Implementation of risk prediction models using electronic health data for early detection of pancreatic cancer: a prospective pilot feasibility study
- Open access
Implementing EHR-based risk models with imaging and blood tests detects pancreatic cancer early in 8.2% of high-risk adults aged 50-84.
- Why it matters: Early detection of pancreatic cancer remains challenging, and integrating predictive models with diagnostic procedures could improve outcomes, but feasibility and patient engagement are uncertain.
- What they did: The study prospectively enrolled 102 adults identified via validated machine-learning risk models, conducting baseline and 18-month imaging and CA19-9 blood tests to assess participation and test completion.
- The result: Most participants completed testing with manageable incidental findings, demonstrating the potential of AI-guided surveillance, though enhancing patient engagement is necessary for broader implementation.