An artificial intelligence tool has successfully identified people at the highest risk for pancreatic cancer using only the patient’s medical records, according to new research led by researchers at Harvard Medical School and the University of Copenhagen in collaboration with the VA Boston Healthcare System, Dana-Farber Cancer Institute, and the Harvard T.H. Chan School of Public Health. This was accomplished up to three years before the diagnosis.

The research, which was published on May 8 in Nature Medicine, suggests that AI-based population screening could be useful in identifying people who are at increased risk for the disease and could hasten the diagnosis of a condition that is all too frequently discovered at an advanced stage when treatment is ineffective and outcomes are poor. One of the worst tumours in the world, pancreatic cancer is expected to claim more lives in the future.

There are currently no population-based techniques available for widespread pancreatic cancer screening. Targeted screening is used to identify those at risk for pancreatic cancer due to family history and particular genetic abnormalities. However, the researchers noted that such focused screens can miss additional cases that don’t fit those descriptions.

“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 Co-Senior investigator Chris Sander, a faculty member in the Department of Systems Biology in the Blavatnik Institute at HMS.

Sander asserts that an AI technique similar to the one employed by the researchers would enable medical practitioners to “zero in” on patients who have the highest chance of developing pancreatic cancer. Based on this, they will be able to determine which individuals might benefit from tests the most, which will help them make better clinical decisions.

Identifying pancreatic cancer risk individuals with AI

In the study, 9 million patient records from Denmark and the US were used to train the AI algorithm on two different data sets. They asked the model to search the records for indicators of pancreatic cancer.

The programme was able to identify which patients are most likely to acquire pancreatic cancer in the future based on the data. It’s interesting to note that several of the symptoms had no clear connection to or origin from the pancreas.

The study put various AI model iterations to the test. These versions were created to be able to identify persons who are more likely than average to develop pancreatic cancer throughout a range of timescales. Specifically, individuals who have a high risk of acquiring cancer within the next six months, a year, two years, or three years.

Each iteration of the model was at least as accurate at predicting the disease, according to the researchers, as genetic sequencing methods, which are currently often only accessible for a limited percentage of individuals in data sets.

Screening for pancreatic cancer is challenging

With a specialised blood test and mammography, you can screen for prostate cancer and breast cancer, respectively. A pap test can also be performed to check for cervical cancer. However, according to Harvard Medical School, pancreatic cancer is far more expensive to screen for and test for when compared to other cancers.

When pancreatic cancer is suspected, doctors may be hesitant to offer the pricey diagnostic procedures needed to find it, such as CT scans, MRIs, and endoscopic ultrasound imaging.

Patients will need to undergo a biopsy even if lesions are found using these diagnostic methods so that medical professionals can examine the tissue more closely to determine whether it is malignant or not. The pancreas, however, is hidden deep inside the abdomen, making it challenging to reach and simple to inflame. The pancreas is referred to as the angry organ by the medical school because of its irritation.

If patients have access to their health records and medical history, the new AI technology may make it possible to screen them for future risk of pancreatic cancer. The researchers claim that this is particularly crucial because many individuals who are at high risk may not even be aware that they are at a high risk of pancreatic cancer.

Like

Dislike

Be a part of Elets Collaborative Initiatives. Join Us for Upcoming Events and explore business opportunities. Like us on Facebook , connect with us on LinkedIn and follow us on Twitter , Instagram.