Gut Microbiome can be used as an indicator of health

The human microbiome can provide information about the risk of developing non-alcoholic fatty liver disease. This was discovered by an international team led by the Leibniz Institute for Natural Products Research and Infection Biology – the Hans Knöll Institute. The researchers developed a model that could predict the possible evolution of the disease based on the composition of intestinal microbes. The research was published in the journal Science Translational Medicine.

Up to 25 percent of the world’s population is affected by non-alcoholic fatty liver disease (NAFLD), which causes a higher number of fat cells in the liver. It is the most common chronic liver disease in industrialized countries around the world and, unlike alcoholic fatty liver, does not cause high alcohol consumption. In some people, undetected NAFLD can lead to liver scarring, liver cancer, or liver failure.

In a long-term study, Gianni Panagiotou, an international research team led by the Hibi Systems Biology and Bioinformatics Research Group at Leibniz, initially examined stools and blood samples from 1,200 people without NAFLD. “It has already been shown that human gut microorganisms contribute to the development of NAFLD. We wanted to know if the microbiome of a healthy person could predict whether or not they would develop NAFLD in the future,” Panagiotou explained. When the issues were re-examined four years later, it was revealed that 90 of them had developed NAFLD. Samples of those affected were compared with a control group of 90 people who did not have NAFLD at the base or follow-up visit. “Using different methods, we were able to find very subtle differences in the samples we took four years earlier,” explains Howell Leung, first author of HibI’s Panagiotou team at Leibniz. “With this data, we have been able to develop a model that predicts who will develop NAFLD in the future based on the microbiome with 80 percent certainty.” Currently, there are clinical models that use biochemical parameters in the blood to predict with 60 percent accuracy. “The model developed combines easily measurable information from blood with microbiome data and therefore can greatly increase reliability,” says Panagiotou.

Disease prediction through machine learning

The research team has developed a model called machine learning, a computer model trained to know certain models in a data set. The model can use these models to analyze new data sets and, in this case, to predict possible non-alcoholic fatty liver disease. “The whole process of developing our model took more than three years due to the complexity of the data. However, we were eventually successful and were able to create a useful tool for predicting NAFLD,” says Panagiotou.

Non-alcoholic fatty liver disease is irreversible and in the worst cases can even lead to liver cancer. People who already have a history or are particularly at risk should therefore be identified early in order to cope with the disease. “NAFLD is a silent disease. This means that it is asymptomatic in most cases and is usually detected only by chance,” explained Gianni Panagiotou. The number of Germans suffering from NAFLD is estimated at about 12 million. People with type 2 diabetes, obesity, hypertension or dyslipidemia are particularly affected by fatty liver disease.

Possible applications and next steps

Using the machine learning model, researchers have already been able to compare and validate the results with data from patients in the US and Europe. In the next step, Panagiotou intends to conduct a global study and use artificial intelligence to integrate larger data sets into research.

“I see microbiome-based diagnosis as something that will reach clinical practice and have great potential for the next ten years,” says Panagiotou. Early treatment of non-alcoholic fatty liver disease risk factors such as type 2 diabetes, hypertension and obesity can stop the development of the disease. Therefore, early prognosis is the only way to prevent the disease.

Reference: Leung H, Long X, Ni Y, et al. Risk assessment with intestinal microbiome and metabolite markers in the development of NAFLD. Sci Trans Med. 2022; 14 (648): eabk0855. doi: 10.1126 / scitranslmed.abk0855

This article has been republished from the following materials. Note: The material may have been edited for length and content. Contact the source for more information.

Leave a Comment