For over 30 years, doctors have been trying hard to find an early test for ovarian cancer, a disease that’s hard to notice until it’s quite advanced.
But recently, a group of scientists at the Georgia Tech Integrated Cancer Research Center made a big step forward.
They’ve created a new test that uses a computer program and blood tests to find ovarian cancer early. This test can tell with 93% accuracy if someone has ovarian cancer, based on their research.
The study was published in a scientific journal called Gynecologic Oncology. John McDonald, a retired professor and the founding director of the research center, played a key part in this study.
He says their new test is better at finding ovarian cancer than the tests doctors have now, especially in the early stages.
The team used computer models to come up with a new way to diagnose ovarian cancer. Instead of a simple ‘yes’ or ‘no’, their test looks at the patient’s blood to give a more detailed answer about the chances of having the disease.
McDonald thinks this approach is not only more accurate but could change the way we find ovarian cancer and maybe other cancers too.
Ovarian cancer is really sneaky. It doesn’t show signs at first, so it’s often not caught until it’s quite advanced and hard to treat. If found late, only about 31% of patients live for more than five years after treatment.
But if it’s caught and treated early, this number jumps to over 90%. That’s why finding it early is so important.
Despite trying for over 30 years, making an early test for ovarian cancer has been tough.
McDonald explains that cancer starts on a very small, molecular level and can develop in many different ways, even for the same type of cancer. Because of this, it’s been hard to find a single test that works for everyone.
To solve this, the team turned to machine learning, a type of artificial intelligence. It’s like teaching a computer to recognize patterns and make predictions.
They decided to focus on something called metabolic profiles. These profiles are like a snapshot of the health of our cells.
Georgia Tech researcher Dongjo Ban, who helped with the study, says that these metabolic changes reflect what’s happening in our bodies on a tiny, molecular level.
By looking at these changes, they can find clues about diseases like cancer.
Jeffrey Skolnick, another team member, adds that they didn’t just focus on some parts of the metabolic profile. Instead, they let the computer figure out which parts are most important.
In conclusion, even though we don’t know everything about these metabolites, the team’s approach shows that you don’t need to.
By using mass spectrometry and machine learning together, they’ve made a test that can accurately tell if someone has ovarian cancer, just by looking at their blood. This is a big step in the fight against a disease that’s often hidden until it’s too late.
If you care about cancer, please read studies that artificial sweeteners are linked to higher cancer risk, and how drinking milk affects risks of heart disease and cancer.
For more information about health, please see recent studies about the best time to take vitamins to prevent heart disease, and results showing vitamin D supplements strongly reduces cancer death.
The research findings can be found in Gynecologic Oncology.
Copyright © 2024 Knowridge Science Report. All rights reserved.
