TL;DR
- AI model detects pancreatic cancer signs early
- Can identify abnormalities up to three years prior
- Potentially increases treatment options for patients
- No routine screenings currently available
- Major advancements in pancreatic cancer research
When it comes to pancreatic cancer, the clock is always ticking. By the time most patients receive a diagnosis, the disease has often progressed beyond the point of effective treatment. But hold onto your rainbow flags, because a new study reveals that artificial intelligence (AI) could be the superhero we didn’t know we needed in the fight against this silent killer.
Researchers at the Mayo Clinic in Rochester, Minnesota, have developed an AI model that can detect signs of pancreatic cancer on CT scans up to three years before doctors make a diagnosis. Yes, you heard that right—three years! This groundbreaking research, published in the journal Gut, could change the game for early detection and treatment.
How does this AI magic work? The scientists trained the model using CT scans from patients who were screened for other medical conditions and later diagnosed with pancreatic cancer. They then compared the AI’s ability to spot early signs of the disease against that of seasoned radiologists. Spoiler alert: the AI was three times better! “We knew, based on the biology of the disease, that this is not something which is coming all of a sudden in three months,” said Dr. Ajit Goenka, a radiologist at the Mayo Clinic and one of the study’s authors. “We just needed to find a way to be able to detect it.”
With a dismal five-year survival rate of just 13%, pancreatic cancer is on track to become the second leading cause of cancer deaths by 2030. A staggering 80% of patients are diagnosed after the disease has advanced significantly. Unlike more commonly screened cancers like colon or breast cancer, there’s currently no routine screening for pancreatic cancer in healthy individuals. And let’s be real—feeling for a lump in the pancreas is about as easy as finding a needle in a haystack.
Symptoms like stomach pain and sudden weight loss usually don’t appear until the cancer has spread to other organs, making early detection even more critical. Unfortunately, early markers of the disease are often too subtle for the human eye to catch on scans. In fact, many patients’ scans can look perfectly normal just six months before they receive a diagnosis.
Dr. Daniel Jeong, a diagnostic radiologist at Moffitt Cancer Center in Tampa, Florida, who wasn’t involved in the Mayo Clinic research, noted, “We’re really looking for a measurable mass that could represent the cancer. So these tumors need to grow to a certain level to become visible.” But thanks to this new AI model, early signs—like abnormal cells in the pancreas that protect cancer from the body’s immune defenses—can now be detected. This could be a game changer for individuals with risk factors, such as a family history or diabetes, who currently show no symptoms.
Of course, if symptoms do appear, it’s usually too late for the AI to save the day. But for those at risk, this model could lead to additional testing and earlier intervention. And it’s not just this AI model making waves; researchers are also exploring mRNA vaccines and experimental drugs like daraxonrasib, which have been shown to prolong survival in patients with pancreatic cancer.
“We’re making, actually, major strides. It hasn’t turned this disease around,” said Dr. Tamas Gonda, director of the pancreatic disease program at NYU Langone’s Perlmutter Cancer Center. But with the potential for AI to catch signs of pancreatic cancer before it spreads, more patients may become candidates for surgery, chemotherapy, or radiation. Dr. Pam Hodul, a surgical oncologist at Moffitt Cancer Center, stated, “This really could be a game changer for us for early detection.”
While it may take some time for the Mayo Clinic’s AI model to make its public debut, as clinical trials need to track participants for three to five years, the progress is a beacon of hope. “In a disease where we have been just wandering in darkness for decades, this is a milestone that shows us the finish line, but we still have to get to the finish line,” Goenka concluded.
https://www.youtube.com/nbcnews