New Blood Test's Promising Results Detect Over 50 Types of Cancer Early

Scientists use the test to study DNA that tumors release to identify patients with cancer even before they show symptoms.

Fabienne Lang

| Apr 01, 2020 06:18 AM EST

Created: Apr 01, 2020 06:18 AM EST

science

photovs/iStock

Stay ahead of your peers in technology and engineering - The Blueprint

By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.

A new blood test that's been developed by scientists used samples from 4,000 people and could detect over 50 types of cancers, sometimes even before symptoms arise.

Moreover, the test was accurate in detecting 12 of the most dangerous forms of cancer, including pancreatic cancer which is usually only detectable at a late stage.

This new test could help save the lives of millions of people as it could detect cancer at a very early stage.

The study was published in Annals of Oncology.

The race against cancer

Many research groups around the world are looking to find methods to identify cancer at an early stage. One such group of scientists includes Michael Seiden, president of U.S. Oncology, who explored different ways of testing for cancer-based on sequencing the DNA tumors shed into the bloodstream.

See Also

RT @BwOtenyo: RT @SwissCognitive: A new blood test that can detect more than 50 types of cancer has been revealed by researchers in the latest study to offer hope for early detection. The system uses #MachineLearning to offer new way to screen for hard-to-detect cancers

…
— Machine Learning (@machine_ml) April 1, 2020

Furthermore, the team discovered that looking at methylation patterns of approximately 1 million sites in DNA proved to be the most promising approach. Methyl groups are chemical tags added to genes in order to inactivate them, and DNA that comes from cancer cells has abnormal methylation patterns.

After this, the team worked on a machine learning system that took information from blood samples of 1,500 people with untreated cancer and 1,500 with no cancer. The system then analyzed these samples.

The specificity percentage of the machine learning system was 99.3%, meaning 0.7% of people were wrongly diagnosed with cancer. "Specificity is extremely important because you don’t want to raise false alarm in people who are well," warned Seiden.

The proportion of cancers detected varied depending on how advanced the cancers were. For instance, for those with one of the 12 most deadly cancers (anal, bladder, bowel, esophageal, stomach, head and neck, liver and bile duct, lung, ovarian and pancreatic cancers, lymphoma, and cancers of white blood cells such as multiple myeloma), the true positive rate was 39% in stage 1, 69% in stage 2, 83% in stage 3, and 92% in stage 4.

Now the test is being trialed on a larger group of people.

A blood test that screens for more than 50 types of cancer could help doctors treat patients at an earlier stage than previously possible,a new study shows. https://t.co/dsmeVfa6gk
— DW News (@dwnews) March 31, 2020

Seiden stated "Considering the burden of cancer in our society, it is important that we continue to explore the possibility that this test might intercept cancers at an earlier stage and, by extension, potentially reduce deaths from cancers for which screening is either not available or has poor adherence."

Professor Fabrice André, editor-in-chief of Annals of Oncology, stated "This is a landmark study and a first step toward the development of easy-to-perform screening tools. Earlier detection of more than 50% of cancers could save millions of lives every year worldwide and could dramatically reduce morbidity induced by aggressive treatments."

Add Interesting Engineering to your Google News feed.

SHOW COMMENT (1) chevron

Job Board