A completely new AI-powered testing method could one day be used to diagnose the early stages of three of the deadliest cancers, using just a drop of dried blood.
Chinese researchers revealed that in primary tests, the tool was able to detect cancer in already diagnosed patients in approximately 82-100% of cases, by recognizing certain chemicals in blood droplet samples. It also distinguished patients who did not have cancer from those with pancreatic, stomach or colorectal cancer.
The new tool is powered by a form of artificial intelligence known as machine learning, capable of detecting metabolites – substances left in the liquid part of blood, serum, after metabolism. These by-products, depending on their type and quantity, act as “biomarkers”, potentially signaling the presence of cancer cells in the body. Writing in the journal Nature Sustainability, the researchers say that by detecting these specific chemicals in the blood, the test has the ability to accurately identify cancer in patients approximately 82 to 100 percent of the time.
This use of metabolites has been proposed as a potential new and effective way to detect and diagnose cancer in the early stages of the disease, when the patient’s chances of survival are higher and they may not yet have any symptoms. symptoms. Despite the pancreas, colorectal And gastric cancers Being among the deadliest cancers in the world, none require a specific diagnostic blood test and are currently generally identified through the use of medical imaging or surgical procedures.
According to Cancer Research UK, pancreatic and bowel cancers are among the top five causes of cancer deaths in the country and are expected to kill 14,620 men and 13,791 women between 2023 and 2025. In theory, this test would only require a single, tiny spot of blood to diagnose these diseases, according to the Chinese scientists who developed it.
-Dr. Chaoyuan Kuang, an assistant professor at Albert Einstein University of Medicine and an oncologist, told Live Science that these blood serum samples can be “collected, stored and transported at a much lower cost and with much simpler equipment.” , thus contributing to “democratize”. availability of early cancer detection tests worldwide”.
The new test is proposed as a sustainable and environmentally friendly way to detect cancer. The study shows that the method is more effective at testing small samples of dried blood than liquid blood. In one experiment, using dried blood drops allowed them to detect 81.2% of pancreatic cancer cases, compared to 76.8% with liquid blood samples.
Although Kuang, who is not involved in the research, suggests that the tests will not be widely available to patients for several years and will require more testing, the scientists behind the method say that if it is used in large-scale cancer screening programs in the future could make a huge difference.
Extensive testing of the method is still needed in diverse and larger populations, as currently only small proof-of-concept tests have been performed on a few hundred samples. The researchers exclusively evaluated the machine learning model on people already diagnosed with cancer and have not yet evaluated its effectiveness as a true diagnostic tool.
Due to the low cost of the test, it could be used in remote areas where access to general practice and cancer screening tests is limited and resources limited, helping those most affected by cancer. barriers to medical care. By 2030, 75 percent of all cancer deaths are expected to occur in low- and middle-income countries.
