Researchers have developed a new machine learning model to detect cancers that are in the early stages of disease by examining DNA fragments from cancer cells in the blood.
A research team from the University of Wisconsin-Madison was able to detect cancer in the blood in most of the samples tested, he said.
Muhammed Murtaza, a professor of surgery at the UW School of Medicine and Public Health based in Madison, Wisconsin, led the study, which was recently published in Science Translational Medicine, a medical journal of the American Association for the Advancement of science, according to the study’s press release.
KIRSTIE ALLEY’S ‘RECENTLY DISCOVERED’ COLON CANCER BATTLE: WHAT TO KNOW ABOUT THE DISEASE
“We are incredibly excited to find that early detection and monitoring of multiple cancer types is potentially feasible using such a cost-effective approach,” Murtaza said in the press release.
Earlier detection of many cancers will lead to better patient outcomes, the statement noted.
“We are incredibly excited to find that early detection and monitoring of multiple cancer types is potentially feasible using such a cost-effective approach,” says the lead author of a new study.
(Stock)
Although other scientists are also developing blood tests to detect cancer earlier, current technology has limitations, such as the cost and “sensitivity” of the test.
Sensitivity, in this case, refers to the ability of the test to correctly detect the presence of cancer, according to the Centers for Disease Control and Prevention (CDC).
How is the test going?
When cells die as part of the body’s natural cell renewal process, fragments of DNA are released outside the cells. These start circulating in the bloodstream, namely plasma, which is the liquid part of blood, according to the researchers.
“It should be focused on patients who have significant family histories or personal risk factors, or who have genetic syndromes associated with multiple cancers.”
The research team hypothesized that cancer cells have DNA fragments that are different from healthy cells, particularly where DNA strands “break”. Nucleotides, which are the “building blocks of DNA”, surround these breakpoints.
ALZHEIMER’S DISEASE MAY BE DETECTABLE BY KEY FLOOD TEST, STUDY FINDS
The research team used a special technique that the study named Genome-wide AnaLYsis of FRagment Ends – or GALYFRE – to analyze “cell-free” DNA from 521 samples.
For a new study, a research team from the University of Wisconsin-Madison also “sequenced” data from 2,147 additional samples from two groups of people: healthy individuals – and patients with 11 types of different cancers.
(Stock)
The team also “sequenced” data from 2,147 additional samples from two groups of people: healthy individuals and patients with 11 different types of cancer.
“DNA sequencing means determining the order of the four chemical building blocks – called ‘bases’ – that make up the DNA molecule,” according to the National Institutes of Health’s Human Genome Research website.
‘EYE’ ON LIFE: WOMAN GOES VIRAL TO SHOW HOW SHE INSERTS ARTIFICIAL EYE AFTER BATTLE WITH CANCER
“The sequence tells scientists what kind of genetic information is contained in a particular segment of DNA.”
The research team then used these analyzes to develop a metric that could reflect the proportion of cancer-derived DNA molecules in each sample.
Machine learning model
They combined this measurement with the genetic information found on the DNA fragments to develop a model that trains a machine to compare DNA fragments from healthy cells to DNA fragments from different types of cancer cells.
“The sequence tells scientists what kind of genetic information is contained in a particular segment of DNA.”
This model differentiated people with cancer at any stage of their diagnosis from people without cancer 91% of the time.
It also “accurately identified samples from patients with stage 1 cancer in 87% of cases, suggesting it has promise for detecting cancer at an early stage,” the statement said.
The research team hopes to do more clinical studies to validate the blood test for specific cancers, such as pancreatic cancer and breast cancer.
(Stock)
The study, while promising, notes that further research is needed to apply the use of GALYFRE to patients of different age groups and those with multiple medical conditions.
Refinement needed for the future
The research team hopes to do more clinical studies to validate the blood test for specific cancers, such as pancreatic cancer and breast cancer.
“One direction we are taking is to refine GALYFRE to make it even more accurate for certain patients who are at risk of developing specific types of cancers,” Murtaza noted in the release.
RETIREMENT EARLY COULD HARM YOUR HEALTH: NEW STUDY
His team is also looking to see if this technology can be used not only for early detection of cancers, but also to monitor how chemotherapy patients respond to cancer treatments.
The researchers hope “this work will lead to a blood test for cancer detection and monitoring that will be clinically available within the next 2-5 years for at least some conditions.”
“I find that the use of cell-free DNA and a liquid biopsy will be most helpful for patients with a known cancer diagnosis and [for] post-treatment to monitor disease recurrence — avoiding the need for [high-risk] biopsy,” Dr. Oren N. Gottfried, a professor at Duke University School of Medicine in Durham, North Carolina, told Fox News Digital.
“This is especially true with brain cancer, where every brain biopsy carries considerable risk,” added Gottfried, who is also a neurosurgeon.
CLICK HERE TO SUBSCRIBE TO OUR HEALTH NEWSLETTER
“In general, as a screening tool, I think it should be focused on patients who have significant family histories or personal risk factors, or who have genetic syndromes associated with multiple cancers.”
CLICK HERE TO GET THE FOX NEWS APP
Murtaza of the UW School of Medicine and Public Health hopes that with further research and development, “this work will lead to a blood test for the detection and monitoring of cancer that will be clinically available within 2 to next 5 years for at least some conditions – and ultimately be accessible to patients with limited healthcare resources in the United States and around the world,” he said in the press release.