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 .
T he 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.”
The algorithm was trained on a broad base of publicly available EEG data, fine-tuned on curated Cleveland Clinic EEG data and validated in a Cleveland Clinic pilot study that wrapped up earlier this year. In the pilot study, the AI system correctly identified nine of 10 seizures with less than 10% false positives.
Sitting in front of a central monitoring system set up for demo purposes for an upcoming neurology summit, Piramidal co-founder and CEO Dimitris Fotis Sakellariou explains in a video call how the AI system can flag abnormalities to neurologists quickly (including via an app), allowing them to focus on the patients who need attention in real time.
“Imagine that you have a heart rate monitor, and you’re in a bed in the inpatient clinic, and your heart rate goes flat. It immediately starts beeping so the doctor knows we need to attend to that person,” he says. The goal is to do something similar for brain waves. “For the EEG that doesn’t exist because it is hard to detect abnormalities.”
Sakellariou, who did a Ph.D. in computational neuroscience at King’s College in London and previously worked as a senior AI engineer at healthcare research and analytics firm Iqvia, launched Piramidal in 2023 and took it through Y Combinator in 2024. The company has raised $6 million in seed funding to date, and expects to raise more soon.
Building an AI model with massive amounts of EEG data is complex, and Sakellariou believes that Piramidal (which submitted its AI model to the FDA in September) was the first to create a foundational model for the brain. “The AI can monitor hundreds or even thousands [of patients] in real time,” he says.
Cleveland Clinic hopes that the AI model will receive clearance and can then be rolled out quickly to patients in its hospitals, including in intensive care. Cleveland Clinic currently monitors 70 to 120 people at its 20 hospitals in Ohio and Florida. The health system is opening a centralized hub for large-scale EEG monitoring at its new state-of-the-art Neurological Institute on its main Ohio campus in early 2027 .
After that, Dr. Najm, who is director of Cleveland Clinic’s Epilepsy Center, says the goal is to expand the AI model to epilepsy patients. Cleveland Clinic has one of the world’s largest and most comprehensive programs for epilepsy for both adults and children.
Doctors who treat epilepsy need to figure out not only that a patient is having a seizure, but where in the brain that seizure originated, in order to come up with a plan for treatment among options that range from anti-seizure medications to brain surgery. To do that, Cleveland Clinic is now refining the algorithm with annotated videos of epilepsy patients – including some 6,000 who have had surgery for the disorder at its hospitals – to guide diagnosis and treatment. Dr. Najm says that he hopes to have a model ready to test for epilepsy treatment in the third or fourth quarter of 2027.
“This would be transformational in the field of epilepsy surgery and treatment in general,” he says.
Former OpenAI Exec Fidji Simo’s $20 Million Plan To Solve Chronic Disease, Including Her Own
I n May 2025, Fidji Simo started her dream job at OpenAI as Sam Altman’s second-in-command. But as she ramped up her work as chief executive of applications and then of AGI deployment, privately she was suffering from a devastating health condition.
She’d been diagnosed six years earlier with postural orthostatic tachycardia syndrome, or POTS, a frustrating chronic condition in which moving from lying down to standing, or even to sitting up, can cause a racing heart and dizziness. But after starting at OpenAI, her condition worsened, and she found she could no longer keep up with the frenetic schedule the AI startup demanded. This July, Simo stepped down from the company, though she remains an adviser there.
“Unfortunately, it’s very, very hard for me to stand without passing out. I can’t sit or stand so long – more than five or 10 minutes, I pass out, which is very inconvenient to say the least,” she says.
For the last year, Simo, 40, has been working on ways to use AI to attack chronic health conditions like her own. In March 2025, while still at OpenAI, she launched a startup called ChronicleBio with Rohit Gupta, who had previously overseen biobanks at Stanford and UCSF, and Rishi Reddy, a managing partner at Tarsadia Investments. While Simo is a cofounder, Gupta is the company’s CEO. Reddy, whose firm gave the company a few million dollars as its first seed funding, is executive chairman.
Their goal: To sort through the thicket of symptoms underlying chronic immune-related diseases like POTS, long COVID and myalgic encephalomyelitis/chronic fatigue syndrome, known as ME/CFS (the term “chronic fatigue syndrome” has fallen out of favor for trivializing and stigmatizing a debilitating health condition). Taken together, perhaps 250 million worldwide suffer from this set of chronic conditions, Gupta estimates.
The company is gathering blood from patients with these complex chronic conditions in the United States (at sites in Utah, Arizona and Texas with more in the works) and in India (where Reddy’s family owns a hospital) to do a comprehensive analysis of what’s going on biologically for them. In August, it also began working with mobile phlebotomy units to reach people who are homebound and bedbound and can’t get to a clinic.
To date, ChronicleBio has collected nearly 200 terabytes of data – roughly four times the amount in OpenAI’s early GPT-3 model – from more than 1,000 patients, with nearly 9,800 tubes of blood that have yielded 40,000 vials of specimens stored in its biobank. From those samples, ChronicleBio measures more than 1 billion data points, including 2,000 metabolites, which are small molecules your body makes when it digests food, repairs cells or performs other functions, and 1,000 proteins that carry out almost every biological function in the body.
Its goal is to first tease out differences among people who are currently lumped together under one header for diagnosis and insurance company purposes. By differentiating those who have subtypes of these chronic conditions, ChronicleBio hopes to provide frustrated patients with more information and treatment. While ChronicleBio is early-stage, it has raised $20 million from investors that include Breyer Capital, Wisdom Ventures and Proximal Ventures, as well as individual investors like Stripe’s Patrick Collison.
The cofounders started by homing in on ME/CFS, which affects an estimated 3.3 million people in the U.S. , and found five subtypes of the disease. They then ran analyses on adjacent conditions, like POTS, on the theory that the names of these conditions are less important than their underlying biology. So far, they’ve identified 13 different subtypes across chronic illnesses. If that holds up in further testing, they believe it could change how clinical trials are set up.
“We think these conditions are names that doctors have put on symptoms, and we think there is a lot of heterogeneity,” Simo says. “If a condition is really 10 conditions, it’s much harder to develop a drug.”
Vivek Ramaswamy’s Ohio Move Cut His Tax Bill By An Estimated $12 Million
As the Republican candidate for governor in Ohio, biotech billionaire Vivek Ramaswamy wants the state to stop taxing capital gains beginning next year, then phase out the state income tax altogether over the next decade. “If we do it,” he said last year, “founders will flock to Ohio in droves.”
Ramaswamy, who is 41 and worth $2.3 billion , has already slashed his own tax bill by making the move. He left New York for Ohio in late 2019 just before one of the largest windfalls of his career, at Roivant Sciences. Forbes estimates, based on conversations with CPAs, tax lawyers and tax professionals who reviewed publicly available information about the matter, that Ramaswamy saved about $12.3 million in state and local taxes by relocating to Ohio.
Swapping states before a big windfall and pending tax liability may be unusual for a gubernatorial candidate, but it is common practice among the rich and tax savvy. As Timothy Fogarty, a professor of tax and accounting at Case Western Reserve University, says: “People are always doing things like this. It’s completely allowed.”
Three neuroscience researchers who made breakthroughs in optogenetics, a technique that uses pulses of light to activate or turn off discrete groups of neurons in the brain, won the Nobel Prize in Physiology or Medicine.
What Oura’s stalled IPO tells us about consumer companies claiming to be tech platforms.
A patient died by suicide after an insurance delay on medication for his lung disease.
The latest Utah test of an “AI doctor” will let startup Nolla Health use its AI to prescribe common acne medications with limited doctor oversight.
In a region plagued by childhood obesity, an international health agency partnered with candy giant Ferrero to help fund vaccinations in Ecuador – then quietly dropped the deal.
Researchers in the lab of Harvard biologist David Sinclair said they’ve discovered small molecules that can reprogram cells to a younger state, raising the possibility of a pill to stall aging .
Republicans tried to punt health care cuts until after the midterm elections, but voters are already feeling the squeeze.