New AI can predict pancreatic cancer 3 years early: study says

Artificial intelligence may now be able to predict whether someone will get pancreatic cancer up to three years in advance, according to a new study.

Research suggests that an AI tool can detect who is at risk for the deadly disease — which is difficult to catch 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 spotted by using an AI-based population screening.

Population screening is when medical professionals perform genetic testing or similar methods to look at the prevalence of a specific trait that’s found among a group of people, according to Nature.com.

It can help to identify a particular biomarker of certain diseases.

“One of the most important decisions clinicians face day to day is who is at high risk for a disease and who would benefit from further testing, which can also mean more invasive and more expensive procedures that carry their own risks,” said study supervisor Chris Sander, a Harvard Medical School professor, in a press release.

“An AI tool that can zero in on those at highest risk for pancreatic cancer who stand to benefit most from further tests could go a long way toward improving clinical decision-making.”

The study was led by investigators at Harvard Medical School and the University of Copenhagen in collaboration with VA Boston Healthcare System, the Dana-Farber Cancer Institute and the Harvard T.H. Chan School of Public Health.

In the study, 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 diagnosis codes in the patient’s data and connect them to pancreatic cancer.

The researchers tried out 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 at predicting who would develop pancreatic cancer than current population-wide estimates of disease incidence.”

However, the technology is still in its early stages and still needs to undergo many more tests.

Currently, pancreatic cancer is one of the most deadly cancers and is very hard to detect early, which is when it has the potential to be curable.

Often when people get a diagnosis, it’s too late, as the cancer in its early stages does not show up on imaging tests, according to the Cleveland Clinic.

There is only a 12.5% rate of five-year relative survival.

“Many types of cancer, especially those hard to identify and treat early, exert a disproportionate toll on patients, families and the health care system as a whole,” said study supervisor Søren Brunak, a professor of disease systems biology at the University of Copenhagen, in a press release.

“AI-based screening is an opportunity to alter the trajectory of pancreatic cancer, an aggressive disease that is notoriously hard to diagnose early and treat promptly when the chances for success are highest.”

Some symptoms of pancreatic cancer include jaundice, pain the middle of your back and upper abdomen, weight loss, itchy skin and fatigue.

This isn’t the first AI-based tool that could make a medical breakthrough.

In March, researchers out of Canada developed an 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 have developed an AI-powered blood test that could look for signs of lung cancer.