• Posted December 10, 2025

AI Can Improve Epilepsy Treatment, Experts Argue

Artificial intelligence (AI) can help improve treatment of epilepsy by connecting the dots in complex cases, a new study says.

AI helped identify patients with drug-resistant epilepsy who might benefit from surgery, and it highlighted missing tests and evaluations that could better guide patients’ care, researchers reported in Atlanta Friday at a meeting of the American Epilepsy Society.

“Patients see multiple specialists and undergo many tests and their treatment plans evolve over years, so it’s easy for crucial details or opportunities for surgical evaluation to be missed,” lead researcher Dr. P. David Adelson said in a news release. He’s vice-chair of the West Virginia University Rockefeller Neuroscience Institute in Morgantown.

“Large language AI models continuously read, organize and interpret medical records to help health teams stay a step ahead,” Adelson said. “They have the potential to transform not just epilepsy care, but any long-term condition that requires coordination across specialties.”

For the study, researchers used an AI to evaluate the records of 820 patients with epilepsy who had scheduled appointments with WVU Medicine neurologists.

The AI identified 88 patients (11%) who met the criteria for drug-resistant epilepsy, researchers said. Guidelines recommend that these folks be evaluated for surgery, though not everyone winds up a candidate.

The AI also found that 54% of patients had outdated or missing MRI scans; 91% had missing neuropsychological evaluations; and 35% had missing electroencephalographs (EEGs).

Filling these gaps could lead to shorter delays in treatment and fewer missed opportunities for patients, Adelson said.

“It’s like having an intelligent research assistant that never gets tired. It keeps the care progress aligned and complete, and makes specialists more efficient, while ensuring that no patient is overlooked because of information gaps or time restraints,” he said. “This allows specialists to focus on interpreting results and planning treatment, helping extend expert-level care to more patients, even in hospitals with limited specialist coverage.”

Epilepsy care is complex and often fragmented, presenting a great opportunity for AI, Dr. Howard Goodkin, past president of the American Epilepsy Society, said in a news release.

“Research like this demonstrates the growing potential of responsible artificial intelligence to enhance epilepsy care,” said Goodkin, who was not involved in the study. “Instead of replacing the epilepsy specialist, AI acts as a partner, enhancing human expertise in medicine by tracking complex medical information, identifying gaps and prompting action to ensure care remains on course over time.”

Findings presented at medical meetings should be considered preliminary until published in a peer-reviewed journal.

More information

The Epilepsy Foundation has more on drug-resistant epilepsy.

SOURCE: American Epilepsy Society, news release, Dec. 5, 2025