Researchers at the University of Geneva have developed a powerful new tool to detect colorectal cancer using gut bacteria and machine learning.
They created the first detailed catalogue of human gut microbiota subspecies and used it to build a model that can identify cancer from simple stool samples—making screening non-invasive, low-cost, and nearly as accurate as colonoscopies (90% vs. 94%).
A clinical trial is now underway to test how well this method detects different cancer stages and lesions. But the potential goes far beyond colorectal cancer
