Locating the source of an epileptic seizure can be tricky. Even the most advanced MRI can’t pinpoint lesions, scars or other abnormalities on the brain in one-quarter of epilepsy patients.

Cleveland Clinic experts are turning to artificial intelligence to help bridge the gap.

Photo: This graphic created by Cleveland Clinic represents the results of imaging and neurophysiological tests layered in 2D and 3D, to help physicians locate the cause of seizures in the brain. (Courtesy Cleveland Clinic)

Neurologists and brain surgeons from the Clinic’s Epilepsy Center are using AI and advanced medical imaging techniques to help locate the source of a patient’s seizures. That gives surgeons a better chance of removing any brain tissue that’s associated with those seizures, which could help the patient live seizure-free for years.

“Every 100 patients we manage this way, 15 or 20 of them now are seizure-free [when] otherwise they would not have been if we had not applied this [technology],” Najm said.

As part of Brain Awareness Week, cleveland.com is highlighting some of the advanced technology being used in brain surgery at each of Cleveland’s three largest health systems. The three-day series will also focus on the use of virtual reality at MetroHealth and robotics at University Hospitals.

The Clinic has been at the forefront of studying the use of AI in health care. The health system established its Center its Clinical Artificial Intelligence in 2019, and CEO Tomislav Mihaljevic has said the technology could be key to the future of health care. On Tuesday, the Clinic announced a partnership with the NFL Players Association to use AI and machine learning to diagnose and treat neurological disease.

“These patients whose seizures are not controlled because none of the medications work, they need some other way to help them,” Najm said.
Epileptic seizures are caused by abnormal electrical activity in the brain, so neurologists need to locate the source of that abnormal activity. If they can’t find any abnormalities on an MRI, they can still use other techniques to find the general area the seizures are originating. But there’s only a 35 to 40% chance of success in those cases, Najm said.

“With these patients we struggle immensely,” Najm said. “And a big chunk of them we don’t do anything, and these patients will go on to live their lives with complications from seizures.”

That’s where AI can help.
Artificial intelligence refers to a collection of technologies, but machine learning is one of the most common used in health care. Machine learning uses algorithms to find patterns in large amounts of data, and it can use those patterns to make predictions. For example, Spotify uses machine learning to suggest a new song you might like based on your listening history.

Experts can then go back and check a patient’s MRI to confirm if there’s an abnormality they couldn’t see with the naked eye, Najm said.

“Just to see something is the single most important step for evaluating someone for epilepsy surgery,” Najm said.

Helping to locate the source of a seizure could be just the beginning of AI’s usefulness in helping epilepsy patients, Najm said. The Clinic is currently studying magnetic resonance (MR) fingerprinting, a technology developed by biomedical engineers at Case Western Reserve University. The technology analyzes an MRI and assigns a value that could help physicians identify the cause of a patient’s disease or illness. Najm hopes it could eventually help determine the cause of epileptic seizures and plan a patient’s treatment or surgery.

It’s difficult to say when that type of technology could be used in a clinical setting, because progress has been incremental, Najm said. But he’s optimistic it could be the next step forward to help epilepsy patients.
Source: Clevland.com by E. MacDonald