Skip to Content

Plug-and-Play Medicine

A step toward letting medical devices communicate.
September 18, 2009

In a key practical step toward the long-sought goal of linking different hospital devices together to better manage patients and their care, a Boston research group has come up with a software platform for sharing information among gadgets ranging from blood-pressure cuffs to heart-lung machines.

Plug and play: Two pulse oximeters, which measure blood oxygen levels, are linked with hardware that uses data from either device to control an intravenous drug device (not shown).

“The vision of fully interoperable medical devices has been around for at least a quarter-century, but lack of adequate standards and lack of manufacturers’ desire to foster such integration has left us in a kind of Dark Ages,” says Peter Szolovits, an MIT computer scientist in the Harvard/MIT Division of Health Sciences and Technology, who was not involved with developing the new standards. He adds that they are “a critical component of making health-care information technology smarter, safer, and more efficient.”

When doctors disconnect a heart-lung machine after finishing heart surgery, they need to turn on the ventilator quickly, or the patient will suffer brain damage. Right now, however, there is no way for the heart-lung machine to sense whether the ventilator was switched on correctly and keep running if it wasn’t. Even the most high-technology medical devices used in hospitals don’t “talk” to each other in the way that, say, your PC “talks” to your printer.

The new standards for the Integrated Clinical Environment (ICE)–written by a research group convened by the Center for Integration of Medicine and Innovative Technology (CIMIT), a hospital/academic consortium in Boston–consist of a set of high-level design principles. Among other things, the standard says that an ICE must include a device analogous to a jet airliner’s “black box” that collects data. This black box will initially prove that integrating different systems can be safe enough to win regulatory approval. But in everyday practice, it will also be crucial to troubleshooting and improving interoperability. The standard also says that there must be only one overarching algorithm that interprets data from all connected machines to avoid conflicting instructions or warnings; and that if one piece fails, the failure must not be able to spread to other parts of the system.

“This is about building a comprehensive platform, like the Web, that allows the global community to innovate and build cool things on top of it that improve patient safety,” says Julian Goldman, director of CIMIT’s Medical Device Interoperability Program, who led the group that developed the standards, which will be published this fall by the standards body ASTM International.

“Any technologically sophisticated person would assume that if you are receiving a potent intravenous medication in a hospital, and at the same time your blood pressure is being measured by an automated cuff every 15 minutes, that we have a way to [automatically] stop that medication infusion if it causes your blood pressure starts to fall or rise rapidly,” says Goldman, who is also an anesthesiologist at Massachusetts General Hospital and medical director of Partners HealthCare Biomedical Engineering, “but it’s impossible to do that today.”

This lack of interoperability can lead to serious errors. It also means that clinicians waste time chasing false alarms set off by individual gadgets. For example, today’s telemetry monitors track heart rhythms, while other gadgets monitor heart rate and levels of blood oxygen. Sudden changes in activity and movement can cause sudden heart-rhythm fluctuations, triggering urgent warnings. But such alarms could be eliminated if an integrated system also checked heart rate and oxygen levels; if these were unchanged, no heart-attack warning would be necessary.

David Osborn, manager of international standards at Philips Healthcare, says that while the new standards will help, “the document put together so far is a high-level framework. The devil is in the details, and the details haven’t been written yet.” However, he adds, “harm is occurring to patients more often than we’d like to admit, and this can be a step toward a solution, if we can get beyond the framework.”

Szolovits says that the eventual goal is an integrated clinical environment, in which all devices are interconnected, in plug-and-play fashion, for better management. Currently, devices made by different manufacturers operate on their own, and, in general, they cannot communicate with one another. Several medical associations, including the American Medical Association, have called for interoperability.

“Even at leading modern hospitals, I have seen pulmonary technicians run around the foot of a patient’s bed to transfer ventilator settings from a device on one side of the bed to a computer system on the other,” says Szolovits. “Not only is such a process laughable to watch, but it increases the risk of errors, corrupts data, and possibly even puts patients at risk.”

Keep Reading

Most Popular

open sourcing language models concept
open sourcing language models concept

Meta has built a massive new language AI—and it’s giving it away for free

Facebook’s parent company is inviting researchers to pore over and pick apart the flaws in its version of GPT-3

transplant surgery
transplant surgery

The gene-edited pig heart given to a dying patient was infected with a pig virus

The first transplant of a genetically-modified pig heart into a human may have ended prematurely because of a well-known—and avoidable—risk.

Muhammad bin Salman funds anti-aging research
Muhammad bin Salman funds anti-aging research

Saudi Arabia plans to spend $1 billion a year discovering treatments to slow aging

The oil kingdom fears that its population is aging at an accelerated rate and hopes to test drugs to reverse the problem. First up might be the diabetes drug metformin.

Yann LeCun
Yann LeCun

Yann LeCun has a bold new vision for the future of AI

One of the godfathers of deep learning pulls together old ideas to sketch out a fresh path for AI, but raises as many questions as he answers.

Stay connected

Illustration by Rose WongIllustration 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.