New Stool Test Detects 90% Of Colorectal Cancers — Researchers

 

A breakthrough in research could transform how colorectal cancer is detected. Scientists have developed a new stool test that identifies up to 90 per cent of colorectal cancer cases without the need for a colonoscopy.

Using artificial intelligence, researchers analysed hidden signals in gut bacteria to detect colorectal cancer with striking accuracy, rivalling one of medicine’s most trusted diagnostic tools.

Colorectal cancer is the second leading cause of cancer-related deaths worldwide. When detected early, it is often highly treatable. However, colonoscopies, the

primary screening method used today, can be costly and uncomfortable, discouraging many people from getting tested on time.

Researchers at the University of Geneva (UNIGE) used machine learning to create the first detailed catalogue of human gut bacteria at a level precise enough to reveal how different microbial subgroups function in the body.

They then applied this data to detect colorectal cancer based on bacteria found in simple stool samples, offering a non-invasive and low-cost alternative.

The findings, published in Cell Host & Microbe, could also help scientists better understand how gut microbiota influence overall health and disease.

Many cases of colorectal cancer are diagnosed at a late stage, when treatment options are more limited. This underscores the urgent need for easier and less invasive screening methods, especially as cases continue to rise among younger adults for reasons that remain unclear.

Scientists have long known that gut microbiota play a role in colorectal cancer. However, translating that knowledge into practical medical tools has been challenging because different strains within the same bacterial species can behave very differently. Some may contribute to cancer development, while others have no effect.

The research required analysing vast amounts of biological data. By combining their bacterial catalogue with existing clinical datasets, the team developed a model capable of identifying colorectal cancer using only stool samples. The results exceeded expectations.

Matija Trickovic, a PhD student in Mirko Trajkovski’s lab and the study’s first author, explained, “Our method detected 90 per cent of cancer cases, a result very close to the 94 per cent detection rate achieved by colonoscopies and better than all current non-invasive detection methods.”

With additional clinical data, the model could become even more accurate and eventually match the performance of colonoscopies. In practice, this type of test could be used for routine screening, with colonoscopies reserved for confirming positive cases.

A clinical trial is now being prepared in partnership with the Geneva University Hospitals (HUG) to determine which cancer stages and lesions the method can detect most effectively.

The implications extend far beyond colorectal cancer. By examining differences between subspecies within the same bacterial species, researchers may uncover how gut microbes influence a wide range of health conditions.

 

Tribuneonline