Skip to Content

"Plug and Play" Hospitals

Medical devices that exchange data could make hospitals safer.

The bewildering variety of new medical devices in U.S. hospitals promises higher standards of care. But it also poses new opportunities for error. A growing number of physicians believe that the interoperability of medical devices–their ability to communicate with each other–could make hospitals safer and more efficient.

Breathe in, breathe out: A ventilator and camera connected to a computer demonstrate how “plug and play” medical devices could help prevent medical errors. Traditionally, a doctor who wants to take an x-ray of a patient on a ventilator has to manually stop the device so that the lungs’ motion won’t blur the image. But that introduces the risk of accidentally leaving the ventilator off for too long. This experimental setup at Massachusetts General Hospital times photographs taken by a webcam so that they correspond to the full-exhalation or full-inhalation states of the ventilator.

“Today, there are many proprietary systems available from different vendors, but the problem is, these systems can’t talk to one another,” says Douglas Rosendale, a surgeon who works on information integration at Veterans Health Administration and Harvard Brigham and Women’s Hospital. “If they can’t interface, then they can’t share information, which could have an impact on patient care.” Estimates of the number of preventable deaths caused each year by medical errors in American hospitals range from 98,000 to 195,000.

Julian Goldman, director of the Center for Integration of Medicine and Innovative Technology’s Medical Device Interoperability Program, based at Massachusetts General Hospital, has developed two demonstration projects that illustrate the idea of the “plug and play” operating room. The first project is an integrated ventilator. A common problem in hospitals is taking chest x-rays of patients on ventilators, says Goldman. To keep the lungs’ movements from blurring the image, doctors must manually turn off the ventilator for a few seconds to take the x-ray. But then they run the risk of inadvertently leaving the ventilator off for too long, says Goldman.

To simulate an x-ray machine, Goldman used a webcam, which he connected to a ventilator and a computer. He synched the camera with the ventilator so that it would capture images only when the ventilator was at the point of full inhalation or exhalation. Goldman says that as a result of his demonstration, standards for ventilators are in the process of being revised so that future versions of the devices will include a pause function and will be subject to network control, moving toward interoperability.

“That’s an example where you actually avoid the risk by simply not having to turn off the ventilator at all,” says Peter Szolovits, a professor of computer science at MIT who studies medical data integration. “In other cases where you have a bunch of data simultaneously, you can do a better job of trying to understand what’s going on with the patient,” he says.

Device interoperability could also reduce the large number of false alarms that nurses must contend with. “If you go into an ICU, it’s a madhouse,” says Szolovits. “There are alarms going off constantly, because each alarm is separate from the others, so none of them have an integrated view of what’s going on with the patient.” If the data from medical monitors were integrated, he says, alarms would be more likely to indicate something truly important.

Goldman’s second plug-and-play demonstration simulates a self-administering pain medication pump, a device widely used in hospitals despite its occasional adverse effects. Monitoring devices strive to eliminate the risk that patients will accidentally overdose, but they set off many false alarms. Goldman speculated that if a computer received data from two or more monitoring devices, it could much more easily distinguish false emergencies from real ones. In his demonstration, simulated patient data is fed to an oximeter and a respiratory monitor. The program sounds an alarm only when both sensors suggest that the patient is undergoing a crisis.

Goldman admits that, while his demos are relatively straightforward, obstacles to device interoperability remain. Monitoring systems are expensive for hospitals to replace, he says: “We’ve made it too difficult to integrate systems to have smart alarms.” Another barrier is old-fashioned competitiveness. A vendor that produces medical equipment tends to make its devices compatible only with each other.

But as Goldman points out, many emergency rooms need such specialized equipment that no one vendor can produce all of it. So selecting a single vendor won’t solve the interoperability problem. “We’re probably a ways off from true interoperability,” Rosendale says. “However, there is clearly momentum growing in this area. As computer technology and device dependence grows, that means interoperability is going to be more and more obvious.”

“I think everyone recognizes that there’s a lot of data generated for patients, but it’s not always used as effectively as it could be,” says Daniel Nigrin, chief information officer and senior vice president for information services at Children’s Hospital Boston. “Over the course of the last 5 to 10 years, there have been several studies that came out that showed basically that there’s room for enormous improvement in reducing errors in medicine. That’s why efforts like [Goldman’s are] so crucial.” Nigrin suggests that hospitals are slowly starting to move toward medical devices that share data with one another and with electronic medical-record systems. “There are instances where you’re starting to see some of the devices connected. Whether that’s having monitoring systems or ventilator systems attached to electronic medical records, you’re starting to see some systems like that implemented in a real-world environment,” he says.

Keep Reading

Most Popular

The inside story of how ChatGPT was built from the people who made it

Exclusive conversations that take us behind the scenes of a cultural phenomenon.

How Rust went from a side project to the world’s most-loved programming language

For decades, coders wrote critical systems in C and C++. Now they turn to Rust.

Design thinking was supposed to fix the world. Where did it go wrong?

An approach that promised to democratize design may have done the opposite.

Sam Altman invested $180 million into a company trying to delay death

Can anti-aging breakthroughs add 10 healthy years to the human life span? The CEO of OpenAI is paying to find out.

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 with a list of newsletters you’d like to receive.