Cargando…

Data integration for prediction of weight loss in randomized controlled dietary trials

Diet is an important component in weight management strategies, but heterogeneous responses to the same diet make it difficult to foresee individual weight-loss outcomes. Omics-based technologies now allow for analysis of multiple factors for weight loss prediction at the individual level. Here, we...

Descripción completa

Detalles Bibliográficos
Autores principales: Nielsen, Rikke Linnemann, Helenius, Marianne, Garcia, Sara L., Roager, Henrik M., Aytan-Aktug, Derya, Hansen, Lea Benedicte Skov, Lind, Mads Vendelbo, Vogt, Josef K., Dalgaard, Marlene Danner, Bahl, Martin I., Jensen, Cecilia Bang, Muktupavela, Rasa, Warinner, Christina, Aaskov, Vincent, Gøbel, Rikke, Kristensen, Mette, Frøkiær, Hanne, Sparholt, Morten H., Christensen, Anders F., Vestergaard, Henrik, Hansen, Torben, Kristiansen, Karsten, Brix, Susanne, Petersen, Thomas Nordahl, Lauritzen, Lotte, Licht, Tine Rask, Pedersen, Oluf, Gupta, Ramneek
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7674420/
https://www.ncbi.nlm.nih.gov/pubmed/33208769
http://dx.doi.org/10.1038/s41598-020-76097-z
Descripción
Sumario:Diet is an important component in weight management strategies, but heterogeneous responses to the same diet make it difficult to foresee individual weight-loss outcomes. Omics-based technologies now allow for analysis of multiple factors for weight loss prediction at the individual level. Here, we classify weight loss responders (N = 106) and non-responders (N = 97) of overweight non-diabetic middle-aged Danes to two earlier reported dietary trials over 8 weeks. Random forest models integrated gut microbiome, host genetics, urine metabolome, measures of physiology and anthropometrics measured prior to any dietary intervention to identify individual predisposing features of weight loss in combination with diet. The most predictive models for weight loss included features of diet, gut bacterial species and urine metabolites (ROC-AUC: 0.84–0.88) compared to a diet-only model (ROC-AUC: 0.62). A model ensemble integrating multi-omics identified 64% of the non-responders with 80% confidence. Such models will be useful to assist in selecting appropriate weight management strategies, as individual predisposition to diet response varies.