A new tool can help predict brain-damaging seizures and free up continuous EEG machines for high-risk patients

In hospital intensive care items, neurologists typically use a easy scorecard to shortly consider a critically in poor health affected person’s probability of getting a brain-damaging seizure to allow them to stop it. The scorecard saves lives, lowers prices and helps docs make way more environment friendly use of essential, costly medical tools.

But it surely wasn’t all the time that approach. Till about 2019, hospitals had no solution to shortly monitor a affected person’s digital mind exercise and precisely predict whether or not a seizure was lurking. Typically, a affected person wanted steady monitoring for twenty-four to 48 hours on a steady EEG (cEEG) machine to know for positive.

These machines are so costly that almost all hospitals solely have a number of, which implies solely a handful of sufferers at a time may gain advantage from them. Typically, the monitor can be used on a affected person at low-seizure threat whereas extra high-risk sufferers must wait.

In 2016, a workforce at MIT led by present Duke pc scientist Cynthia Rudin with then Ph.D pupil Berk Ustun and neurologist colleagues Aaron Struck and Brandon Westover started work on a brand new instrument for docs to make use of. The workforce crunched knowledge from hundreds of sufferers utilizing synthetic intelligence to create a greater solution to shortly consider mind harm sufferers.

The ensuing scorecard—referred to as “2HELPS2B,” assigns factors to sufferers primarily based on the patterns discovered of their cEEG knowledge. It shortly estimates a likelihood {that a} affected person would have a seizure in a variety from 5 to 95%.

“There was no mannequin to do that earlier than,” mentioned Rudin. She is a Duke professor of engineering and pc science who beforehand labored at MIT; it was throughout her time at MIT that she started work on this mission.

Rudin’s workforce used a machine studying algorithm that evaluated about 70 various factors derived from knowledge from greater than 5,000 sufferers, a sophisticated course of that took a number of years to excellent.

Now, a mind monitoring course of that when took as much as two days is finished as quick as 60 minutes, mentioned Westover, the Harvard neurologist.

The cEEG monitor derives knowledge on a affected person’s mind exercise {that a} specialist evaluates utilizing the scorecard. The scorecard assigns factors to elements equivalent to whether or not a sure electrical sample is current, or whether or not the affected person has had a previous seizure. A rating of zero means a affected person could be very unlikely to have a seizure; a rating of two suggests a probability of a seizure is 27%; a rating of 6 or extra is the utmost—which helps docs allocate assets successfully.

“It is a very, very great tool,” Westover mentioned. “In important care, the one that wants mind monitoring is often confused or comatose, so you don’t have any thought whether or not they’re having seizures now. Seizures can harm the mind, and if they’ve a mind harm already, a seizure will make it worse.”

A March 2025 research by UNC Chapel Hill researchers discovered that it has produced important advantages. Their research, revealed within the journal Neurology Medical Observe, discovered that the scorecard will help hospitals shortly decide which sufferers had been low threat and transfer their assets to different, extra important ones. Doing so made extra environment friendly use of the displays with out compromising the power to precisely predict seizures, the research concluded.

One of many scorecard’s greatest options is its simplicity; it does not require any sophisticated arithmetic, only a fast tally of small numbers, solely 1s and 2s. That is one motive it is now broadly used, Westover mentioned.

“It is ubiquitous now,” he mentioned. “My estimate can be that at the least 90% of hospitals, if they’ve any ICU EEG providers in any respect, will use this scorecard.”

It’s notably satisfying to Rudin that the instrument, publicly funded by taxpayers by means of the federal authorities, is accessible on the Web for anybody to make use of.

“You’ll be able to’t do that should you work at a personal firm,” Rudin mentioned. “The one approach I could make my fashions and algorithms public is as a result of I’m funded in a approach that lets me do one thing for the general public good. My aim is to make instruments that everybody can use.”