acm-header
Sign In

Communications of the ACM

ACM TechNews

Blood Test That Finds 50 Types of Cancer Accurate Enough to Be Rolled Out


The blood tests are accurate enough to be rolled out as a screening test.

A simple blood test developed using a machine learning algorithm can detect more than 50 types of cancer before any clinical signs or symptoms of the disease emerge in a person.

Credit: Getty Images

Researchers found that a blood test developed using a machine learning algorithm is accurate in detecting more than 50 types of cancer.

The test, which looks for changes in cell-free DNA shed by tumors into the bloodstream, was studied in 2,823 people with cancer and 1,254 people without; it accurately identifyied cancer at any stage in 51.5% of cases.

The false positive rate was just 0.5%, the researchers said.

The test was able to generate positive test results in 65.6% of cases involving solid tumors without screening options, twice as high as for solid tumors with screening options.

The tissue in which the cancer was located was accurately identified in 88.7% of cases.

Cleveland Clinic's Eric Klein said, "If used alongside existing screening tests, the multi-cancer detection test could have a profound impact on how cancer is detected and, ultimately, on public health."

From The Guardian (U.K.)
View Full Article

 

Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account