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

By Luciana Constantino  |  Agência FAPESP – Considered the largest genetic study of epilepsy in the world, a study published in the journal Nature Genetics reveals specific alterations in DNA that signal a greater risk of the brain disorder. Identifying these alterations will improve diagnosis and advance the possibility of new treatments for the disease.

The researchers identified 26 different areas (loci) of the genome that are linked to epilepsy, with 29 genes thought to play an important role in the disorder. Of these genes, 17 were associated with epilepsy for the first time; ten are linked to the development of the disease when mutated or altered (known as monogenic epilepsy genes) and the other seven are known to already have approved drugs that focus on treating autism spectrum disorders.

Analysis of the subtypes revealed significantly different “genetic architectures” mainly between two subtypes of epilepsy – focal and generalized – and common variations in DNA can explain between 39.6% and 90% of the genetic risk for the latter type.

Coordinated by a consortium of the International League Against Epilepsy (ILAE) involving more than 350 scientists, the study compared data from 29,944 people with the disease to those of 52,538 control subjects. It included epilepsy cases of European (92%), African (3%) and Asian (5%) descent.

Brazil was the only Latin American representative through the Brazilian Institute of Neuroscience and Neurotechnology (BRAINN), a FAPESP Research, Innovation and Dissemination Center (RIDC) based at the State University of Campinas (UNICAMP).

“We at BRAINN were involved in all stages of the work, from the detailed characterization of the patients from a clinical, imaging and neurophysiological point of view – which we’re very good at – to planning the analyses, suggesting how they could be carried out and then checking the results. We were also actively involved in writing the article, which was submitted to the journal over a year ago. Many international studies exclude patients from Brazil because we have such great genomic diversity. However this study did a meta-analysis, which allows us to combine populations with different genomic structures. For the future, we want to expand this diversity even more,” Iscia Teresinha Lopes-Cendes, a professor at UNICAMP’s School of Medical Sciences and co-author of the BRAINN article, told Agência FAPESP.

There are an estimated 2 million Brazilians with epilepsy, at least 25% of whom are uncontrolled, according to the Ministry of Health. Worldwide, the World Health Organization (WHO) estimates that 50 million people are affected by the disorder, a third of whom are resistant to the treatments available on the market.

A highly hereditary neurological disease with no cure, epilepsy causes seizures, up to 40 or 50 a day in the most severe cases, leading to loss of consciousness and falls. Uncontrolled seizures not only disrupt the patient’s daily routine but also pose a serious risk of sudden and premature death.

Treatment involves a combination of medications, which are not always effective. Most medications reduce the activity of neurons across the board, which controls seizures, but they have side effects. An alternative is surgery to remove the part of the brain affected by the malformation.

Now, the researchers are proposing some medications that are normally used for other conditions, but act on the epilepsy risk genes identified in the study.

Knowledge over time

Recognizing the complexity of the genetic and environmental factors related to epilepsy, the consortium was formed in 2010 to collaborate on investigating large datasets at an international level.

“This is an important milestone for the ILAE Consortium on Complex Epilepsies and shows what can be achieved when scientists collaborate openly and share data from around the world,” said the league’s president, Professor Helen Cross, in a press release.

To arrive at the results suggesting different genetic architectures between focal and generalized forms of epilepsy, genetic data were combined with databases of phenotypic information, expanding the sample to more than 51,600 patients and 1 million “controls.” This discovery of the different genetic framework for the different types of epilepsy provides clues to understanding the various syndromes.

In their work, the scientists point out that the proteins that carry electrical impulses through the gaps between the brain’s neurons are part of the risk for generalized forms of epilepsy. In this sense, they emphasize the importance of accurately characterizing or classifying specific epileptic syndromes (syndromic phenotyping) in order to better understand the genetic basis of the disease.

An advocate of studies with so-called “pure data,” Lopes-Cendes says that she is now working specifically on mesial temporal lobe epilepsy (MTLE) with hippocampal atrophy. “We’ve been continuously generating data for specific research on the topic. I’d argue that in certain studies, mixing information from different types of epilepsy can ’dilute’ the data and not highlight results that might appear if the group of patients studied was more homogeneous. I think a balance is needed,” she adds.

In early 2023, the researcher and her group published another article that deepened our understanding of MTLE, considered the most common and refractory to pharmacological treatment, by evaluating, for the first time, the profile of messenger RNA (mRNA, a molecule that contains the information for the production of proteins) from surgical tissue obtained from patients.

Because of her work in genetics, Lopes-Cendes was recently invited by the WHO to join the new Technical Advisory Group on Genomics (TAG-G), which is responsible for contributing to the process of accelerating access to genomic knowledge and technologies, especially in low- and middle-income countries. The group consists of 15 scientists from different countries.

The article “GWAS meta-analysis of over 29,000 people with epilepsy identifies 26 risk loci and subtype-specific genetic architecture” can be read at: www.nature.com/articles/s41588-023-01485-w.

Text and Photos: Camila Delmondes. Originally published on the FCM Unicamp portal.
July 20, 2023

The International Society of Neuropathology (ISN), in association with the International League Against Epilepsy (ILAE) and the support of the Brazilian Institute of Neuroscience and Neurotechnology (CEPID BRAINN), promoted the 12th International Summer School on Neuropathology and Neuroimaging in Epilepsy (INES 2023) from July 19 to 22 in Campinas, Brazil. The event took place at the Casa do Professor Visitante (CPV) at Unicamp and brought together postgraduate students, neurologists, and pathologists from Brazil, Germany, Sweden, Mexico, Bolivia, Honduras, Uruguay, Argentina, Peru, Ukraine, the United States, and Russia.

Researchers from different countries gathered in Campinas for training in neuropathology and neuroimaging, aiming at the diagnosis and treatment of focal epilepsy / Photo: Camila Delmondes

The course focuses on the recognition and classification of brain lesions, integrating skills and knowledge from the fields of neuropathology and neuroimaging to provide a detailed diagnosis for the successful management of focal epilepsy. Over four days, participants engaged in practical activities for the interpretation of brain images obtained through Magnetic Resonance Imaging (MRI) and attended lectures by renowned specialists from Brazil and Germany.

Neuropathologist from Friedrich-Alexander University Erlangen-Nürnberg (Germany), Ingmar Blümcke, on his fourth visit to Brazil. “Based on the analysis of brain tissue extracted by the neurosurgeon, the pathologist raises some hypotheses and cross-references the information with clinical data. With a more accurate diagnosis of brain lesions, it is possible to make the treatment of patients more efficient,” he explained during the INES 2019 edition, also held in Campinas / Photo: Camila Delmondes

Neurologist Fernando Cendes – the lead researcher of CEPID BRAINN, head of the Department of Neurology at the Faculty of Medical Sciences (FCM) of Unicamp, and host of the event, along with Fábio Rogério, a professor in the Department of Pathology at FCM -, explained that compared to previous editions, INES 2023 places more emphasis on neuroimaging, aiming not only to discuss advances in research in this field but also to provide a moment of practical immersion.

A global reference in epilepsy-related studies, Fernando Cendes discussed the advances of the international scientific community in the diagnosis and treatment of the disease in recent years through events like INES, which aim to disseminate knowledge, especially among young researchers.

Neurologist Fernando Cendes is a professor at the Faculty of Medical Sciences of Unicamp, BRAINN researcher and a global reference in epilepsy studies / Photo: Camila Delmondes

“The advances have been incremental. In recent years, we have had a new revision of the international classification of epilepsies, including pathologies that were previously not understood or diagnosed; we made progress in the field of genetics, identifying molecular markers for a more accurate diagnosis of epilepsy; and we reached a consensus in the international scientific community regarding the terminologies used, so now we speak the same language in various parts of the world [when it comes to epilepsy and its scientific findings in general]”, said Dr. Cendes.

As guests in the program, sharing their expertise, were present the professors Ingmar Blümcke, Roland Coras, and Stefan Rampp from Germany; Enrico Ghizoni, Helder Tedeschi, Clarissa Lin Yasuda, Iscia Lopes-Cendes, Fábio Rogério, Simoni Avansini, Marcus Vinicius Giglio, and Marina Alvim from Brazil.

EVENT PHOTOS

Click to enlarge.

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.

October 11th 2017     by Redação WebContent

Every year, the Coordination for the Improvement of Higher Education Personnel (CAPES, in Portuguese) presents its Thesis Awards, dedicated to the best doctoral thesis defended in the whole country. In 2017, UNICAMP was awarded two prizes, one of them being of special relevance to BRAINN.

The thesis “FUNCTIONAL AND STRUCTURAL CONNECTIVITY IN PATIENTS WITH FOCAL EPILEPSY“, by student Brunno Machado de Campos, received the CAPES Award in the category ‘Medicine I’. Brunno is supervised by prof. Fernando Cendes, BRAINN´s main Coordinator.

The award winners receive, in addition to honors, several incentives to improve his/her academic career:

• a diploma,
• a medal and
• a national postdoctoral fellowship of up to 12 months;

Dr. Fernando Cendes will receive assistance for participation in any national congress, in the amount of R$3 thousand. There are also distinctions to be given to the supervisor, co-orientator and the program in which the thesis was defended; as well as a fully paid trip for the author and his supervisor to attend the award ceremony, which takes place in December.

BRAINN congratulates Brunno and dr. Fernando Cendes for this invaluable achievement!