Skip to main content
  1. Home
  2. Emerging Tech
  3. Legacy Archives

New brain implant warns of epileptic seizures minutes before they happen

Add as a preferred source on Google

brainOne of the worst things about epilepsy is its unpredictability. There is no way of knowing when those who struggle with the condition will have a seizure, nor any way to prepare for one. Or, at least, there wasn’t.

Researchers at the University of Melbourne are working on a brain implant that would be able to warn of seizures minutes in advance, giving their owners the chance to get ready as much as possible. By learning of an oncoming attack beforehand, they can remove themselves from any situation where a seizure would present a safety risk to themselves or others, such as operating heavy machinery or driving a car.

Recommended Videos

The project is headed up by Mark Cook, with funding from a U.S.-based medical device company called NeuroVista. At first, the implant’s software tracks the brainwave activity of its wearer, so that it can “learn” what kind of activity registers as unusual and potentially preparatory for a seizure. When it has enough data to make that prediction, the device will notify the user as soon as such activity is detected by transmitting a signal to a receiver worn outside their clothing.

In tests, 15 people with epilepsy tried the system for four months, and successfully predicted seizures for 11 of them 65 percent of the time. For two in particular, the device successfully warned of seizures every time one was about to occur, with a rough “warning time” of around four minutes before the seizure begins. “You can’t stop [the seizures],” Cook told New Scientist, “but if you knew one was going to happen, you could prepare… Just being able to predict them could improve people’s independence enormously.”

One unusual side effect of the trial was discovering that the device recorded seizures test subjects themselves weren’t even aware of. One subject in particular believed that he had only suffered 11 seizures during the test period, while information from the device suggested that the number was almost ten times that at 102. Christian Elger, who works at the University of Bonn in Germany, says this isn’t a new phenomenon. Studies suggest that patients tend to only realize of a quarter of their seizures.

Elger is hopeful about the implant’s use in future, noting that it could help with anti-seizure medication, which can take up to 15 minutes to have an effect and are often useless once a seizure has begun. With advance warning, it might be possible to administer medication ahead of time to prevent the seizure in the first place, he believes.

Tests continue to perfect the system; if nothing else, the fact that the system didn’t appear to offer significant predictive benefits for four of the test subjects at all is worth investigating. Still, sooner than later, there may be significant help on the way for their hopes to lead a less dangerous life.

Graeme McMillan
Former Digital Trends Contributor
A transplant from the west coast of Scotland to the west coast of America, Graeme is a freelance writer with a taste for pop…
Researchers hid a prompt injection inside a PNG, and AI fell for it
Hacker

AI coding assistants like Claude are becoming every developer's favorite coworker. They can review code, explain confusing functions, and even write entire features with a single prompt. But new research suggests that this growing trust could also become their biggest weakness.

A team of security researchers (professor Sudipta Chattopadhyay and researcher Murali Ediga) has demonstrated an unusual attack that doesn't target the AI model directly. Instead, it targets what the AI doesn't pay enough attention to during code reviews. Rather than hiding malicious instructions in lines of code, the researchers tucked them inside an image file. Since many AI review tools treat images as decorative assets rather than as something worth inspecting, the pull request can appear perfectly harmless and sail through the review.

Read more
AI has already fallen into the wrong hands and they’re using it to make bombs
Logo, Text

Artificial intelligence has quickly become the go-to tool for everything from writing emails and summarizing meetings to helping students study or developers debug code. But the same technology that saves people time can also be misused, and a new report suggests that terrorist organizations are finding ways to do exactly that.

According to a research paper shared with The New York Times ahead of its publication, researchers found evidence that members of Boko Haram have been using popular AI chatbots to support both day-to-day activities and combat-related tasks. Interviews with 27 former members conducted in Nigeria over the past two years suggest that tools such as ChatGPT, Gemini, Claude, Grok, Meta AI, and DeepSeek were used to gather technical information, troubleshoot weapons, and even assist with planning attacks.

Read more
Claude Code can now browse the web without opening Chrome
The desktop app now includes an in-app browser that can read websites, click links, and interact with web apps.
Claude Code Featured

Developers spend a surprising amount of time bouncing between their code editor, browser tabs, API documentation, GitHub issues, and design files. Anthropic thinks Claude Code should simply do all of that without constantly asking users to switch windows. The company has announced a new in-app browser for Claude Code on desktop, allowing its AI coding assistant to open websites, read documentation, inspect designs, and interact with web pages directly from within the application.

A browser built into Claude Code

Read more