Here’s a scenario: You find yourself sitting in a local emergency room, or standing in the admitting line of an emergency clinic. But instead of just cooling your heels (and having a cardboard tag tied around your neck, as Gulf Coast clinics did after Katrina), you’ve been given a fanny pack containing a pocket-sized computer and ultrasound transponder. And wires come out of it, leading to a sensor on your finger and some more on your chest. Now, if something happens – say, you quietly go into a cardiac arrest – the doctors will know and can come running.
At least that’s the vision of researchers at Brigham & Women’s Hospital in Boston, who are collaborating with colleagues from Harvard Medical School and MIT to test what they’re calling “Scalable Medical Alert and Response Technology” (SMART).
“In every disaster there is real lag time in keeping track of where the patients are,” says Tom Stair, a staff physician at the Brigham hospital. “You have to move one person out as a sicker person comes in, and later you’re asking, ‘Did she go to x-ray?’”
It’s a good idea to track emergency patients even under normal conditions, Stair says. “We’ve had them wander out of the ER waiting room and collapse in the bathroom, and not be found until it’s too late.”
After two and a half years of development, the SMART team plans to test its prototype system on actual emergency patients at the Brigham this summer. Each monitored patient would get a fanny pack containing a “pocket PC” from Hewlett-Packard (the iPaq h5500), says Dorothy Curtis, research scientist in computer science and artificial intelligence at MIT.
The device receives data from a blood oxygen sensor on the patient’s finger and three electrocardiogram sensors on the chest, then transmits the data via Wi-Fi back to a nurse’s station for monitoring. Software at the station issues an alert if a patient’s condition changes, Curtis says. The iPaq itself runs in “dark” mode, meaning it doesn’t emit beeps or flashes, which might startle the patient.
Also in the fanny pack is a transponder from Sonitor Technologies of Oslo, Norway, that allows the patient to be tracked with ultrasound. The researchers chose not to use radio-frequency tracking transponders primarily because they did not want the tracking signals to travel through walls. With a Sonitor sensor in each room, though, staff immediately know what room a patient is in, Curtis says. “We can’t tell what chair you’re in, but we can tell if you are in the waiting room versus the restroom or offsite, and that’s what we need,” Curtis says.
For the initial study, Stair hopes that 10 ER patients will agree to wear a SMART system for about an hour each during peak traffic periods at the Brigham’s emergency room, especially if they have chest pains or shortness of breath. “Who knows, we might find [the patients] are not as stable as we thought,” Stair says. He hopes to eventually gather a database on how patients flow through the ER and into the hospital, discover bottlenecks, and ultimately improve the operations of the Brigham hospital’s emergency room.
The researchers have gotten a $3 million grant from the National Library of Medicine to develop emergency-response technology. And they hope that a system like SMART might eventually be manufactured commercially.
But there are still plenty of bugs to work out, they say. For one thing, battery life needs to be longer, points out Robert Greenes, director of the Decisions Systems Group at the Brigham, who’s also on the SMART team. The current system leaves its electricity-hogging Wi-Fi transmitter on all the time. And for real-world use, Greenes says, the wires to the heart and oxygen sensors need to be replaced by wireless Bluetooth connections. “I want to move to another plateau and have a robust trial,” he says.
Home page image courtesy of Brigham and Women’s Hospital, Boston. Caption: Thomas O. Stair, M.D., research director, Brigham and Women’s Hospital Emergency Department and associate professor, Harvard Medical School, holding some of the SMART equipment.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
The walls are closing in on Clearview AI
The controversial face recognition company was just fined $10 million for scraping UK faces from the web. That might not be the end of it.
A quick guide to the most important AI law you’ve never heard of
The European Union is planning new legislation aimed at curbing the worst harms associated with artificial intelligence.
These materials were meant to revolutionize the solar industry. Why hasn’t it happened?
Perovskites are promising, but real-world conditions have held them back.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.