‘Revolutionary’ method of analysing baby brainwaves could save vulnerable newborns

UCC researchers have discovered a revolutionary method of analysing newborn babies’ brainwaves; Prof Andriy Temko, Electrical and Electronic Engineering; Sergi Gomez-Quintana, CRT-AI and Electrical and Electronic Engineering; Andreea Factor, Anatomy and Neuroscience; and Dr  Emanuel Popovici, CRT-AI/INSIGHT Centres, Electrical and Electronic Engineering. Picture: Ralph O’Flaherty.

A “revolutionary” way to analyse babies’ brainwaves using sound has been discovered by a research team working at University College Cork (UCC) with the potential to save many vulnerable newborns.

This new approach uses sound rather than images to analyse brainwaves and detect  neonatal seizures with electroencephalography (EEG) monitoring. It is assisted with artificial intelligence (AI).

These EEG recordings are commonly used by neurophysiologists to identify seizures and are analysed using images.

“However, neurophysiological expertise is expensive and not available 24/7, even in tertiary hospitals,” the study found.

“Other neonatal and pediatric medical professionals (nurses, doctors, etc) can make erroneous interpretations of highly complex EEG signals.” 

Instead, this new method extends the idea of using a stethoscope to listen to heartbeats or other sounds from a patient’s body to also listening to brainwaves.

“Specifically, EEG is converted to sound using an AI-driven attention mechanism,” the study states.

“The perceptual characteristics of seizure events can be heard using this method, and an hour of EEG can be analysed in five seconds.” 

Co-supervisor Professor Andriy Temko of the School of Engineering and Architecture at UCC described the findings as “a potential game-changer” in healthcare.

“A lack of interpretation expertise has always been a bottleneck in the widespread usage of EEG monitoring in newborns,” he said.

“We have developed a method where AI augments human senses in an explainable manner to keep a healthcare professional in the decision-making loop. 

It is a potential game-changer in the EEG monitoring industry as the new method brings both accuracy and speed while requiring no training to be adopted in clinical settings.” 

A survey of users, including staff with no experience in this area, found it “drastically” reduces the time needed to review EEG data.

The same survey also found the accuracy of results obtained by these staff was on par with what experienced neurophysiologists found.

Another co-supervisor, Dr Emanuel Popovici of the School of Engineering and Architecture at UCC said this is “potentially high-impact research” and shows it is important for different specialities to collaborate together.

“It is another great example of the type of projects which can better humanity,” he said.

“The study opens up many possibilities in the future, from battery-operated edge devices to bringing this technology closer to the patient through commercialisation — ultimately contributing to improved care in disadvantaged communities settings.” 

The work was carried out by researchers in the multi-award-winning Embedded Systems Lab at UCC and the UCC School of Engineering and Architecture, which is supported by the SFI CRT-AI and Insight Centres.

The study also involved researchers from Munster Technological University and the UCC' Department of Anatomy and Neuroscience. 

The paper ‘A method for AI-assisted human interpretation of neonatal EEG’ was published in Nature Scientific Reports.