Metabolic profiling reveals risk of multiple diseases at once

nature medicine (2022). DOI: 10.1038 / s41591-022-01980-3″ width=”800″ height=”348″/>

Details of the metabolic state model. a) Overview of the remaining architecture of the metabolic state model. 168 circulating metabolic markers are fed to the common stem network to learn a common co-representation. The endpoint-specific head networks then predict the metabolic status of each endpoint from the co-representation and input using residual connectivity. b) Remaining head network details. attributed to him: nature medicine (2022). DOI: 10.1038 / s41591-022-01980-3

To prevent diseases from occurring in the first place, it is important to identify those individuals at particularly high risk as soon as possible. However, current screening methods are often expensive and focus only on one disease at a time. Scientists from the Berlin Institute of Health at the Charité (BIH), the Charité-University of Berlin and University College London identified 168 metabolic markers in the blood samples of more than 100,000 people and combined this data with their medical histories. With the help of artificial intelligence, they were able to predict the risk of developing several diseases with just one test and show where early intervention can be beneficial.

Their findings have now been published in the journal nature medicine.

Prevention is better than cure: This is the mantra that was on the minds of scientists from BIH, Charité and University College London when they began delving into the huge treasure trove of data in the UK Biobank. The British study has been tracking more than 500,000 participants for more than 15 years. Since all Britons have had an electronic health record since the 1990s, this anonymized data allows for monitoring of disease progression over long periods of time.

Recently, the UK Biobank made a massive data package available to researchers: participants were frozen blood samplessome of which were over 15 years old, were analyzed for their levels of 168 metabolites using nuclear magnetic resonance (NMR) spectroscopy.

This method is powerful, easy to perform, and relatively inexpensive. Measures levels of substances such as cholesterol and Blood sugar, but also less well-known molecules that are less recognized in blood tests. “Recent studies have shown that individual metabolites – intermediate or end products of metabolism – are associated with the development of a variety of diseases,” explains Jacob Steinfeldt, Physician Assistant in the Department of Cardiology at the Charité Campus Benjamin Franklin.

“We suspected that the combination of many different metabolites could provide predictive information about an individual’s risk of developing a number of different diseases. This is what we wanted to investigate.”

Calculating disease risk with artificial intelligence

Together with colleagues from the BIH’s Center for Digital Health, the scientists examined participants’ data on 24 common diseases – including metabolic disorders such as diabetes and cardiovascular diseases such as heart attacks and chronic diseases. heart failuremusculoskeletal diseases and a variety of cancers and neurological diseases such as Parkinson’s.

They identified participants who had any of the 24 diseases during the study and combined this information with the composition of metabolites in their blood (blood metabolite) from a sample taken prior to disease onset. With this information, they then turned into Artificial intelligence To create a model capable of calculating to what extent the metabolic state of the blood predicts the development of a disease in the future.

“We tested metabolic profiles for their predictive power and compared these results to traditional methods for calculating disease risk,” reports Thore Bürgel, a doctoral student at the BIH’s Center for Digital Health and co-first author of the paper with Jacob Steinfeldt. “We found that our profiles improved risk prediction for the majority of the diseases studied when we combined them with information about the age and sex of the participants.”

Seeking to identify early risks and take precautionary measures

The combination of age, gender, and metabolic status was able to predict the risk of developing diabetes or heart failure, for example, better than clinical predictors that measure glucose or cholesterol. At a cost of less than 20 euros, metabolite assay is relatively inexpensive.

“This is exciting, because we can use the metabolite to assess the risk of several diseases simultaneously,” explains Professor Ulf Landmesser, Director of Cardiology at the Charité Campus Benjamin Franklin. “Of course, if there are blood abnormalities that indicate an increased risk of disease, we will examine the patient more before the intervention. But that is exactly the direction we are also trying to move forward with the new focused Friede Springer Cardiovascular Prevention system: to motivate people to have regular check-ups after a certain age so that they can undergo it Preventative measurements “On time if necessary,” he says. “Most people already do the same with their cars.”

The scientists took their model one step further and calculated thresholds that could indicate when preventive interventions are recommended. Specifically: At what thresholds does the new method best identify those who can be saved from heart failure, for example, through the use of medications?

“Again, we saw that metabolic profiling combined with information on age and gender was as good or better than traditional analyzes in identifying patients who could benefit from a preventive intervention in the form of medication or Lifestyle change, “says Professor Roland Ailes, founding director of the Center for Digital Health in Bosnia and Herzegovina.” We have since been able to successfully validate our model in four other cohort studies conducted in the Netherlands and the United Kingdom, indicating that our models are broadly applicable. ”


How eating eggs can boost heart health


more information:
Roland Eils, Metabolic profiles predict individual multiple disease outcomes, nature medicine (2022). DOI: 10.1038 / s41591-022-01980-3

Provided by the Berlin Institute of Health at der Charité

the quote: Predictive Power of Blood: Metabolic Profiling Reveals Risk of Multiple Diseases at Once (September 22, 2022) Retrieved September 22, 2022 from

This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.