AI Can Predict Pancreatic Cancer: Three Years Before Diagonosis

A new study shows that AI can detect pancreatic cancer up to three years earlier than a human doctor. Cancer is such a very challenging disease to see at an early stage, but through AI, it has become possible to detect it at an early stage.

Pancreatic cancer is a deadly disease with only a five-year survival rate of 12%. The Nature Medicine study presented that potential pancreatic cases could be spotted using AI-based population screening.

In addition, population screening refers to genetic testing or similar tests to look at the prevalence of a specific trait found among a group of people. AI helps to detect the early spot at the very first stage.

A paper reads that “AI on real-world clinical records has the potential to produce a scalable workflow for early detection of cancer in the community, to shift focus from treatment of late-stage to early-stage cancer ,to improve the quality of life of patients and to increase the benefit/cost ratio of cancer care.”

Chris Sander, a professor at Harvard Medical School, stated that “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.”

In addition, he also stated that”an AI tool that can zero in on those at higher risk of pancreatic cancer who stand to benefit most from further tests could go a long way toward improving clinical-decision making.”

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

Moreover, at the beginning of the feasibility phase, researchers applied an AI algorithm to clinical data from 9 million patients from U.S. and Denmark.
Additionally, they trained AI learning models to detect the diagnosis codes in the patient’s data and connect them to pancreatic cancer.

The team of researchers tested various models of AI to get the desired results. They tried different versions six months, one-year, two years, and three years. Later, they reached the point that “substantially more accurate at predicting who would develop pancreatic cancer than current population-wide estimates of disease incidence.”

The research is not yet final and needs to undergo many stages. However, the software can not be used to run screening programs. Cancer is a hazardous disease; according to different theories, it has only a 12.5% survival rate.

Sander also stated that “once a survellience program is implemented ,the actual computing costs for applying the software are moderate. The training is what consumes considerable computing resources. The actual clinical tests to see early signs of cancer or to detect cancer when it is still very small are costly, much more expensive than for example mammograms”.

Soren Brunak, a professor of disease system biology at the University of Copenhagen, said in a press release that “many types of cancers specially, those hard to identify and treat early, exert a disproportionate toll on patients,families and the health care system as a whole.”

He also stated that “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.”

Though, there are specific symptoms through which pancreatic cancer can be diagnosed, such as jaundice, pain in the middle of your back and upper abdomen, fatigue, itchy skin, and weight loss. But still, it is essential to have a device that can detect accurately at an early stage.

Read more:

Apple co-founder Steve Wozniak says that AI Will Make Scams Harder to Spot

Google Will Soon Add Smart AI Features to its Search