Mayo Clinic research published April 28 showed an AI model could detect pancreatic cancer up to three years before clinical diagnosis. Projected to be the second-leading cause of cancer-related death in the U.S. by 2030, early diagnosis has a significant effect on survival outcomes for pancreatic cancer patients.
The study from Rochester, Minn.-based Mayo Clinic adds to the larger evidence of AI’s value for cancer detection, but are health systems willing and able to scale these tools?
Eduardo Sotomayor, MD, PhD, vice president and executive director of Tampa (Fla.) General Hospital’s Cancer Institute, expressed frustration on how the broader healthcare industry has been slower than others to adopt AI.
“Why, as an industry, are we behind everybody else in adapting innovation and technology? What are the barriers [contributing to our industry being] the last in adopting technologies? Is it because of us? Because of the system? Because of state regulation? Because of government regulations?” he told Becker’s. “I’m not looking to blame anyone. Let’s just go and see why we are late to the party and then learn from that. We were invited late to the party, now we are going to run the party. Innovation, technology, AI, everything that is coming; we need to be at the forefront.”
For their part, cancer researchers are continuing to find ways to strengthen disease detection with AI.
For example, a molecular test designed by researchers at Pittsburgh-based UPMC Hillman Cancer Center and the University of Pittsburgh School of Medicine detected nearly twice as many bile duct cancers as standard pathology.
Meanwhile, biopharmaceutical companies and technology firms are establishing partnerships to push diagnostic capabilities forward.
Bristol Myers Squibb and Microsoft launched a digital health collaboration aimed at accelerating early detection of lung cancer using AI-driven radiology workflows. The initiative deploys FDA-cleared algorithms through Microsoft’s Precision Imaging Network — used by more than 80% of U.S. hospitals — to analyze X-ray and CT images, help detect lung nodules and identify early-stage disease, and support patient tracking through care pathways.
The University of Texas MD Anderson Cancer Center in Houston and New York City-based Mount Sinai Health System have both independently partnered with SOPHiA Genetics to expand cancer research and genomic testing.
Some hospitals are taking matters into their own hands. At Providence St. Joseph Hospital in Orange, Calif., radiologists are identifying 20% more cancers up to two to three years earlier than traditional screening and reducing false positives and unnecessary callbacks by about 7% by integrating an AI algorithm with human interpretation of mammograms.
Despite this progress, one leader questions whether today’s health systems are operationally prepared to scale this technology and detect cancer earlier.
Ajit Goenka, MD, a radiologist, nuclear medicine specialist and senior author of the Mayo Clinic study on using AI to detect pancreatic cancer earlier, shared his thoughts with Becker’s:
“The honest answer is: [They are not prepared] yet. Most health systems are built to respond to cancer after it declares itself, not to act on a signal from an AI model before a lesion is even visible. That is a fundamentally different clinical workflow and it raises questions we have not had to answer before. Who receives the AI flag? What is the escalation pathway when the scan looks normal but the algorithm says otherwise? How do you communicate risk to a patient who feels perfectly fine? How do payers cover a workup triggered by a model rather than a symptom?
“These are solvable problems, but they require deliberate investments in our infrastructure. The science of detection is advancing. The science of deployment needs to keep pace.”
At the Becker's Perioperative Summit, taking place September 14–15 in Chicago, perioperative leaders and healthcare executives will focus on improving operating room efficiency, enhancing patient safety, optimizing staffing and driving innovation across surgical services. Apply for complimentary registration now.
