Skip to Content

Wireless Detectors for Dementia

Researchers hope that radio transmitters can warn of cognitive decline earlier.

Researchers at the University of South Florida (USF) have developed a wireless network that evaluates walking patterns in an attempt to detect early signs of dementia.

Walking patterns: The RFID transponder shown here weighs 40 grams. It sends information about the walking patterns of residents at an assisted-living center in Florida, which may reveal early signs of dementia.

Currently, doctors ask patients to answer a series of questions to determine whether they may be suffering from Alzheimer’s or another form of dementia. But by the time a patient is diagnosed, she may have already begun to experience symptoms such as memory loss. Drugs that are currently available can only slow the progression of related diseases, so the earlier dementia is caught, the better a patient’s treatment will be.

Researchers are exploring ways to identify the condition earlier–for example, by detecting biomarkers, conducting new brain scans, or monitoring movements such as walking. The USF researchers have developed an RFID system that allows walking patterns to be monitored in a natural setting.

“We’re looking at a device that may help us perform early detection [of dementia] as a way of ensuring that [older] people get the best remaining years they can,” says William Kearns, an assistant professor who researches aging and mental health at USF. In particular, dementia increases the risk of injury caused by a fall. “That’s a huge problem for assisted-living facilities,” he says.

To test the approach, the USF researchers put RFID tags on the wrists of residents at two assisted-living homes in Florida. These tags transmitted signals that were picked up by receivers placed around each building, revealing the wearer’s movements in all three spatial dimensions to within 10 inches of accuracy.

The researchers analyzed participants’ movements for telltale signs of cognitive decline: a tendency to wander, veer suddenly, or repeatedly pause. In a study involving 20 residents the researchers found a statistical relationship between those who showed abnormal walking patterns and those whose mental test scores indicated dementia. In the future, the USF team plans to develop software that will automatically detect these warning signs.

Others are exploring RFID technology as a low-cost way to improve elder care. In 2004, Intel launched a project that used passive RFID tags attached to objects to monitor individuals’ everyday activities. This approach can warn a caregiver to check, for example, that a patient has taken his medicine that day. Other systems, such as Accutech’s ResidentGuard, send an alarm when users wearing an RFID bracelet venture beyond a designated zone, in order to prevent those with dementia from wandering.

Donald Patterson, a professor of informatics at the University of California, Irvine, says that the USF approach is more straightforward than those designed to monitor complex activities. “The more you get into the straight biological measurements … the easier it becomes,” he says.

The USF technique relies on highly accurate RFID equipment. The ultra-wideband (UWB) chips used suffer less interference than do passive RFID chips and can send and receive signals through walls. The transmitters have a range of 600 feet and allow multiple people to be monitored even in a crowded room. The tags have batteries that last up to three years and accelerometers that put them into sleep mode when the user is motionless. According to Kearns, the entire system, including half a dozen tags, costs around $7,000 to implement.

Tanzeem Choudhury, an Intel researcher who uses RFID to gather social information, says that RFID technology is useful because it is so simple. “It’s great they’re showing a correlation with these [RFID tags],” she says.

Although walking patterns have been tied to dementia in previous studies, some experts question the approach. “There are a lot of factors that influence movement, and the disease in its very early stages is not a movement disease,” says Robert Green, codirector of the Alzheimer’s Disease Clinical and Research Program at Boston University. Green also points out that the USF researchers only looked for post-symptomatic dementia in their test.

However, Lisa D’Ambrosio, a research scientist at MIT’s AgeLab, believes that the approach may be worth exploring. “It’s a very interesting application of RFID technology,” she says. “One of the trends in a lot of the neurology work is to move toward trying to diagnose Alzheimer’s disease and cognitive impairment earlier.”

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.