Using machine learning to predict the consumption of a Mediterranean diet with untargeted metabolomics data from controlled feeding studies
RF and DT models can predict the consumption of a MedDiet diet with high accuracy in full-feeding conditions in males based on plasma untargeted metabolomics data. However, accuracy is reduced when models are applied to a more heterogenous sample (sample of males and females and less controlled feeding conditions).
Authors
- Jacques Corbeil (ORCID: https://orcid.org/0000-0002-9973-2740)
- Benoı̂t Lamarche (ORCID: https://orcid.org/0000-0002-4443-5378)
- Pier-Luc Plante (ORCID: https://orcid.org/0000-0002-3700-8239)
- Francis Brière
- Didier Brassard (ORCID: https://orcid.org/0000-0002-7064-3066)
- Simone Lemieux (ORCID: https://orcid.org/0000-0003-3170-4062)
- Mélina Côté (ORCID: https://orcid.org/0000-0003-2206-9124)
- Patrick Couture (ORCID: https://orcid.org/0000-0002-8414-3847)
Institutions
- Université Laval (CA)
Publication Details
- Journal
- Nutrition Metabolism and Cardiovascular Diseases
- Published
- 2025-09-04
- DOI
- https://doi.org/10.1016/j.numecd.2025.104290
- Citations
- 1
- Primary Topic
- Nutritional Studies and Diet
- Type
- article
- Field-Weighted Citation Impact
- 1.88