Geneva AI stool test detects 90% of colorectal cancers
Get the Health newsletter
Daily health & science — research, biotech, public health, the studies worth knowing. Free.
- University of Geneva created the first comprehensive catalogue of human gut microbiota subspecies using AI‑driven machine learning, enabling functional analysis of bacterial subgroups.
- Mirko Trajkovski led the research and highlighted that subspecies‑level profiling captures disease‑relevant microbial differences while remaining generalizable across populations.
- Matija Trickovic reported that the stool‑based model detected 90% of colorectal cancer cases, approaching the 94% detection rate of colonoscopies and surpassing existing non‑invasive tests.
- Geneva University Hospitals will partner on a clinical trial to evaluate the test’s ability to identify various cancer stages and lesions in real‑world screening.
- Cell Host & Microbe published the findings, noting the method could be extended to develop non‑invasive diagnostics for a wide range of diseases beyond colorectal cancer.
Why it matters: Patients gain a simple, low‑cost screening tool that could boost early detection rates, while healthcare systems may reduce reliance on expensive colonoscopies; the 90% detection accuracy suggests the test could become a new standard for colorectal cancer screening and a platform for broader disease diagnostics.
