In a possible first in Japan, doctors have used artificial intelligence to diagnose a rare type of leukemia and identify life-saving therapy far faster than if they had examined the genetic data manually.
According to Arinobu Tojo, professor of molecular therapy at a hospital affiliated to the University of Tokyo’s Institute of Medical Science, a female patient in her 60s admitted in January 2015 was initially diagnosed with acute myeloid leukemia, a blood cancer characterized by rapid growth of abnormal white blood cells.
She underwent chemotherapy at the hospital, which successfully attacked the cancer cells.
However, her recovery from post-remission therapy was unusually slow. Tojo said this led doctors to suspect a different type of leukemia, though conventional tests failed to show any sign of it.
That was when the institute turned to IBM’s Watson, a cloud-based AI-powered computer system that has ingested tens of millions of oncology papers and vast volumes of leukemia data made available by international research institutes.
To find out more about the cause of her illness, the researchers supplied the woman’s genetic data, and Watson cross-checked it with the database, detecting gene mutations that are unique to a particular type of leukemia.
“This patient had mutations in more than 1,000 genes, but many of them were not related to her disease and they were just hereditary characteristics she had inherited from her parents,” Tojo said. “While it would have taken about two weeks for human scientists to check which of the 1,000 changes were diagnostically important or not, Watson did it in 10 minutes.”
Based on Watson’s analysis, Tojo’s team concluded that the case was one of rare secondary leukemia caused by myelodysplastic syndromes, a group of diseases in which the bone marrow makes too few healthy blood cells.
The doctors changed the patient’s therapy plan, after which her condition improved significantly. She was discharged from the hospital in September, Tojo said.
“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,” he said. “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.”
The university hospital has collaborated with Watson since July last year. So far, the hospital has used the computer system for about 100 patients with hematological diseases, Tojo said, adding that Watson has helped find causes of illnesses for 70 to 80 of them.
“Right now the system is not perfect as it occasionally makes mistakes,” Tojo said. “But in 10 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.”