Skip to Content
Uncategorized

Raising the IQ of Critical Care Units

January 1, 1999

Anyone who has recently kept a bedside vigil in a hospital’s intensive care unit (ICU) is likely to have been impressed by just how much information is now gathered on a critically ill patient. Sophisticated monitors surround the bed, the electronic screens spewing out a torrent of data. That information can be vital, particularly for those near death. But it also poses a critical challenge for today’s hurried nurses and physicians: how to make sense of all that data.

To help out, researchers at the University of Pennsylvania Medical Center are testing a “smart” ICU technology that collects and analyzes a patient’s vital signs. The artificial-intelligence system produces a 3-D graph that could make it easier for a clinician to quickly pick up any warning signs. The smart ICU uses adapted off-the-shelf software for neural networks and fuzzy logic that allows it to analyze several measurements simultaneously, looking for dangerous trends; it can also “learn” the patterns of a patient, including their ideal vital signs.

“It’s not intended to replace a physician,” says C. William Hanson, section chief of anesthesia/critical care at the medical center and developer of the technology. “It’s intended to act as an intelligent assistant that’s vigilant.” Patients in the ICU, says Hanson, are “monitored for everything we can monitor electronically, and there’s very sophisticated minute-by-minute information” on everything from respiratory rates to blood flow. But actual analysis of the data “is, in reality, totally unsophisticated,” says Hanson. “There’s hidden information in a lot of that stuff.”

By uncovering that information, the smart ICU will, if it works, flag dangerous conditions soon after they develop. For example, says Hanson, blood accumulating around the heart can be a serious problem for some patients, but it’s often not noticed until the individual’s blood pressure significantly falls. In fact, there are early warning signs, including a series of interrelated, predicting signals, such as a drop in blood pressure and an increase in heart rate. While “a really good clinician” would likely notice those indicators, says Hanson, that “presupposes that there’s a really good, experienced clinician-and that they’re at the bedside.”

Preliminary real-life tests of the system are under way. Hanson notes that the medical center’s ICU is already installing a PC at every bedside that will collect information from the monitors and act as an electronic spreadsheet. “In the world of information technology, that’s a fairly trivial thing to do,” says Hanson. “There are a lot more interesting things the PCs can do. There’s still a lot of smartening up that can go on in the ICU.”

In today’s busy hospitals, a more intelligent ICU can only be a good idea.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

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 customer-service@technologyreview.com with a list of newsletters you’d like to receive.