Inferring food intake from multiple biomarkers using a latent variable model

DOI10.1214/21-AOAS1478zbMATH Open1498.62205arXiv2006.02995OpenAlexW3033781410MaRDI QIDQ132201FDOQ132201

Authors: Silvia D'Angelo, Lorraine Brennan, Isobel Claire Gormley, Silvia D'angelo, Lorraine Brennan, Isobel Claire Gormley 

Publication date: 4 June 2020

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: Metabolomic based approaches have gained much attention in recent years due to their promising potential to deliver objective tools for assessment of food intake. In particular, multiple biomarkers have emerged for single foods. However, there is a lack of statistical tools available for combining multiple biomarkers to infer food intake. Furthermore, there is a paucity of approaches for estimating the uncertainty around biomarker based prediction of intake. Here, to facilitate inference on the relationship between multiple metabolomic biomarkers and food intake in an intervention study conducted under the A-DIET research programme, a latent variable model, multiMarker, is proposed. The proposed model draws on factor analytic and mixture of experts models, describing intake as a continuous latent variable whose value gives raise to the observed biomarker values. We employ a mixture of Gaussian distributions to flexibly model the latent variable. A Bayesian hierarchical modelling framework provides flexibility to adapt to different biomarker distributions and facilitates prediction of the latent intake along with its associated uncertainty. Simulation studies are conducted to assess the performance of the proposed multiMarker framework, prior to its application to the motivating application of quantifying apple intake.

Full work available at URL: https://arxiv.org/abs/2006.02995

Recommendations

• Bayesian hierarchical models for food frequency assessment
• A new multivariate measurement error model with zero-inflated dietary data, and its application to dietary assessment
• Estimating the distribution of dietary consumption patterns
• Latent Class Analysis of Complex Sample Survey Data
• Seemingly Unrelated Measurement Error Models, with Application to Nutritional Epidemiology

zbMATH Keywords

factor analysislatent variable modelsmixture of expertsordinal regressionmetabolomics

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Cites Work

• Sparse Bayesian infinite factor models
• Robust factor analysis.
• Heteroscedastic factor mixture analysis
• Extension of the mixture of factor analyzers model to incorporate the multivariate \(t\)-distribution
• Mixtures of skew-\(t\) factor analyzers
• Title not available (Why is that?)
• Extending mixtures of factor models using the restricted multivariate skew-normal distribution
• Infinite mixtures of infinite factor analysers
• On the use of bootstrap with variational inference: theory, interpretation, and a two-sample test example
• A Note on Wadley's Problem with Overdispersion
• A factor mixture analysis model for multivariate binary data
• Measurement error correction and sensitivity analysis in longitudinal dietary intervention studies using an external validation study
• Title not available (Why is that?)
• Title not available (Why is that?)
• Penalized factor mixture analysis for variable selection in clustered data

Cited In (3)

• Extraction of food consumption systems by nonnegative matrix factorization (NMF) for the assessment of food choices
• multiMarker
• Using a Bayesian hierarchical linear mixing model to estimate botanical mixtures

Uses Software

• R
• multiMarker

This page was built for publication: Inferring food intake from multiple biomarkers using a latent variable model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q132201)