According to the latest reports, it seems that cancer detection can be made sooner with the help of looking for repetitive DNA in blood. Check out the latest reports about this below.
New breakthrough in cancer detection
It is possible that a routine blood test can detect cancer in its early stages before it becomes uncontrollable. Recent research published in Science Translational Medicine shows that this possibility may become a reality soon.
The study employs machine learning, specifically an algorithm known as Alu Profile Learning Using Sequencing (A-Plus). This algorithm detects Alu elements in the blood, a type of repetitive DNA.
Researchers have found that people with solid cancers, such as those in organs like the breast or prostate, have fewer Alu elements in their blood compared to those without cancer. Based on these findings, they have improved a test that helps in early detection of cancer. The researchers have reproduced and validated their results using a larger sample size, ten times larger than those typically used in such studies, as mentioned in a news release.
Blood testing and AI
Liquid biopsy is a technique that uses body fluids, typically blood, to detect cancer instead of having to perform a standard biopsy that involves removing tissue from a tumor to look for cancer cells.
This method is less invasive, less painful, and has a lower risk of complications, making it more convenient for patients.
Christopher Douville is an assistant professor of oncology at Johns Hopkins Medicine and the study’s lead author.
“Blood testing holds great promise for the earlier detection of cancers before people exhibit any symptoms,” Mr. Douville said in a news release.
He continued and stated the following according to the latest reports:
“However, analyzing results with machine learning has not necessarily translated into long-term success for patients when minor fluctuations produce widely different predictions in these complex models. To have a long-term impact on patient care, physicians and patients must have confidence that models consistently and reproducibly classify cancer status. In our manuscript, we evaluated 1,686 individuals multiple times to assess whether our machine learning model consistently delivers the same answer.”
One other benefit of using AI is the fact that we will have fewer false positives.
We suggest that you check out the latest discoveries in the original study.
