizures when brain activity can be tracked continuously. The research is opening a new window into the ways in which seizures develop and helping shape the next generation of neurotechnology at Mayo Clinic.  

Dr. Brinkmann’s work contributes to Mayo’s BIONIC program—Bioelectronics Neuromodulation Innovation to Cure—which unites scientists and clinicians to develop smarter, more responsive technologies and therapeutics for the brain, spine, and nervous system. The goal is to develop systems that can sense trouble and respond instantly to stop it.  

The  Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education, and research, and providing compassion, expertise, and answers to those needing healing.

Keep Up With Our Content. Subscribe To Medical Product Outsourcing Newsletters