Artificial intelligence can now predict if someone will get pancreatic cancer up to three years in advance, according to a new study.
The research suggests that an artificial intelligence tool can detect who is at risk of the deadly disease, which is difficult to detect in its early stages, by using the patient’s medical records.
The study, which was published in the journal Nature Medicine this week, showed that potential cases of pancreatic cancer could be detected using AI-based population screening.
Population assessment is when medical professionals perform genetic tests or similar methods to look at the prevalence of a specific trait found among a group of people, according to Nature.com.
It can help identify a particular biomarker for certain diseases.
“One of the biggest decisions doctors face every day is who is at high risk for a disease and who would benefit from further testing, which can also mean more invasive and costly procedures that carry their own costs. risks,” said Chris, study supervisor. Sander, a professor at Harvard Medical School, in a news release.
“An artificial intelligence tool that can zero in on those people most at risk of pancreatic cancer who will benefit most from more testing could go a long way toward improving clinical decision making.”
The study was led by researchers from Harvard Medical School and the University of Copenhagen in collaboration with the Boston VA Health System, the Dana-Farber Cancer Institute and the Harvard TH Chan School of Public Health.
In the study, the researchers applied an AI algorithm to clinical data from 9 million patients from Denmark and the US.
They trained AI learning models to be able to read diagnostic codes in patient data and connect them to pancreatic cancer.
The researchers tested different versions of the AI models for potential diagnosis at different times (six months, one year, two years, and three years) and found that their methods were “substantially more accurate in predicting who would develop pancreatic cancer than the population.” current”. broad estimates of disease incidence.
However, the technology is still in its early stages and still needs to undergo much more testing.
Pancreatic cancer is one of the deadliest cancers today and is very difficult to detect early, when it has the potential to be curable.
Often by the time people get a diagnosis, it’s too late, since cancer in its early stages doesn’t show up on imaging tests, according to the Cleveland Clinic.
There is only a 5-year relative survival rate of 12.5%.
“Many types of cancer, especially those that are difficult to identify and treat early, have a disproportionate effect on patients, families, and the broader health care system,” said study supervisor Søren Brunak, professor of disease systems biology. at the University of Copenhagen. , in a press release.
“AI-based detection is an opportunity to alter the trajectory of pancreatic cancer, an aggressive disease that is notoriously difficult to diagnose early and treat promptly when the chances of success are highest.”
Some symptoms of pancreatic cancer include jaundice, pain in the mid-back and upper abdomen, weight loss, itchy skin, and fatigue.
This is not the first AI-based tool that could lead to a medical breakthrough.
In March, researchers in Canada developed artificial intelligence that they say could predict a patient’s survival rate for a cancer called hepatocellular carcinoma.
Another team of scientists in the US has developed an AI-powered blood test that could look for signs of lung cancer.