Skip to Content
Artificial intelligence

An AI system can diagnose childhood diseases better than some doctors

February 12, 2019

The new deep-learning system beat less experienced pediatricians at detecting illnesses including meningitis and flu.

The study: The system was trained on medical records from 1.4 million visits by 567,498 patients under 18 to a medical center in Guangzhou, China. A team distilled this information into keywords linked to different diagnoses, and then fed these into the system to help it detect one of 55 diseases.

How did it do? Pretty well. The system managed to diagnose conditions ranging from common ailments like influenza and hand-foot-mouth disease to life-threatening conditions like meningitis with 90% to 97% accuracy. Its accuracy was compared with that of 20 pediatricians. It managed to outperform the junior ones, but more senior doctors had a higher success rate. The findings are described in a paper in Nature Medicine this week.

Potential uses: AI systems have shown huge promise within the field of diagnosis. But they’re still a long way from replacing, rather than merely aiding, doctors. This sort of system could be useful for triage purposes in emergency care.

This story first appeared in our newsletter The Download. Sign up here to get your daily dose of the latest in emerging tech.

 

Deep Dive

Artificial intelligence

A Roomba recorded a woman on the toilet. How did screenshots end up on Facebook?

Robot vacuum companies say your images are safe, but a sprawling global supply chain for data from our devices creates risk.

The viral AI avatar app Lensa undressed me—without my consent

My avatars were cartoonishly pornified, while my male colleagues got to be astronauts, explorers, and inventors.

Roomba testers feel misled after intimate images ended up on Facebook

An MIT Technology Review investigation recently revealed how images of a minor and a tester on the toilet ended up on social media. iRobot said it had consent to collect this kind of data from inside homes—but participants say otherwise.

How to spot AI-generated text

The internet is increasingly awash with text written by AI software. We need new tools to detect it.

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.