AI Tool MELD Graph Revolutionizes Epilepsy Diagnosis by Detecting Hidden Brain Lesions

5 Sources

Share

A new AI-powered tool called MELD Graph has shown remarkable success in detecting brain abnormalities linked to epilepsy, often missed by human radiologists. This breakthrough could significantly improve diagnosis and treatment for millions of epilepsy patients worldwide.

News article

AI Tool Detects Hidden Brain Lesions in Epilepsy Patients

Researchers from King's College London and University College London (UCL) have developed an artificial intelligence tool called MELD Graph that could revolutionize the diagnosis and treatment of epilepsy. The study, published in JAMA Neurology, demonstrates the tool's ability to detect subtle brain abnormalities that human radiologists often miss

1

2

3

.

Improved Detection of Focal Cortical Dysplasias

MELD Graph significantly improves the detection of focal cortical dysplasias (FCDs), a leading cause of epilepsy. In the study, the AI tool accurately identified 82% of known lesions that had been successfully removed in surgeries, rendering patients seizure-free

1

. More impressively, it detected an additional 64% of lesions that radiologists had previously overlooked when reviewing MRI scans

1

2

3

.

Study Methodology and Results

The research team pooled MRI data from 1,185 participants, including 703 people with FCD and 482 controls, from 23 epilepsy centers worldwide as part of the Multicentre Epilepsy Lesion Detection project (MELD)

2

3

. Half of the dataset comprised scans from children. The AI was trained on half of the MRI scans and then tested on the remaining half

1

2

.

Dr. Konrad Wagstyl, the project lead-author from King's College London, emphasized the tool's potential to support radiologists in their decision-making process, potentially making healthcare systems more efficient and speeding up treatment for patients

2

3

.

Potential Impact on Patient Care

Researchers estimate that MELD Graph could drastically change care for approximately 30,000 patients in the UK and 4 million worldwide who suffer from this particular cause of epilepsy

2

3

. The tool is expected to:

  1. Speed up diagnosis times
  2. Facilitate quicker access to surgical treatment
  3. Reduce healthcare costs by up to £55,000 per patient

    2

    3

Real-World Application

Dr. Luca Palma from Bambino Gesù Children's Hospital in Italy shared a compelling example of the tool's effectiveness. MELD Graph identified a subtle lesion in a 12-year-old boy with daily seizures that had been missed by many radiologists. The patient had previously tried nine anti-seizure medications without improvement

1

2

3

.

Future Prospects and Availability

While MELD Graph is not yet clinically available, the research team has released it as open-source software. They are currently conducting workshops to train clinicians and researchers worldwide, including at prestigious institutions like Great Ormond Street Hospital and the Cleveland Clinic

2

3

4

.

Professor Helen Cross, a co-author and consultant at Great Ormond Street Hospital, highlighted the tool's potential to rapidly identify removable abnormalities that could potentially cure epilepsy

4

5

. However, further trials are needed to investigate the long-term benefits for patients whose brain lesions are detected using this AI tool

5

.

As the epilepsy community continues to search for ways to expedite diagnosis and treatment, initiatives like MELD offer hope for improved outcomes and quality of life for millions of patients worldwide.

TheOutpost.ai

Your Daily Dose of Curated AI News

Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Spend less time searching for the latest in AI and get straight to action.

© 2025 Triveous Technologies Private Limited
Instagram logo
LinkedIn logo