Clinicians use AI device to remotely monitor COVID-19 patient
MIT researchers have demonstrated the remote home monitoring of a COVID-19 patient—including her breathing rates, walking speeds and sleep patterns—using an AI-enabled device stationed where the patient lives.
The feat may offer a way for physicians to watch for signs of deterioration in patients who have too mild a case of the disease to warrant hospitalization but may need quick response if the condition worsens.
It would do so while keeping hospital beds available for more serious cases of all kinds—and, no less importantly, reducing healthcare workers’ chances of contracting COVID themselves.
The modem-like device, called “Emerald,” isn’t entirely new. It’s been used in a number of hospitals and assisted-living facilities.
But the researchers behind its invention, Dina Katabi, PhD, and her team at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), have now successfully shown its usefulness with a consenting COVID-19 patient. The patient resides at an assisted-living facility elsewhere in Massachusetts.
Emerald emits very little radiation. Because it uses AI to infer vital signs, sleep and movement, its indications could expand to include monitoring other health problems, according to a news item filed by CSAIL communications officer Adam Conner-Simons.
Conner-Simons spoke with Ipsit Vahia, MD, a Harvard professor and geriatric psychiatrist who has used Emerald with a patient suffering from anxiety and insomnia. The device’s algorithms predicted the patient had sleep apnea. This was confirmed in follow-up exams.
“In just the last few weeks, there’s been a newfound urgency about developing remote-sensing technologies like Emerald that can help doctors do their jobs as safely as possible,” says Vahia. “Given how Emerald can generate important health data without any patient contact, it could minimize the risk that doctors and nurses will catch [COVID-19] from their patients.”
CSAIL professor Katabi says COVID-19 is particularly challenging for assisted living facilities and retirement homes, which house vulnerable elderly persons already beset by other conditions.
William McGrory, a clinical social worker who works with the assisted-living facility, adds that high-risk elderly patients “would greatly benefit from us being able to passively gather medical data over time when it is not possible to interface with each person directly.”
A pilot project is underway to see how well Emerald does at assessing dementia, according to MIT.
Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.