Imagine a box, similar to a Wi-Fi router, that sits in your home and tracks all kinds of physiological signals as you move from room to room: breathing, heart rate, sleep, gait, and more.
Dina Katabi, a professor of electrical engineering and computer science at MIT, built this box in her lab. And in the not-so-distant future she believes it will be able to replace the array of expensive, bulky, uncomfortable gear we currently need to get clinical data about the body.
Speaking at MIT Technology Review’s EmTech conference in Cambridge, Massachusetts on Wednesday, Katabi said the box she’s been building for the last several years takes advantage of the fact that every time we move—even if it’s just a teeny, tiny bit, such as when we breathe—we change the electromagnetic field surrounding us.
Her device transmits a low-power wireless signal throughout a space the size of a one- or two-bedroom apartment (even through walls), which reflects off people’s bodies. The device then uses machine learning to analyze those reflected signals and extract physiological data. So far, it has been installed in over 200 homes of both healthy people and those with diseases like Parkinson’s, Alzheimer’s, depression, and pulmonary diseases, she said. Katabi cofounded a startup called Emerald Innovations to commercialize the technology, and has already made the device available to biotech and pharmaceutical companies for studies.
To illustrate how this could be helpful, Katabi also showed off data gathered over eight weeks in a Parkinson’s patient’s home, indicating his gait improved around 5 or 6 a.m. each morning—right around when he took his medication.
“Not only do you start understanding the life of the patient, but you start understanding the impact of the medication,” she noted, which could also help doctors figure out how some medications help certain patients but not others.
Katabi also said that her research found the device can accurately monitor sleep, including individual sleep stages, in a person’s own bed, with no changes to the way they sleep or what they wear—a big difference from today’s status quo, where accurately tracking sleep typically calls for snoozing in a lab setting with a lot of electrodes and wires connected to your body. Because the device would be installed in a person’s home, it could track them over time, too, which could be useful for watching conditions like Alzheimers or depression where sleep disruption occurs, she said.
It might sound alarming to have anything in your home that is constantly tracking you, as it could be ripe for snooping or other kinds of abuse. Katabi said the data is only collected about specific traits with a person’s consent, is encrypted, and is limited to certain designated recipients. And don’t worry about a rogue neighbor pointing this box in your direction: Katabi said the setup process requires a user to complete a series of specific movements before they can be tracked, so it would be very difficult to secretly follow an unwilling participant.
While Katabi is currently focused on healthcare applications for the data, she’s also considering how it could be used for other things, like fine-tuning your smart home so when you sit on the couch your smart TV could put on your favorite show.
