Goodbye colonoscopy? Simple stool test discovers 90 % of colon and rectum cancers

Colon and rectum cancer is often diagnosed in an advanced stage when the treatment options are limited. This emphasizes the need for simpler and less invasive diagnostic tools, especially in the face of an increase that is still not explained in cases among young people. Although it is long known that the microbiota intestine plays a role in the development of colon and rectal cancer, translating these results into a clinical practice has proven challenging. This is because different strains of the same bacterial species can have opposite effects, while strengthening some disease and others have no effect.

“Instead of Relay on the Analysis of the Various Species Composition The Microbiota, You Dos Not Capture All Meangful Differences, Or of Bacterial Strains, Who Vary Great from one one Individual to Another, We Focused on An Interdiate Level of the Microbiota, The Subspecies, “Explains Mirko Trajkovski, Full Professor in the Department of Cell Physiology And metabolism and in the Diabees Center at the Unive Faculty of Medicine, which led this research. “The accuracy of the sub -species is specific and can capture the differences in how bacteria work and contribute to diseases, including cancer, with general survival to detect these changes between different groups of individuals, population or countries.”

With the help of machine learning

The first step was to analyze huge amounts of data. “As a vital world, the challenge was to reach an innovative approach to the analysis of collective data,” Matija Tradovic, a doctoral student at the Mirko Trajkovski Laboratory and the first author of this study. “We have successfully developed the first comprehensive catalog of the exact types of human intestine, as well as an accurate and effective way to use it for research and in the clinic.”

By combining this catalog with existing clinical data, scientists have developed a model that can predict the presence of colon and rectum cancer only based on bacteria in stool samples. “Although we were confident in our strategy, the results were striking,” Matiga was excited. “We discovered 90 % of cancer cases, which is a very close result of the 94 % detection rate achieved by colonoscopy and better than all currently invasive detection methods.”

By combining more clinical data, this model can become more accurate and coincide with colonoscopy accuracy. It can become a routine examination tool and facilitate early detection of colon and rectal cancer, which will then be confirmed by colonoscopy but only in a selection of patients.

A new world of applications

A first clinical trial is created in cooperation with Geneva University Hospitals (HUG) to determine the stages of cancer and pests that can be discovered. However, applications go beyond colon and rectal cancer. By studying the differences between the sub -species of the same bacterial species, researchers can now determine the mechanisms of work through which they affect human health. “The same method can soon be used to develop non -invasive diagnostic tools for a wide range of diseases, all of which depend on the analysis of one microbial,” Merko Trajkovsky concludes.