Medical tech: Smart arm bracelet warns of night-time epileptic seizures

A new NightWatch could save lives without the hassles of other sensors. Night-time epileptic seizures can be genuinely dangerous. If you have therapy-resistant epilepsy or a mental condition, you may have a one-in-five chance of dying from them

The Nightwatch  Image courtesy: Livassured
The Nightwatch
Image courtesy: Livassured

Now, researchers at TUe may have a viable way of detecting and responding to those seizures in time to save lives. They’ve developed a smart arm bracelet, Nightwatch, that both detects signs of severe seizures and contacts care staff. It combines both a heart rate sensor and a motion sensor to look for both an unusually high heart rate as well as the rhythmic jolting characteristic of a seizure.

The researchers involved think that this bracelet can reduce the worldwide number of unexpected night-time fatalities in epilepsy patients. They published the results of a prospective trial this week in the scientific journal Neurology.

In trials, the bracelet caught 85 per cent of serious epileptic seizures and 96 per cent of the most severe cases. That may not sound reliable, but it’s far more effective than a conventional bend sensor, which only detected 21 per cent of serious attacks. It’s also comfortable to wear, helping patients both fall and stay asleep.

The early Nightwatch model sends two separate alerts, one for each symptom. There’s work to be done before the two can be combined and increase accuracy.

The scientists have already created a company (LivAssured) to sell a finished product, though, and there are plans to coordinate the bracelet with audio-visual systems.

Ultimately, the team would like to customise alerts on a patient-by-patient basis, ensuring that even those with unusual symptoms can get timely help.

Night time seizures are among the most dangerous part of epilepsy and current ways of monitoring for them are inaccurate, bulky, or both. The study showed not only that NightWatch was reasonably accurate, but also that care providers found the system easy to use, giving it an average score of 7.3 out of 10 for user-friendliness.

Source: TUe/Eindhoven University of Technology