AI helps detect epilepsy before doctors do.
Researchers say that artificial intelligence (AI) could play a crucial role in the early detection of brain abnormalities associated with epilepsy, helping to improve diagnostic accuracy and expedite treatment.
Accordingly, Meld Graph software, developed by scientists at King's College London and University College London (UCL) in the United Kingdom, is an advanced diagnostic tool designed to detect brain abnormalities that radiologists might miss.
This technology is designed to identify focal cortical dysplasia (FCD), a type of malformation that occurs when nerve cells do not develop normally in certain areas of the brain.
This is one of the common causes of drug-resistant epilepsy, which refers to cases that do not respond to treatment with conventional anti-epileptic drugs.
Statistics show that there are currently around 630,000 people with epilepsy in the UK, with one in five having epilepsy caused by brain damage.
Notably, many of these cases can be effectively treated by surgically removing the damaged brain tissue. However, detecting FCD is not straightforward, as the lesion is often subtle and easily overlooked in routine imaging tests.
Dr. Konrad Wagstyl from King's College London commented: "Radiologists have to process a large amount of medical data, including very small and hard-to-detect lesions. Using an AI-assisted tool like Meld Graph can help them make faster and more accurate decisions."
"This not only improves the efficiency of the healthcare system but also shortens treatment times, helping patients avoid unnecessary and costly tests or procedures," shared Dr. Konrad Wagstyl.
How Meld Graph works
In a study published in the prestigious American medical journal JAMA Neurology, a team of experts used magnetic resonance imaging (MRI) data from 1,185 patients, including 703 patients with FCD, collected from 23 epilepsy treatment centers worldwide. Half of the data came from children, a group particularly vulnerable to epilepsy.
Meld Graph was trained by analyzing brain images, focusing on detecting subtle abnormalities that might be overlooked by the naked eye or traditional methods.
The results showed that this AI tool could detect 64% of brain abnormalities, significantly improving the rate of early diagnosis for epilepsy patients.
The research team believes that, if applied in clinical practice, Meld Graph could revolutionize the diagnosis and treatment of focal epilepsy, giving more patients a chance for timely and effective treatment.
Dr. Luca Palma from Bambino Gesu Children's Hospital (Italy), co-author of the study, shared a specific case: "Meld Graph detected an extremely subtle lesion that many radiologists had previously overlooked in a 12-year-old boy. This boy suffered daily seizures and had tried nine different anti-epileptic drugs without improvement."
"Thanks to this tool, we can accurately pinpoint the location of the lesion, helping us make surgical decisions, minimize risks, save costs, and optimize treatment outcomes," added Dr. Luca Palma.
The next steps
Although Meld Graph is not yet widely used in clinical practice, the research team has released the software as open source and organized training workshops to help clinicians access and apply this technology in practice.
Dr. Mathilde Ripart from UCL shared: "One of the most memorable moments for me was hearing doctors from all over the world, from the UK, Chile, India to France, share that they had used our tool to help their patients."
In the UK, Great Ormond Street Children's Hospital is one of the pioneering facilities participating in the Meld Graph trial.
Professor Helen Cross, a consultant epilepsy physician at the hospital and Director of the UCL Great Ormond Street Institute for Child Health, emphasized: "Many of the children I treat have gone through years of seizures and countless tests before we found any damage in their brains."
Professor Helen Cross added: "The medical community specializing in epilepsy is working to accelerate diagnosis and treatment. Advanced technologies like Meld Graph can help quickly identify surgically treatable abnormalities, potentially giving patients a chance of complete recovery."
With its immense potential, Meld Graph could become a groundbreaking tool in the diagnosis and treatment of epilepsy, offering new hope to millions of patients worldwide.
