Predicting early peritoneal relapse in gastric cancer with AI-powered models
Official title: Multimodal computational models for early prediction of peritoneal recurrence in gastric cancer
Funded at Wake Forest University Health Sciences · NIH-11367404 · Data updated 2026-11-12
A new AI-based tool will combine clinical data, CT images, and tissue slides to predict which gastric cancer patients are at risk of early peritoneal recurrence after surgery.
Quick facts
| Grant type | R37 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Wake Forest University Health Sciences NIH-funded |
| Lab location | 1 site (Winston-Salem, United States) |
| Project start | June 18, 2026 |
| Project end | May 31, 2031 |
| Funding year | 2026 |
| Award (this year) | $513,915 |
| NIH project number | 1R37CA304421-01A1 |
| Project ID | NIH-11367404 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults with gastric cancer who have undergone radical surgery and are at risk for peritoneal recurrence (based on clinical criteria and available imaging/tissue data).
✕Less likely to help
Patients without gastric cancer or those not at risk for peritoneal recurrence based on current clinical criteria are unlikely to benefit.
What this research studies
This project aims to build and test advanced deep learning models that integrate patient records, imaging scans, and histology slides to foresee early peritoneal spread in gastric cancer. By combining multiple data types, the model seeks to identify high-risk patients who may benefit from closer monitoring or altered treatment plans. The work will involve developing multimodal algorithms, validating them on retrospective data, and refining predictions for clinical use. If successful, clinicians could use these insights to personalize follow-up schedules and intervene sooner to improve outcomes.
Why it matters
Potential benefit: If successful, the model could help doctors identify patients at high risk for early recurrence and tailor treatment and monitoring to improve survival and quality of life.
How similar studies have gone: Previous work shows promise for AI models in cancer risk prediction, but multimodal integration for peritoneal recurrence is an emerging area with room for validation.
Where this research is happening
-
Wake Forest University Health Sciences
Winston-Salem, United States Active
Researchers
- Principal investigator: Jiang, Yuming — Wake Forest University Health Sciences
- Study coordinator: Jiang, Yuming
Related research
Other NIH-funded projects on the same topics.
-
Keloid recurrence study using multi-omics in diverse patients
A research effort will look at why keloids come back after surgery, especially in African American patients, using comprehensive molecular data from patient samples.
-
Combined Imaging and RNA Markers to Predict Head and Neck Cancer Recurrence
A research project aims to use imaging and RNA data to better predict if head and neck cancer will come back, helping doctors tailor treatments for patients.
-
Advancing gastric cancer care for Latinos through patient-derived tumor models
Aimed at Latinos with gastric cancer, this project uses patient-derived tumor models to study how cancer biology and treatments work in real tumors.
-
Oral cancer recurrence predictor using tumor microbes and gene activity
This NIH grant explores how bacteria and immune signals inside oral cancer tumors relate to whether the cancer comes back, with the aim of making a practical risk predictor for patients.
-
How air pollution affects recurrent heart events in older adults
This grant explores how air pollution, especially PM2.5, influences the recurrence and progression of heart problems in people aged 65 and older.
-
Circulating metabolites as early warning signs for gastric cancer
Researchers will look at blood-based metabolites to find signs that predict gastric cancer risk in people, with a focus on those in large, multi-center cohorts.
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.