This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

A patch the size of a Band-Aid, stuck to your forehead, can now do something no traditional sleep study or fitness tracker can: nudge your brain toward a better night's sleep. William Coon, a sleep scientist at the Johns Hopkins Applied Physics Laboratory, has built a wearable device, meant to be used at home, that listens to brain activity and uses neurostimulation and other techniques to manufacture deep, restorative sleep.

The device is "using information in real time to actually personalize, optimize and improve sleep as a controllable biological system," Coon says. That approach borrows from a familiar model: "We're developing foundation models [and] frontier models that are assessing brain signals the same way that LLMs assess language signals."

Getting there meant first determining how to accurately measure the brain's sleep signals without a clinic full of equipment. The clinical gold standard, polysomnography, requires a technician to place sensors across the scalp, then spend 30 minutes manually classifying the signals into sleep stages. This process is governed by scoring rules written in the 1950s and capped at roughly 85% accuracy.

Consumer wearables have historically forced a trade-off between comfort and accuracy: Bulky headband-based EEG devices could track brain activity, but few people would wear one nightly. Comfortable options like the Apple Watch skip brain activity entirely, relying only on motion tracking.

Coon's team trained an artificial intelligence model on more than 11,000 overnight recordings from a public archive called the National Sleep Research Resource.

Source link