originally published at King´s College London

MELD Graph is an AI tool that could drastically change the care for 30,000 patients in the UK and 4 million worldwide with one cause of epilepsy, researchers say.

The study, published today in JAMA Neurology by a team at King’s College London and University College London (UCL), shows how the tool significantly improves the detection of focal cortical dysplasia’s (FCDs) which is a leading cause of epilepsy.

Researchers say the tool will speed up diagnosis times, get patients the surgical treatment they need quicker, and reduce costs to the NHS by up to £55,000 per patient.

In the UK, 1 in 100 people are affected by epilepsy and seizures often present in childhood. 1 in 5 people with epilepsy have seizures caused by a structural abnormality (“lesion”) in the brain. FCDs are a common structural cause of epilepsy and in people with this type of epilepsy, seizures are usually not able to be controlled with medications. Surgery to remove the lesion can be an effective and safe way to stop the seizures. However, the challenge is that FCDs can be subtle and difficult to see with the human eye and up to half of these lesions are missed by radiologists. Delays to diagnosis and surgery mean more seizures, more visits to A&E, and more disruption to school, work and home life.

In the study, the researchers pooled MRI data from 1185 participants – including 703 people with FCD and 482 controls – from 23 epilepsy centres around the world in the Multicentre Epilepsy Lesion Detection project (MELD). Half of the dataset is from children. They then trained the artificial intelligence tool, MELD Graph, on the scans to detect these subtle brain abnormalities that might otherwise go undetected.

Project lead-author, Dr Konrad Wagstyl, from King’s College London, said: “Radiologists are currently inundated with images they have to review. Using an AI-powered tool like MELD Graph can support them with their decisions, making the NHS more efficient, speeding time to treatment for patients and relieving them of unnecessary and costly tests and procedures.”

Co-author Dr Luca Palma, from Bambino Gesù Children’s Hospital, Italy, said: “MELD Graph identified a subtle lesion missed by many radiologists in a 12-year-old boy who had daily seizures and had tried nine anti-seizure medications with no improvement to his condition. This tool could identify patients with surgically operable epilepsy and help with surgical planning – reducing risks, saving money, improving outcomes.”

While the tool is not yet clinically available, the research team have released the AI-tool as an open-source software. They are running workshops to train clinicians and researchers around the world, including Great Ormond Street Hospital and the Cleveland Clinic, in how to use it.

First author, Dr Mathilde Ripart from UCL, said “One of the highlights for me is hearing from doctors around the world, including the UK, Chile, India and France have been able to use our tools to help their own patients.”

Co-author Professor Helen Cross, Prince of Wales’s Chair of Childhood Epilepsy, President of the International League Against Epilepsy, Consultant Epileptologist at Great Ormond Street Hospital, and Director of the UCL Great Ormond Street Institute of Child Health, OBE said: “Many of the children I see have experienced years of seizures and investigations before we find a lesion. The epilepsy community is searching for ways to speed up diagnosis and treatment. Initiatives such as MELD have the potential to rapidly identify abnormalities that can be removed and potentially cure the epilepsy.”

Co-lead Dr Sophie Adler from UCL said: “This type of research is only possible with international collaboration. We were privileged to work with 75 researchers and clinicians towards this common goal of “no missed epilepsy lesions worldwide”.”

Reference 

• Ripart M et al., 2025. Detection of epileptogenic focal cortical dysplasia using graph neural networks: a MELD study. JAMA Neurology, Feb 24. doi:10.1001/jamaneurol.2024.5406

April 29th 2019  | originally published at Agência FAPESP

Maria Fernanda Ziegler | Agência FAPESP – Researchers in Australia are developing implantable electronic devices for patients with epilepsy. The goal is to predict seizures, identify the pattern of seizure frequency, and even release medications to prevent further episodes. The devices are not yet marketable, but some of them are already being tested in humans.

Epilepsy affects about 1% of the world’s population, and yet it is still shrouded in stigma and mystery. In it, for some genetic or environmental reason, a group of brain cells becomes extremely active, to the point of making the electrical signals completely disorganized. This mismatch often culminates in loss of memory and convulsions.

“Epilepsy is not a rare disease and has many effects on people’s lives. Therefore, the patient needs to know that it is an electrical problem in the brain that can be predicted, monitored and treated. This takes away all the mystery of the disease which, to the unhappiness of patients, is shrouded in ignorance and superstition”, said Australian scientist Mark Cook, a professor at the University of Melbourne and director of the Department of Neurology at St. Vincent’s Hospital in Australia.

The researcher participated, in April, in the 6th BRAINN Congress, at the State University of Campinas (Unicamp). The event was conducted by the Research Institute on Neuroscience and Neurotechnology (BRAINN) – a Research, Innovation and Dissemination Center (CEPID) funded by FAPESP.

In his speech, Cook presented the new devices that, according to him, could give greater quality of life to people with epilepsy in the future. He also talked about the latest results of his research on patterns of seizures in patients with the disease.

“Each patient has a specific pattern [of seizures] – we have already proven that. Imagine, then, being able to predict when you will have one of those episodes? People could protect themselves by staying home and being accompanied, rather than engaging in some risk activity on that particular day”, Cook told Agência FAPESP.

The new devices are aimed primarily at anticipating the onset of a seizure and are being developed by the Bionics Institute through a partnership between the University of Melbourne and St. Vincent’s Hospital. The institute has donations and funds, such as the one received on the television program The Shark Tank Miami (USA) – in which Cook competed and won in a special edition on epilepsy in 2015.

Prediction

“There are two ways to detect a seizure. In one of them, it is possible to read the brain signal and detect the electrical signature that occurs before it happens. Another way is to monitor the seizures for a certain period and identify a pattern. As soon as this pattern is established, the prediction becomes very accurate”, he said.

In the first case – detecting brain electrical signals -, implantable devices that can deliver drugs are being developed. One of them was implanted two years ago in a patient in Australia, who has so far responded well to the treatment.

Researchers are also developing an equipment with implantable electrodes to apply electroshock treatment – which is another way of treating epilepsy, besides medications and surgery – but there is still no human test prediction.

To monitor seizures in order to identify patterns, devices have been developed to be inserted under the scalp or behind the ear (such as cochlear implants for the deaf).

“We realized that, if we could count the seizures reliably, it would be possible to identify each patient’s monthly, weekly, or daily patterns. This would make it safer for patients to perform everyday activities and avoid embarrassment”, said the researcher.

Based on comprehensive databases (from the SeizureTracker and NeuroVista applications), Cook and his team identified striking periodicities between one seizure and another. According to the study, more than 80% of patients had one-day intervals between seizures. Cycles of one week or three weeks or more have also been observed.

“Understanding these patterns can have significant implications for managing people’s lives and predicting crises. Typically, patients are encouraged to write journals or use cell phone applications to track the seizures. However, this has proven to be very imprecise, as seizures can cause memory loss and unconsciousness. Many times, the patient does not realize that there was a small lapse”, Cook explained.

Much more accurate than the journals, implantable devices can be used for a long time, making it possible to cross information with external conditions that may be related to seizures, such as temperature, air humidity or even stress, food and medication. Clinical testing for this device should begin in the second half of 2019. According to Cook, all devices were designed for the study of epilepsy cases, but could also be used for other conditions, such as controlling the blood sugar of diabetics, for example.