Data integration for prediction
of weight loss in randomized
controlled dietary trials
Rikke Linnemann Nielsen, Marianne Helenius, Sara L. Garcia, Henrik M. Roager, Derya Aytan‑Aktug, Lea Benedicte Skov Hansen, Mads Vendelbo Lind, Josef K. Vogt,
Marlene Danner Dalgaard, Martin I. Bahl, Cecilia Bang Jensen, Rasa Muktupavela,
Christina Warinner, Vincent Aaskov, Rikke Gøbel, Mette Kristensen, Hanne Frøkiær,
Morten H. Sparholt, Anders F. Christensen, Henrik Vestergaard, Torben Hansen,
Karsten Kristiansen, Susanne Brix, Thomas Nordahl Petersen, Lotte Lauritzen,
Tine Rask Licht, Oluf Pedersen and Ramneek Gupta
Abstract
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 nonresponders
with 80% confidence. Such models will be useful to assist in selecting appropriate weight
management strategies, as individual predisposition to diet response varies.
Scientific Reports (2020) DOI: https://doi.org/10.1038/s41598-020-76097-z