This neural network can diagnose pneumonia better than your doctor

"Add diagnosing dangerous lung diseases to the growing list of things artificial intelligence can do better than humans," said Jackie Snow at MIT Technology Review. Researchers from Stanford University have developed a neural network that can "beat radiologists at spotting pneumonia" on chest X-rays. When the network's algorithm was expanded, it also proved better than doctors at identifying 13 other diseases. More than 1 million adults are hospitalized with pneumonia each year in the U.S.

The illness is also "the single largest infectious cause of death" for children worldwide, so early detection could save millions. Radiologists and other physicians are "on notice," say the researchers. Other AI experiments have produced algorithms that can "identify heart arrhythmias better than a human expert" and spot cancerous skin lesions "just as well as a board-certified dermatologist."

Subscribe to The Week

Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

SUBSCRIBE & SAVE

Sign up for The Week's Free Newsletters

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

Sign up