With the use of artificial intelligence, researchers can screen hard-to-detect cancers
Every once in a while, medical researchers have a stroke of good luck. In this case, ‘stroke of good luck” has a profound effect on the medical community. This time, in a study involving thousands of participants, a new blood test detected more than 50 types of cancer.
An international team of researchers led by Dana-Faber Cancer Institute and Mayo Clinic also revealed that they can detect the locations of the cancers within the body with a high degree of accuracy. Researchers say the blood test can not only detect whether someone has cancer but can also put light on the type of cancer they have.
The blood test is based on DNA that is shed by tumors and found circulating in the blood. More precisely, it focuses on chemical changes to this DNA, known as methylation patterns.
Published online by the Annals of Oncology, indicate that the blood test — the team reveal how the test was developed using a machine learning algorithm — a type of artificial intelligence. In the process, the systems pick up on patterns within data and as a result, learn to classify it.
Dr. Geoffrey Oxnard of Boston’s Dana-Farber Cancer Institute, part of Harvard Medical School said, “You need to use a test like this in an independent group at risk of cancer to actually show that you can find the cancers, and figure out what to do about it when you find them.”
The study
In the study, the team initially fed the system with data on methylation patterns in DNA from within blood samples taken from more than 2,800 patients, before further training it with data from 3,052 participants, 1,531 of whom had cancer and 1,521 of whom did not.
“In pregnant women we look in their free-floating DNA for foetal abnormalities,” said Oxnard. “We know this [approach] exists, the question is how do you fine-tune and perfect the art of looking for cancer in this free-floating DNA? And that is what the machine learning did.”
The results reveal that less than 1% of those without cancer were wrongly identified by the system as having the disease. Detection was better the more advanced the disease was. Overall, cancer was correctly detected in 18% of those with stage I cancer, but in 93% of those with stage IV cancer.
