- A new study suggests that an AI model can identify people at higher risk of pancreatic cancer up to 5 years before diagnosis, using routine electronic health records and laboratory data.
- The findings show promising predictive performance, suggesting the AI model could effectively distinguish people at higher and lower risk of pancreatic cancer.
- However, further research is still necessary, and prospective testing is underway, with plans to evaluate the AI model within a healthcare system before determining whether it could play a role in routine clinical care.
Despite pancreatic cancer accounting for roughly 3% of all new cancer cases, it is responsible for approximately 8% of cancer deaths, highlighting its particularly high mortality burden.
Pancreatic cancer can be difficult to detect, with many cases diagnosed after it has spread. An early diagnosis could be particularly beneficial, as data show a 5-year relative survival of about 44% when the cancer is still localized, compared with just 3% when it has spread to distant parts of the body.
Now, research suggests that an artificial intelligence (AI) model could identify people at increased risk of pancreatic cancer as early as 5 years before it becomes clinically apparent, using information routinely collected in electronic health records.
The findings were presented at the American College of Surgeons (ACS) Clinical Congress 2026 in Washington, D.C., by Mayo Clinic researchers. As such, it is important to note that the findings have not yet been peer-reviewed.
The researchers developed the model using longitudinal health information from the Mayo Clinic health system. According to the press release, this involved electronic health records for almost 40,000 patients and results from routine laboratory tests collected over many years.
This included 6,066 people who developed pancreatic cancer and 33,396 people who served as controls. Participants had between 7.5 and 19 years of clinical history available for analysis. The researchers’ goal was to determine whether patterns in routine medical data could reveal subtle signs associated with an increased future risk of pancreatic cancer.
Pancreatic cancer can develop over many years. However, the clinical signs that would prompt a doctor or patient to investigate the disease may not appear until much later.
Because pancreatic cancer is relatively uncommon in the general population, routinely screening everyone for the disease is not currently considered feasible. As such, an approach that could identify people at elevated risk might allow further evaluation to focus on this group.
“The most important finding was that subtle patterns across a patient’s healthcare journey could reveal elevated pancreatic cancer risk up to five years before the diagnosis was first documented,” lead study author Chris Varghese, MBChB, surgical data analyst at Mayo Clinic, told Medical News Today.
“This creates a potential window to move detection upstream—from reacting to symptoms to proactively identifying patients who may benefit from earlier, targeted screening or further evaluation—an approach that has historically been difficult because pancreatic cancer is relatively rare and existing screening tests are not practical for broad population use.”
— Chris Varghese, MBChB
The researchers assessed the model’s ability to distinguish between people who would later develop pancreatic cancer and those at lower risk.
Varghese informed MNT that the abstract has been updated with more data. Five years before a pancreatic cancer diagnosis, the model achieved an area under the receiver operating characteristic curve (AUROC) of 0.853 in a slightly smaller cohort of patients. The updated numbers are 0.84 for 1-year, 0.80 for 2-year, and 0.76 for 3-year prior to diagnosis.
AUROC values range from 0.5, which indicates performance no better than chance, to 1.0, representing perfect discrimination.
The researchers additionally assessed calibration, or how closely the model’s predicted risk corresponded to what happened in the study population. The reported slope of the calibration plot was 1.08.
“An AUROC in this range means the model is reasonably good at distinguishing people who are at higher risk of pancreatic cancer from those who are at lower risk,” Varghese explained to MNT. “But for clinical use, calibration—whether the risk predicted by the model actually matches the rate of pancreatic cancer we observe in practice—is also very important.”
“Given these promising results, and ongoing research that may further improve performance using more advanced AI models, the next challenge is determining what level of predicted risk should trigger additional evaluation. That threshold may differ depending on the downstream test being considered, its risks and costs, and the potential benefit of detecting cancer earlier.”
— Chris Varghese, MBChB
“Defining those thresholds and testing how the model performs within a real screening pathway are important next steps,” Varghese said.
In the press release, the researchers gave an example of how the predicted risk could potentially be interpreted: among people for whom the model estimated a greater than 50% risk of pancreatic cancer, 88% were diagnosed with the disease within a year.
Importantly, these results describe the model’s performance in the research dataset. They do not yet establish that using the AI system in routine clinical care will improve pancreatic cancer detection or patient outcomes.
“We found that the model’s predictions were strongly informed by routine blood tests, particularly components of the complete blood count, which are often obtained for other reasons or as part of routine care,” study co-author Cornelius Thiels, DO, MBA, surgical oncologist at Mayo Clinic, told MNT.
“Expected clinical associations such as diabetes, pancreatitis, and other pancreatic conditions were also important. In addition, patterns in seemingly unrelated healthcare interactions contributed useful information. None of these signals alone would be sufficient to suggest a future diagnosis of pancreatic cancer, but the AI model was able to learn from how they appeared and changed over time across a patient’s longitudinal healthcare record.”
— Cornelius Thiels, DO, MBA
The current findings are an early step, not evidence that the AI model is ready for use as a pancreatic cancer screening test.
The researchers say they designed the system to rely primarily on information that is already routinely collected in healthcare settings.
The researchers are now moving the model beyond retrospective analysis and into prospective research at Mayo Clinic. The team also plans to evaluate the model at a non-Mayo healthcare system and is investigating newer machine-learning approaches that may further improve its performance.
Prospective validation will be important because an AI model can perform differently when applied to patients outside the dataset on which it was developed. Researchers will also need to determine how the model performs across different healthcare systems and patient populations.
What happens to those identified as having higher risk?
Another important question is what should happen after someone is identified as being at elevated risk. A prediction tool could potentially lead to additional testing or imaging, but such follow-up would need to balance the potential benefit of earlier cancer detection against the risks, costs, and anxiety associated with false-positive results.
If further studies confirm that the model can reliably identify people who are likely to develop pancreatic cancer before symptoms or conventional clinical signs emerge, it could eventually provide clinicians with another tool for deciding who may benefit from closer monitoring or further evaluation.
“Identifying what should happen after someone is flagged as high risk is one of the most complex and important next steps, and we do not yet know the optimal approach,” Thiels explained to MNT.
“Our hope is that by first identifying a smaller, higher-risk population, downstream screening tests—such as CT, MRI, endoscopic ultrasound, or blood-based biomarker tests—may perform better and become more practical. We and others are actively working to determine how best to combine digital risk prediction with these downstream tests and to validate those strategies prospectively before they are ready to be rolled out to patients.”
— Cornelius Thiels, DO, MBA
