AI-Powered Headset Capable of Predicting Seizures

A study involving 200 patients with epilepsy showed that 43% of patients suffered physical injuries as a result of a seizure, including head injury, dental injury, and even fractures.

The risk of injury from a seizure is one of the biggest concerns and worries around managing epilepsy, and understandably so. Recognising when a seizure is likely to occur and reacting quickly is crucial to minimising such concerns.

While there are already many epilepsy monitoring devices available on the market, studies like the one mentioned above emphasise the need for further research and development in this area.

Existing devices do well to provide early warnings of a seizure, but there is a gap in devices that can successfully detect a potential seizure before it occurs.

Addressing this need is a group of researchers at Glasgow Caledonian University who, approximately three years ago, set out to develop an AI solution that could transform the diagnosis and treatment of epilepsy.

Typically, to identify an epileptic seizure, a trained clinician manually reviews a variety of live or pre-recorded data, such as recordings from an EEG or ECG, which is often a time-consuming process that can take several hours per patient. To address this issue, the initial phase of the project in Glasgow involved training an AI software to analyse such data and identify a seizure for the clinician to review.

From there, the team has created a tool that can monitor multiple patients at the same time, improving both the quality and efficiency of the diagnostic process, and even providing a warning before a potential seizure occurs.

The next phase of the project involved integrating the AI software into a wearable device that could monitor patients for epileptic seizures. By May 2024, the project, led by Professor Hadi Larijani, gained significant recognition when it was entered into the Converge Challenge.

In early January 2026, the researchers of this project revealed their AI-powered headset capable of predicting seizures with up to 95% accuracy.

Similar to an ECG and EEG, the headset continuously analyses the wearer’s brain waves and heart functions. Further, the AI software can detect subtle patterns that happen in the brain and body before a seizure occurs, subsequently warning the wearer that a seizure is imminent.

By providing a warning of an impending seizure, users and those around them have time to respond and reduce the risk involved with a seizure, potentially avoiding injuries. This could significantly improve the quality of life for those suffering from epilepsy and provide peace of mind to the people who care for them.

Those involved in the project aim to develop this technology into something discreet and wearable, such as a cap, fit for daily use. To help launch the project, they have successfully secured £9 million in funding from UK Research and Innovation (UKRI).

We are excited for the potential impact this product can have on those with epilepsy and their families. However, before the product can become widely available for use, it must meet regulatory approvals, which could take several years.

Professor Hadi Larijani has made a promising statement in this area: “It takes time to get through the hurdles. But I think we’ve done the initial feasibility testing both on the software and the hardware characteristics.”

He continues, “Now we’re looking at a more commercial-ready product that hopefully will be going through the hurdles of the initial accreditation for medical devices.”

We are looking forward to seeing how this project develops, and we strive to inform you of any crucial updates around it. For further news and updates relating to Epilepsy Alarms UK, please refer to our blog.