Cargando…

Warped Bayesian Linear Regression for Normative Modelling of Big Data

Normative modelling is becoming more popular in neuroimaging due to its ability to make predictions of deviation from a normal trajectory at the level of individual participants. It allows the user to model the distribution of several neuroimaging modalities, giving an estimation for the mean and ce...

Descripción completa

Detalles Bibliográficos
Autores principales: Fraza, Charlotte J., Dinga, Richard, Beckmann, Christian F., Marquand, Andre F.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7613680/
https://www.ncbi.nlm.nih.gov/pubmed/34798518
http://dx.doi.org/10.1101/2021.04.05.438429
_version_ 1783605509213913088
author Fraza, Charlotte J.
Dinga, Richard
Beckmann, Christian F.
Marquand, Andre F.
author_facet Fraza, Charlotte J.
Dinga, Richard
Beckmann, Christian F.
Marquand, Andre F.
author_sort Fraza, Charlotte J.
collection PubMed
description Normative modelling is becoming more popular in neuroimaging due to its ability to make predictions of deviation from a normal trajectory at the level of individual participants. It allows the user to model the distribution of several neuroimaging modalities, giving an estimation for the mean and centiles of variation. With the increase in the availability of big data in neuroimaging, there is a need to scale normative modelling to big data sets. However, the scaling of normative models has come with several challenges. So far, most normative modelling approaches used Gaussian process regression, and although suitable for smaller datasets (up to a few thousand participants) it does not scale well to the large cohorts currently available and being acquired. Furthermore, most neuroimaging modelling methods that are available assume the predictive distribution to be Gaussian in shape. However, deviations from Gaussianity can be frequently found, which may lead to incorrect inferences, particularly in the outer centiles of the distribution. In normative modelling, we use the centiles to give an estimation of the deviation of a particular participant from the ‘normal’ trend. Therefore, especially in normative modelling, the correct estimation of the outer centiles is of utmost importance, which is also where data are sparsest. Here, we present a novel framework based on Bayesian Linear Regression with likelihood warping that allows us to address these problems, that is, to scale normative modelling elegantly to big data cohorts and to correctly model non-Gaussian predictive distributions. In addition, this method provides also likelihood-based statistics, which are useful for model selection. To evaluate this framework, we use a range of neuroimaging-derived measures from the UK Biobank study, including image-derived phenotypes (IDPs) and whole-brain voxel-wise measures derived from diffusion tensor imaging. We show good computational scaling and improved accuracy of the warped BLR for certain IDPs and voxels if there was a deviation from normality of these parameters in their residuals. The present results indicate the advantage of a warped BLR in terms of; computational scalability and the flexibility to incorporate non-linearity and non-Gaussianity of the data, giving a wider range of neuroimaging datasets that can be correctly modelled.
format Online
Article
Text
id pubmed-7613680
institution National Center for Biotechnology Information
language English
publishDate 2021
record_format MEDLINE/PubMed
spelling pubmed-76136802022-10-06 Warped Bayesian Linear Regression for Normative Modelling of Big Data Fraza, Charlotte J. Dinga, Richard Beckmann, Christian F. Marquand, Andre F. Neuroimage Article Normative modelling is becoming more popular in neuroimaging due to its ability to make predictions of deviation from a normal trajectory at the level of individual participants. It allows the user to model the distribution of several neuroimaging modalities, giving an estimation for the mean and centiles of variation. With the increase in the availability of big data in neuroimaging, there is a need to scale normative modelling to big data sets. However, the scaling of normative models has come with several challenges. So far, most normative modelling approaches used Gaussian process regression, and although suitable for smaller datasets (up to a few thousand participants) it does not scale well to the large cohorts currently available and being acquired. Furthermore, most neuroimaging modelling methods that are available assume the predictive distribution to be Gaussian in shape. However, deviations from Gaussianity can be frequently found, which may lead to incorrect inferences, particularly in the outer centiles of the distribution. In normative modelling, we use the centiles to give an estimation of the deviation of a particular participant from the ‘normal’ trend. Therefore, especially in normative modelling, the correct estimation of the outer centiles is of utmost importance, which is also where data are sparsest. Here, we present a novel framework based on Bayesian Linear Regression with likelihood warping that allows us to address these problems, that is, to scale normative modelling elegantly to big data cohorts and to correctly model non-Gaussian predictive distributions. In addition, this method provides also likelihood-based statistics, which are useful for model selection. To evaluate this framework, we use a range of neuroimaging-derived measures from the UK Biobank study, including image-derived phenotypes (IDPs) and whole-brain voxel-wise measures derived from diffusion tensor imaging. We show good computational scaling and improved accuracy of the warped BLR for certain IDPs and voxels if there was a deviation from normality of these parameters in their residuals. The present results indicate the advantage of a warped BLR in terms of; computational scalability and the flexibility to incorporate non-linearity and non-Gaussianity of the data, giving a wider range of neuroimaging datasets that can be correctly modelled. 2021-12-15 2021-11-17 /pmc/articles/PMC7613680/ /pubmed/34798518 http://dx.doi.org/10.1101/2021.04.05.438429 Text en https://creativecommons.org/licenses/by/4.0/This work is licensed under a CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) International license.
spellingShingle Article
Fraza, Charlotte J.
Dinga, Richard
Beckmann, Christian F.
Marquand, Andre F.
Warped Bayesian Linear Regression for Normative Modelling of Big Data
title Warped Bayesian Linear Regression for Normative Modelling of Big Data
title_full Warped Bayesian Linear Regression for Normative Modelling of Big Data
title_fullStr Warped Bayesian Linear Regression for Normative Modelling of Big Data
title_full_unstemmed Warped Bayesian Linear Regression for Normative Modelling of Big Data
title_short Warped Bayesian Linear Regression for Normative Modelling of Big Data
title_sort warped bayesian linear regression for normative modelling of big data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7613680/
https://www.ncbi.nlm.nih.gov/pubmed/34798518
http://dx.doi.org/10.1101/2021.04.05.438429
work_keys_str_mv AT frazacharlottej warpedbayesianlinearregressionfornormativemodellingofbigdata
AT dingarichard warpedbayesianlinearregressionfornormativemodellingofbigdata
AT beckmannchristianf warpedbayesianlinearregressionfornormativemodellingofbigdata
AT marquandandref warpedbayesianlinearregressionfornormativemodellingofbigdata