This neural network can diagnose pneumonia better than your doctor
This could save millions of lives

"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."
A free daily email with the biggest news stories of the day – and the best features from TheWeek.com
The Week
Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

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.
-
Taking aim at Venezuela’s autocrat
Feature The Trump administration is ramping up military pressure on Nicolás Maduro. Is he a threat to the U.S.?
-
Comey indictment: Is the justice system broken?
Feature U.S. attorney Lindsey Halligan has indicted former FBI Director James Comey on charges of lying and obstructing Congress
-
Government shuts down amid partisan deadlock
Feature As Democrats and Republicans clash over health care and spending, the shutdown leaves 750,000 federal workers in limbo