Researchers Say a Blood Test, AI May Help Detect Cancer Long Before People Show Symptoms
A non-invasive test named PanSeer may help detect cancer in individuals who haven’t developed symptoms yet, according to research published in Nature Communications. This test does not pick up on all types of cancer, but can detect cancerous growths that do not show symptoms, or are undetectable by other methods. Therefore, it is important to note that this test cannot predict the likelihood of an individual developing cancer.
As of now, this test shows, “95% accuracy rate in detecting cancer in asymptomatic individuals who were later diagnosed.” This number is impressive, but researchers caution that future longitudinal studies are required to confirm this result.
What this test provides is a non-invasive means to aid early detection of cancer. As of now, very few early screening tests exist, and that too, for very few cancer types. When cancer is detected early, patient survival rates increase significantly. This is because identifying the disease in its early stage helps cull its spread, and allows doctors to either surgically remove tumors or treat them with appropriate drugs.
Related on The Swaddle:
The test is done as a liquid biopsy, in which blood samples are used to detect stray cancer cells, or DNA from tumors. Researchers first took samples of patients’ blood plasma and searched for tumor DNA via looking for telltale compounds like methyl groups. Their process was able to find extremely small quantities of such DNA, which aided accuracy. Then, researchers used artificial intelligence to develop algorithms that can determine if the DNA circulating in blood belonged to tumors, in order to speed up the process.
“The ultimate goal would be performing blood tests like this routinely during annual health checkups,” Kun Zhang, co-author and chair of the Department of Bioengineering at the University of California San Diego, said in a statement. He added, “But the immediate focus is to test people at higher risk, based on family history, age or other known risk factors.”