How Cleveland Clinic Is Developing AI To Monitor The Brain

Cleveland Clinic’s AI for brain seizures. Fidji Simo’s plan to solve complex, chronic disease. Vivek Ramaswamy’s estimated $12 million tax cut. These stories and more in this week’s InnovationRx newsletter. To get it in your inbox, subscribe here.

The Cleveland Clinic is working on AI to monitor patients’ brain health that could be a game-changer in the ICU – and potentially for epilepsy treatment, as well.

For more than a year, the Ohio-based hospital system has been collaborating with New York-based startup Piramidal to develop an AI model for the brain. The model is based on EEG data, which is collected by placing electrodes on the scalp, and represents the brain’s electrical activity. Doctors use EEGs to detect seizures and declines in brain function.

Continuous EEG data is the gold standard for monitoring of patients’ brain activity in the hospital, and demand for it has surged – leaving technicians struggling to keep up, even at the top health systems. The problem is that reading an EEG is a painstaking process that requires a technician to peer through multiple squiggly lines on pages of reports to come up with an explanation for a person’s behavior. It can take two hours for a well-trained tech to go through 24 hours of EEG data.

Cleveland Clinic hopes that the AI model, which Piramidal has submitted to the FDA for clearance following a successful pilot study, could help turn all that EEG data into a real-time clinical assistant.

“Our goal is to develop a technology that helps us as clinicians improve outcomes in patients,” Dr. Imad Najm, director of the Cleveland Clinic Epilepsy Center, tells Forbes. “Our challenge, considering all the noise we hear about AI everywhere, is to make sure that when we talk about AI in healthcare, that it is trusted.”

“This would be transformational in the field of epilepsy surgery and treatment in general,” he says.