We use cookies on our website. Some are necessary for the operation of the website. You can also allow cookies for statistical purposes. You can adjust the data protection settings or agree to all cookies directly.
Development of a semantic knowledge base with integrated specific machine learning methods for the transnational project AMBROSIA for the development and evaluation of an innovative food product against malnutrition in elderly people with heart disease (AMBROSIA)
Project
Project code: 2820ERA20E
Contract period: 01.01.2021
- 31.12.2023
Budget: 166,474 Euro
Purpose of research: Experimental development
Keywords: nutrition, nutritional information/recommendation, malnutrition, health-related consumer protection, health promotion, food analysis, modeling, prevention, elderly people
The transnational and multidisciplinary AMBROSIA project addresses one of the current major challenges in the field of nutrition and health, malnutrition in a well-defined 'elderly' population such as patients with heart failure (HF) and atrial fibrillation (AF). In these patients, malnutrition is a key factor leading to inflammation, loss of function and ultimately death. AF and HF contribute to a frail state and these patients enter a vicious cycle of 'malnutrition, inflammation and cachexia that progressively determines cognitive decline and body mass regression. The aim of AMBROSIA is to develop an innovative food product, extensively investigate its mode of action and efficacy for preventing malnutrition in elderly HF and AF patients. For this purpose, a clinical trial is conducted and predictors of malnutrition and mode of action of the treatment are identified using high-throughput experimental data, an integrated semantic knowledge base and specially developed machine learning methods. As the German project partner, Genevention GmbH is developing a systems medicine platform, based on its proprietary 'semares' software system, in which the very diverse data can be captured, annotated and linked ('integrated'). Semantic technologies and sustainable data management concepts are used for the integration purpose. In addition, Genevention is developing specific machine learning (ML) methods for the project to deeply analyze the AMBROSIA data. In particular, the development of the ML methods will investigate the possibility to combine clinical and different experimental data in a meaningful way based on their harmonized annotations. The developed ML applications will be integrated into the AMBROSIA platform so that they are available to clinical end users for identifying potential biomarkers for early detection of malnutrition and the mode of action of the Ambrosia bar.
Section overview
Subjects
- Physiology of Nutrition