AI breakthrough offers hope for curing childhood epilepsy

Australian researchers have developed an artificial intelligence (AI) tool that can detect tiny, hard-to-spot brain malformations in children with epilepsy.

This tool could significantly improve treatment and offer a potential cure for children with drug-resistant epilepsy.

The latest example demonstrates how AI can crunch vast amounts of data and play a pivotal role in changing healthcare by assisting doctors with diagnoses.

Experts have identified that epilepsy has several distinct causes, and overall, around three in ten cases are due to structural abnormalities in the brain.

The tiny brain lesions that cause seizures are frequently missed on the MRI scans, especially the smallest ones that are sometimes hidden at the bottom of a brain fold.

A paediatric neurologist at the Royal Children’s Hospital in Melbourne trained an AI tool on child brain images to find contusions the size of a blueberry or smaller.

In this connection, Macdonald-Laurs held a briefing ahead of the publication of her team’s studies in the journal Epilepsia where she stated, “They are frequently missed, and many children are not considered as surgical candidates.”

It has been observed that similar research was published in February by a KCL team using AI on MRI data and spotted 64-percent of epilepsy-linked brain lesions that were previously missed by radiologists.

Nonetheless, the results were exciting as a proof of concept of the AI tool in treating child epilepsy; it is dramatically performing to improve diagnostic accuracy for children with drug–resistant seizures.