Data integration prediction

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

https://www.3g-center.dk/publications/data-integration-prediction
10 DECEMBER 2024