AI sleep trackers that predict Alzheimer’s

A research study could help determine who should receive further Alzheimer's tests

Spotted: Sleep disruption can be one of the early signs of Alzheimer’s disease, even before cognitive symptoms show up. However, high-quality sleep assessments are expensive and provide limited data, often from just one night. Now, a researcher at the University of Massachusetts at Amherst is working on collecting additional, essential data.

The new research project, led by Professor of Biomedical Engineering Joyita Dutta, is being supported by a grant of $3.9 million grant from the National Institutes of Health. The work aims to assess if sleep trackers can log sleep patterns that correlate with future cognitive decline, as indicated by blood biomarkers.

In the study, participants with a genetic predisposition to Alzheimer’s disease but no observable signs of cognitive decline will wear three types of common sleep trackers for a week: the Apple Watch, the Oura Ring, and a wearable electroencephalogram (EEG) called the CGX Patch.

The data collected from the wearables will be compared to new blood tests measuring amyloid and tau proteins, which are thought to be important early biomarkers of Alzheimer’s disease. This assessment will be repeated after two years. With genetic information, blood-based biomarkers, and wearables-derived metrics, it should create a more comprehensive picture of the relationship between sleep and dementia.

Dutta is not arguing that wearable devices are a substitute for clinical approaches, rather, they could be used as a tool for flagging at-risk individuals or as an early warning system. For example, they could alert users that they are at risk and should see a neurologist, enabling them to implement treatments that could significantly slow the disease’s progression.

Written By: Lisa Magloff