Mediaboss Marketing

CLEVELAND, Ohio -- Locating the source of an epileptic seizure can be tricky. Even the most advanced MRI cant 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.

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

The use of AI has already helped the Clinic improve the odds a surgery will result in a patient living without seizures, said Dr. Imad Najm, the director of the Epilepsy Center at the Cleveland Clinic Neurological Institute.

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 Clevelands 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.

An estimated 3.4 million people in the U.S. have epilepsy, and many of them suffer from seizures that could happen at any time. There are medications that can help, but a U.S. Centers for Disease Control and Prevention study found they prevented seizures in just 44% of patients. Those medications can also cause side effects such as fatigue, dizziness or blurred vision.

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 cant find any abnormalities on an MRI, they can still use other techniques to find the general area the seizures are originating. But theres 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 dont do anything, and these patients will go on to live their lives with complications from seizures.

Thats 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.

Clinic experts used an algorithm developed by a physicist in Switzerland and adapted it so it could help epilepsy patients. The algorithm analyzes a large amount of patient data and uses that data to predict the location of the brain tissue associated with the patients epileptic seizures.

Experts can then go back and check a patients MRI to confirm if theres an abnormality they couldnt 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 AIs 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 patients disease or illness. Najm hopes it could eventually help determine the cause of epileptic seizures and plan a patients treatment or surgery.

Its difficult to say when that type of technology could be used in a clinical setting, because progress has been incremental, Najm said. But hes optimistic it could be the next step forward to help epilepsy patients.

In the field of difficult-to-treat epilepsies, this is very exciting, Najm said. The field of epilepsy surgery has made major advances over the last 80 years. But this new ability for us to see something we previously were not seeing has been a major step forward in the field of epilepsy surgery.

Original post:
Artificial intelligence is helping the Cleveland Clinic improve the odds an epilepsy patient can live seizure - cleveland.com