Predicting resting metabolic rate in healthy adults: a comparative analysis using the enable cohort.

Brandl B, Keppner GM, Manz Q, Schicker C, Fromme T, Holzapfel C, Kleigrewe K, Bosy-Westphal A, Müller MJ, Volkert D, Skurk T, Hauner H, List M, Klingenspor M (2026)

Publication Type: Journal article

Publication year: 2026

Journal

American Journal of Physiology-Endocrinology and Metabolism American Physiological Society

Book Volume: 330

Pages Range: E247-E256

Journal Issue: 2

DOI: 10.1152/ajpendo.00375.2025

Abstract

Resting metabolic rate (RMR) is modulated by a variety of factors. Accurate prediction of RMR is essential for planning energy requirements but remains challenging due to interindividual variability. This study aimed to develop and evaluate machine learning models for predicting RMR using comprehensive data from the cross-sectional enable study and to identify the most predictive and stable features across different study populations. RMR was predicted using data from 454 participants of the enable phenotyping platform (Freising and Nuremberg cohort). We systematically compared linear and nonlinear machine learning models trained on either the full set of 94 predictors or a reduced set of routinely accessible variables, including sex, age, body weight, fat mass, and fat-free mass. Model performance was assessed by cross-validation. The best-performing model (Lasso) was further evaluated on independent test datasets from other cohorts. Feature importance and stability were assessed using repeated cross-validation and marginal variance decomposition. Lasso regression consistently outperformed other models, particularly when trained on the enable cohort feature set. The final model explained 76.8% of RMR variance in the Freising cohort. Key predictive features included fat-free mass, body weight, and mean outdoor temperature. Blood-based features contributed marginally, whereas microbiota and fecal short-chain fatty acids variables did not contribute to explaining RMR. This novel prediction model for RMR shows improved accuracy in comparison with traditional models. Although microbiota composition did not contribute to explain the residual variation in RMR, the inclusion of clinical blood parameters and outdoor temperature improved predictive performance. Clinical Trial Registry Number: DRKS00009797.NEW & NOTEWORTHY We introduce a novel machine learning framework for predicting resting metabolic rate (RMR), emphasizing the superior performance of Lasso regression. Our analysis incorporates both standard clinical variables and previously underexplored factors such as gut microbiota, fecal short-chain fatty acids (SCFAs), and mean outdoor temperature.

Authors with CRIS profile

Dorothee Volkert Professur für Klinische Ernährung im Alter

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) Christian-Albrechts-Universität zu Kiel DE Germany (DE)

How to cite

APA:

Brandl, B., Keppner, G.M., Manz, Q., Schicker, C., Fromme, T., Holzapfel, C.,... Klingenspor, M. (2026). Predicting resting metabolic rate in healthy adults: a comparative analysis using the enable cohort. American Journal of Physiology-Endocrinology and Metabolism, 330(2), E247-E256. https://doi.org/10.1152/ajpendo.00375.2025

MLA:

Brandl, Beate, et al. "Predicting resting metabolic rate in healthy adults: a comparative analysis using the enable cohort." American Journal of Physiology-Endocrinology and Metabolism 330.2 (2026): E247-E256.

BibTeX: Download