Scottish Scientists Develop 95% Accurate AI Headset to Predict Epileptic Seizures
AI Headset Predicts Epileptic Seizures with 95% Accuracy

Scientists in Scotland have unveiled a groundbreaking wearable device that uses artificial intelligence to predict epileptic seizures several minutes before they occur. The team from Glasgow Caledonian University says this "unique" AI-powered headset could revolutionise how the neurological condition is managed, offering unprecedented advance warnings.

How the AI Seizure Prediction System Works

The innovative headset analyses a combination of brainwaves and heart function data to detect the subtle electrical and physiological patterns that signal an impending seizure. The system was trained using thousands of hours of historical electroencephalography (EEG) and electrocardiography (ECG) recordings. Researchers also employed a custom-made "phantom head" with attached electrodes to simulate real-world usage.

Professor Hadi Larijani, who leads the research team, explained the device's potential impact. "Providing even a few minutes' warning could be life changing," he stated. "Our goal is to empower patients and families with time to act to stay safe and live more independently." The AI algorithm boasts an accuracy of up to 95% and can even display its confidence level regarding the likelihood of a seizure.

Transforming Lives and Enhancing Safety

Currently, there is no readily available commercial device that offers people with epilepsy reliable advanced warnings. This gap in care leaves hundreds of thousands of individuals in the UK, and millions globally, vulnerable to sudden seizures and potential secondary injuries.

The headset's primary benefit, according to its developers, is the confidence and security it can restore. An alert issued minutes beforehand allows the wearer to take precautions, such as moving to a safe location, assuming a secure position, or alerting someone nearby. "For families affected by epilepsy, even a brief warning means they can prevent injuries and reduce fear," Professor Larijani emphasised. "That is the true measure of success for us."

The Path to a Commercial Medical Device

The research team is actively refining the design, aiming for a final product that is discreet, wireless, lightweight, and suitable for both adults and children. While initial prototypes have utilised third-party hardware, the goal is to develop bespoke models.

However, bringing such a device to market requires navigating stringent regulatory pathways. "The most regulated things are medical devices. It takes time to get through the hurdles," Professor Larijani noted. The team has completed initial feasibility testing and is now developing a more commercial-ready product. They have recently secured further support from UK Research and Innovation's £9 million Proof of Concept programme, but it may still be several years before the headset becomes widely available to patients.