AI to spot early signs of pancreatic cancer from CT scans and health records

Multimodal AI Fusion Model for Early Detection for Pancreatic Cancer

NIH-funded research Mayo Clinic Arizona · NIH-11193447

A computer tool that combines routine CT images and medical records to spot early signs of pancreatic cancer in people without symptoms.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionMayo Clinic Arizona NIH-funded
Lab location1 site (Scottsdale, United States)
Project IDNIH-11193447 on NIH RePORTER

What this research studies

Researchers are training an AI called PRECISE to read routine abdominal CT scans and pick out subtle imaging signs that may appear before pancreatic cancer is diagnosed. They will combine those imaging features with clinical information from electronic health records—like age, weight, and diabetes history—to estimate a person's risk. The team will use deep learning to segment imaging biomarkers and apply adversarial debiasing so the tool works across different hospitals and patient groups. Validation will use imaging and records from Mayo Clinic, Cornell, and UCSF.

Who could benefit from this research

Good fit: Ideal candidates are adults who have had abdominal CT scans and have linkable electronic health records, especially those with risk factors such as older age, obesity, or diabetes.

Not a fit: People without prior abdominal CT imaging or without accessible electronic health records, as well as those already diagnosed with pancreatic cancer, would not benefit from this approach.

Why it matters

Potential benefit: If successful, this could help detect pancreatic cancer earlier in people without symptoms, potentially leading to earlier treatment and better outcomes.

How similar studies have performed: Previous smaller studies suggest CT-based imaging biomarkers can flag early pancreatic changes, but combining those markers with EMR data using multimodal AI and explicit debiasing is relatively new.

Where this research is happening

Scottsdale, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-10 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.