Finding early pancreatic cancer with metabolic clues and AI
Altered metabolism and machine learning for pancreatic cancer early detection
This work uses AI on medical records plus stool, blood, and CT-based metabolic markers to find early pancreatic cancer in people at higher risk.
Quick facts
| Grant type | U01 cooperative agreement |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Dana-Farber Cancer Inst NIH-funded |
| Lab location | 1 site (Boston, United States) |
| Project ID | NIH-11177770 on NIH RePORTER |
What this research studies
Researchers will train machine-learning models on electronic medical records to identify who may be at increased risk for pancreatic cancer. They will search for metabolic changes caused by early tumors using non-invasive stool samples and detailed CT imaging. The team will also analyze circulating cell-free DNA methylation patterns and CT features to try to detect hidden metastases before surgery. Together these approaches aim to pick out people who need closer imaging surveillance and to predict who might recur after surgery.
Who could benefit from this research
Good fit: Ideal candidates are adults with higher-than-average pancreatic cancer risk, such as those with pancreatic cysts, a strong family history, or other clinical risk indicators.
Not a fit: People without risk factors or those with already-advanced, symptomatic pancreatic cancer are unlikely to benefit from these early-detection efforts.
Why it matters
Potential benefit: If successful, these tools could detect pancreatic cancer earlier, focus surveillance on people who need it, and help guide treatment to reduce rapid recurrence.
How similar studies have performed: Prior biomarker and AI efforts for pancreatic cancer have shown promise, but combining metabolic stool/CT signals with EMR-based machine learning and cfDNA methylation is relatively new and not yet proven.
Where this research is happening
Boston, United States
- Dana-Farber Cancer Inst — Boston, United States (Active)
Researchers
- Principal investigator: Wolpin, Brian Matthew — Dana-Farber Cancer Inst
- Study coordinator: Wolpin, Brian Matthew
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.