AI ‘Detective’ Identifies Hidden Causes of Child Epilepsy, Paving Way for Life-Changing Surgeries

118

TOKYO — Researchers in Australia have developed an artificial intelligence tool that acts as a super-sleuth, detecting minuscule, hard-to-spot brain malformations in children with epilepsy. This breakthrough promises to accelerate the path to potentially curative surgery for countless children whose conditions were previously deemed inoperable.

The innovation is a powerful example of how AI, with its ability to analyze vast and complex datasets, is transforming healthcare by augmenting human expertise and leading to more precise diagnoses.

Epilepsy, which causes recurrent seizures, affects approximately one in 200 children. A significant challenge is that about one-third of these cases are drug-resistant, meaning medications do not control the seizures. For many of these children, surgery to remove the small area of brain tissue causing the problem is the best hope for a seizure-free life.

The hurdle, however, has been finding the precise culprit. Experts estimate that structural abnormalities in the brain cause around 30% of epilepsy cases. These malformations, known as Focal Cortical Dysplasia (FCD), are often tiny lesions—sometimes the size of a blueberry or smaller—and can be hidden deep within the folds of the brain, making them notoriously difficult to identify on standard MRI scans.

“These subtle lesions are frequently missed, and as a result, many children are not even considered as surgical candidates,” said Dr. Emma Macdonald-Laurs, a paediatric neurologist at the Royal Children’s Hospital in Melbourne who led the research. “They live with debilitating seizures, and the opportunity for a cure is overlooked.”

How the AI ‘Detective’ Works

Dr. Macdonald-Laurs and her team at the Murdoch Children’s Research Institute trained their AI tool by feeding it a wealth of brain scans from children with known FCD. The AI learned to recognize the subtle patterns and textures of these malformations that are often invisible to the naked eye.

The system doesn’t rely on MRI alone; it cross-references MRI data with another type of scan called a Positron Emission Tomography (PET) scan, which measures brain metabolism. The AI fuses these two datasets, creating a comprehensive picture that highlights areas of concern with remarkable accuracy.

In their study, published in the journal Epilepsia, the tool’s performance was striking. It successfully identified lesions with a 94% success rate in one test group and 91% in another. Notably, 80% of the participants in the study had previously had their MRI scans reported as “normal.”

“The tool doesn’t replace radiologists or epilepsy doctors,” Dr. Macdonald-Laurs emphasized, “but it’s like a detective that helps us put the puzzle pieces together quicker. It flags the area, and then our clinical team can focus our expertise to confirm the finding. This means we can offer potentially life-changing surgery to children much sooner.”

The real-world impact is already evident. Of 17 children in the first study group, 12 underwent surgery to remove their identified brain lesions. Eleven of them are now living seizure-free.

Expert Reaction and Future Directions

Independent experts have hailed the research as a significant step forward.

“This work is really exciting as a proof of concept, and the results are really impressive,” said Konrad Wagstyl, a biomedical computing expert at King’s College London, who was not involved in the study. His own team published research in February using AI on MRI data alone, which identified 64% of missed lesions.

Wagstyl did note a consideration for wider adoption: “The Australian researchers used MRI with PET, which is a powerful combination. But some caveats are that PET is expensive, it’s not as widely available as MRI, and there is a dose of radiation associated with it.”

The Melbourne team’s next step is to validate the tool in real-world clinical settings on new, undiagnosed patients. The goal is to integrate this AI “detective” into hospital workflows worldwide, ensuring that more children with hidden brain malformations get the chance at a surgery that could end their seizures and transform their lives.

 

 

Support Dawat Media Center

If there were ever a time to join us, it is now. Every contribution, however big or small, powers our journalism and sustains our future. Support the Dawat Media Center from as little as $/€10 – it only takes a minute. If you can, please consider supporting us with a regular amount each month. Thank you
DNB Bank AC # 0530 2294668
Account for international payments: NO15 0530 2294 668
Vipps: #557320

  Donate Here

Support Dawat Media Center

If there were ever a time to join us, it is now. Every contribution, however big or small, powers our journalism and sustains our future. Support the Dawat Media Center from as little as $/€10 – it only takes a minute. If you can, please consider supporting us with a regular amount each month. Thank you
DNB Bank AC # 0530 2294668
Account for international payments: NO15 0530 2294 668
Vipps: #557320

Comments are closed.