Can a robot treat patients as well as a human? That’s the question behind a new study involving an “artificially intelligent pediatrician“—and the results could help a lot of kids.
Researchers at the University of California in San Diego trained an AI by using medical records from over one million patients. The records included illness history, laboratory test results and notes written by doctors. When tested on previously unseen cases, the AI pediatrician was able to diagnose glandular fever, roseola, influenza, chicken pox and hand-foot-mouth disease with 90 and 97 percent accuracy. Whoa!
photo: Walt Disney Animation Studios via YouTube
“When you’re busy you can see 80 patients a day. And you can only grasp so much information. That’s where we potentially as human physicians might make mistakes. AI doesn’t have to sleep, it has a large memory and doesn’t lose energy,” said Kang Zhang, lead study author.
This doesn’t mean you’ll be seeing a robot in your pediatrician’s office for your next appointment. The AI is still reliant on a human being to be in the room with patients discussing symptoms and inputing data into the system. However, the use of artificial intelligence in hospitals and doctors offices could help cut down on wait times and help new doctors with confirming diagnosis on patients. The team is now working training the AI to diagnose adult patients as well.
“Given sufficient data, AI should be able to tell if this is an urgent situation and needs referral or if it’s a cold,” says Zhang. He continues, “You don’t want to go to the emergency room and wait five hours because you have some pain in the abdomen that’s not appendicitis but just related to gastroenteritis or the food you ate. All those diseases have tell-tale signs, and just as we physicians ask a series of questions to drive a diagnosis, AI can do the same.”
What a time to be alive.