Skip to content

IBM’s Watson gives proper diagnosis for Japanese leukemia patient after doctors were stumped for months

IBM's Watson was able to come up with the proper diagnosis after sifting through 20 million cancer research papers within 10 minutes.
AP
IBM’s Watson was able to come up with the proper diagnosis after sifting through 20 million cancer research papers within 10 minutes.
Author
PUBLISHED: | UPDATED:

It turns out the world’s smartest supercomputer is a pretty good doctor, too.

Five years after dominating geniuses in its debut on Jeopardy!, IBM’s Watson is still putting human intelligence to shame.

The artificial intelligence machine correctly diagnosed a 60-year-old woman’s rare form of leukemia within 10 minutes — a medical mystery that doctors had missed for months at the University of Tokyo.

Doctors were stumped after treatment for the original leukemia diagnosis didn’t work, leading them to plug the patient’s genetic information into Watson’s program for answers, the University of Tokyo reported.

The supercomputer sifted through 20 million cancer research papers, and came up with the proper diagnosis within 10 minutes, suggesting a new treatment that has since been more effective, according to Silicon Angle.

The supercomputer first “enrolled” in medical school at Columbia University in 2011, as well as at the University of Maryland School of Medicine. There, Watson was loaded up with medical cases and millions of pages of research papers. The program also went through several sessions with doctors, being corrected whenever it gave a wrong answer.

Watson graduated from its medical residency in 2013, becoming available for doctors and health insurance companies shortly after. IBM claimed Watson had improved its performance by 240% from 2011 to 2013.

Last January, the supercomputer took its talent to the kitchen, teaming up with the Institute of Culinary Education to create recipes with its massive database of ingredients, chemical breakdowns of food, flavor combinations and nutritional details.