Data integration for prediction of weight loss in randomized controlled dietary trials
| Autor: | Marlene Danner Dalgaard, Christina Warinner, Rasa Muktupavela, Lea Benedicte Skov Hansen, Torben Hansen, Henrik Vestergaard, Thomas Nordahl Petersen, Morten H. Sparholt, Vincent Aaskov, Cecilia Bang Jensen, Ramneek Gupta, Sara L. Garcia, Mads Vendelbo Lind, Lotte Lauritzen, Derya Aytan-Aktug, Oluf Pedersen, Josef Korbinian Vogt, Tine Rask Licht, Mette Kristensen, Karsten Kristiansen, Susanne Brix, Rikke Linnemann Nielsen, Henrik Munch Roager, Hanne Frøkiær, Marianne Helenius, Anders F. Christensen, Rikke J Gøbel, Martin Iain Bahl |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Male
0301 basic medicine lcsh:Medicine Physiology Urine Overweight Machine Learning 0302 clinical medicine Weight loss Weight management Computational models Sequencing Medicine lcsh:Science Randomized Controlled Trials as Topic Whole Grains Multidisciplinary Postprandial Period Data processing Treatment Outcome Female Data integration medicine.symptom Microbial genetics Genotype Predictive medicine 030209 endocrinology & metabolism Article 03 medical and health sciences SDG 3 - Good Health and Well-being Weight Loss Metabolome Humans Metabolomics business.industry lcsh:R Reproducibility of Results DNA Anthropometry Omics Individual level Computer science Gastrointestinal Microbiome 030104 developmental biology ROC Curve Computer modelling lcsh:Q business Biomarkers Diet Therapy Genome-Wide Association Study |
| Zdroj: | Scientific Reports, Vol 10, Iss 1, Pp 1-15 (2020) Scientific Reports Nielsen, R L, Helenius, M, Garcia, S L, Roager, H M, Aytan-Aktug, D, Hansen, L B S, Lind, M V, Vogt, J K, Dalgaard, M D, Bahl, M I, Jensen, C B, Muktupavela, R, Warinner, C, Aaskov, V, Gøbel, R, Kristensen, M B, Frøkiær, H, Sparholt, M H, Christensen, A F, Vestergaard, H, Hansen, T, Kristiansen, K, Brix, S, Petersen, T N, Lauritzen, L, Licht, T R, Pedersen, O & Gupta, R 2020, ' Data integration for prediction of weight loss in randomized controlled dietary trials ', Scientific Reports, vol. 10, 20103 . https://doi.org/10.1038/s41598-020-76097-z Nielsen, R L, Helenius, M, Garcia, S L, Roager, H M, Aytan-Aktug, D, Hansen, L B S, Lind, M V, Vogt, J K, Dalgaard, M D, Bahl, M I, Jensen, C B, Muktupavela, R, Warinner, C, Aaskov, V, Gøbel, R, Kristensen, M, Frøkiær, H, Sparholt, M H, Christensen, A F, Vestergaard, H, Hansen, T, Kristiansen, K, Brix, S, Petersen, T N, Lauritzen, L, Licht, T R, Pedersen, O & Gupta, R 2020, ' Data integration for prediction of weight loss in randomized controlled dietary trials ', Scientific Reports, vol. 10, no. 1, 20103 . https://doi.org/10.1038/s41598-020-76097-z |
| ISSN: | 2045-2322 |
| DOI: | 10.1038/s41598-020-76097-z |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|