University of Geneva scientists developed the first comprehensive catalogue of gut microbiota subspecies and applied machine learning to stool samples, enabling detection of colorectal cancer in 90% of cases. This performance is close to colonoscopy’s 94% accuracy but at a fraction of the cost and discomfort. The approach could revolutionize non-invasive screening and expand into diagnostics for other cancers and diseases.
Key Takeaways
- Stool-based machine learning test identified 90% of colorectal cancer cases.
- Nearly matches colonoscopy accuracy (94%), outperforms other non-invasive methods.
- Uses microbiota subspecies analysis for greater precision.
- Clinical trial underway at Geneva University Hospitals.
- Could extend beyond colorectal cancer to a wide range of diseases.