AI tool to improve colorectal cancer diagnosis and prognosis in Kenya
Official title: Leveraging artificial intelligence/machine learning-based technology to overcome specialized training and technology barriers for the diagnosis and prognostication of colorectal cancer in Africa
Funded at Aga Khan University (Kenya) · NIH-11172236 · Data updated 2026-11-12
An artificial-intelligence computer program will read routine pathology slides to help diagnose and predict outcomes for people with colorectal cancer in Kenya.
Quick facts
| Grant type | U01 cooperative agreement |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Aga Khan University (Kenya) NIH-funded |
| Lab location | 1 site (Nairobi, Kenya) |
| Project start | September 15, 2023 |
| Project end | August 31, 2026 |
| Funding year | 2025 |
| Award (this year) | $249,999 |
| NIH project number | 5U01CA287852-03 |
| Project ID | NIH-11172236 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are people in the Kenyan cohort who have had colorectal biopsies or surgical specimens with available H&E slides and linked clinical outcome data.
✕Less likely to help
People without available tissue slides, without linked clinical data, or whose care is outside the participating hospitals are unlikely to directly benefit from this project.
What this research studies
If I take part, my routine tissue slides from a colon biopsy or surgery will be digitally scanned and analyzed by an AI pipeline (SIVQ/VIPR) that identifies tumor features at the pixel level. The team will link those image features to clinical records to see how well the AI can match diagnoses and predict outcomes. This work is being done with partners at Aga Khan University East Africa, Tenwek Hospital in rural Bomet, and the University of Michigan using samples from an existing Kenyan patient group. The goal is to create an affordable, locally relevant tool that can work where trained pathologists and resources are scarce.
Why it matters
Potential benefit: If successful, this could speed up and improve diagnosis and prognosis information for colorectal cancer patients in areas with few pathologists, helping doctors choose better treatments sooner.
How similar studies have gone: Other AI-based pathology tools have shown promising accuracy, and the SIVQ/VIPR pipeline has previously outperformed subject-matter experts, but large-scale validation in an African clinical population is new.
Where this research is happening
-
Aga Khan University (Kenya)
Nairobi, Kenya Active
Researchers
- Principal investigator: Saleh, Mansoor N — Aga Khan University (Kenya)
- Study coordinator: Saleh, Mansoor N
Related research
Other NIH-funded projects on the same topics.
-
Improving colorectal cancer screening and follow-up care.
This study is working to help more people get screened for colorectal cancer and receive the follow-up care they need, especially those who haven't been screened much before, so that everyone can have better access to important health checks and improve their overall health.
-
Colorectal cancer prognosis through a broad, collaborative study
A large, multi-center study follows people newly diagnosed with colorectal cancer to find biomarkers and patterns that predict outcomes and guide future care.
-
Ceramides and how they affect metabolism and colorectal cancer in adults
A study in adults with obesity-related health issues will explore how a fat-related molecule called ceramide influences metabolic problems and colorectal cancer risk.
-
Automated point-of-care DNA methylation test for colorectal cancer in LMICs
A fast, affordable blood test using DNA markers to help identify people at higher risk of colorectal cancer in low- and middle-income countries.
-
Rewiring Colorectal Cancer to Harness Therapeutic Hyperactivation
A Yale team is exploring brain-storming new ways to treat colorectal cancer by safely boosting certain cancer signaling pathways to kill cancer cells and by reshaping cancer cell states to improve responses to existing therapies.
-
Comparative modeling to guide colorectal cancer screening and care
A researcher team will use computer models to study how access to care, risk, and new screening options affect colorectal cancer outcomes and costs for adults in the US.
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.