IBM’s Watson Detected Rare Leukemia In Just 10 Minutes

The supercomputer swiftly cross-referenced a patient’s genetic data to make a diagnosis that would have taken a human doctor weeks.

AsianScientist (Aug. 15, 2016) – We’ve previously asked the question of whether disease diagnosis can be performed by artificial intelligence; that is, without human doctors. In a world where big data is fast transforming healthcare across the globe, PCs could not only assist GPs, but eventually, replace them.

Now, it appears that IBM’s supercomputer Watson has greatly speeded up the diagnosis of a rare form of leukemia in a patient, and in doing so, may have saved her life.

In January 2015, the patient was admitted to a hospital affiliated to the University of Tokyo’s Institute of Medical Science in Japan. Doctors initially diagnosed her with acute myeloid leukemia, a type of blood cancer.

After a successful round of chemotherapy however, the doctors observed that her recovery from post-remission therapy was unusually slow, leading them to believe that they were looking at a different type of leukemia.

Here, the hospital’s research team looked to Watson for a solution. The cloud-based, artificial intelligence-powered supercomputer is capable of cross-referencing and analyzing data from tens of millions of oncology papers from research institutes all over the world. From vast volumes of data, it can instantly pull out the information it needs, much faster than humans can.

By cross-referencing the patient’s genetic data with its own database, Watson detected over a thousand genetic mutations in her DNA. More importantly, the supercomputer could filter out which of the thousand were diagnostically important and not just hereditary characteristics that were unrelated to her disease.

Remarkably, Watson accomplished this feat in just ten minutes—human scientists would have taken two weeks.

“We would have arrived at the same conclusion by manually going through the data, but Watson’s speed is crucial in the treatment of leukemia, which progresses rapidly and can cause complications,” Professor Arinobu Tojo, who led the research team, was quoted by The Japan Times as saying.

“It might be an exaggeration to say AI saved her life, but it surely gave us the data we needed in an extremely speedy fashion.”

Watson’s quick work helped the researchers to conclude that the patient had a rare secondary leukemia caused by myelodysplastic syndromes, a group of diseases in which the bone marrow makes too few healthy blood cells.

As remarkable as Watson may be at number-crunching and data-dicing, it still makes mistakes, according to Tojo. But he noted that in ten years or so, its quality will improve to such a degree that it will be common for doctors to use genetic tests in cancer treatment.


Copyright: Asian Scientist Magazine; Photo: Shutterstock.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.

Coming from a design background, Filzah brings a fresh perspective to science communications. She is particularly interested in healthcare and technology.

Related Stories from Asian Scientist