FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149809682> ?p ?o ?g. }

• W3149809682 abstract "Abstract 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." @default.
• W3149809682 created "2021-04-13" @default.
• W3149809682 creator A5043557856 @default.
• W3149809682 creator A5057492639 @default.
• W3149809682 creator A5061982826 @default.
• W3149809682 creator A5083226215 @default.
• W3149809682 date "2021-04-06" @default.
• W3149809682 modified "2023-10-16" @default.
• W3149809682 title "Warped Bayesian Linear Regression for Normative Modelling of Big Data" @default.
• W3149809682 cites W1097741600 @default.
• W3149809682 cites W2006931708 @default.
• W3149809682 cites W2023485038 @default.
• W3149809682 cites W2030561475 @default.
• W3149809682 cites W2045246746 @default.
• W3149809682 cites W2082704080 @default.
• W3149809682 cites W2102521965 @default.
• W3149809682 cites W2229782077 @default.
• W3149809682 cites W2341441143 @default.
• W3149809682 cites W2342934749 @default.
• W3149809682 cites W2522628945 @default.
• W3149809682 cites W2561810854 @default.
• W3149809682 cites W2607804943 @default.
• W3149809682 cites W2742214638 @default.
• W3149809682 cites W2789530810 @default.
• W3149809682 cites W2896481393 @default.
• W3149809682 cites W2902182551 @default.
• W3149809682 cites W2902291850 @default.
• W3149809682 cites W2912484553 @default.
• W3149809682 cites W2952396505 @default.
• W3149809682 cites W2953822436 @default.
• W3149809682 cites W2976981404 @default.
• W3149809682 cites W3016980863 @default.
• W3149809682 cites W3084546953 @default.
• W3149809682 cites W3088995957 @default.
• W3149809682 cites W3097486279 @default.
• W3149809682 doi "https://doi.org/10.1101/2021.04.05.438429" @default.
• W3149809682 hasPublicationYear "2021" @default.
• W3149809682 type Work @default.
• W3149809682 sameAs 3149809682 @default.
• W3149809682 citedByCount "6" @default.
• W3149809682 countsByYear W31498096822021 @default.
• W3149809682 countsByYear W31498096822022 @default.
• W3149809682 crossrefType "posted-content" @default.
• W3149809682 hasAuthorship W3149809682A5043557856 @default.
• W3149809682 hasAuthorship W3149809682A5057492639 @default.
• W3149809682 hasAuthorship W3149809682A5061982826 @default.
• W3149809682 hasAuthorship W3149809682A5083226215 @default.
• W3149809682 hasBestOaLocation W31498096821 @default.
• W3149809682 hasConcept C105795698 @default.
• W3149809682 hasConcept C107673813 @default.
• W3149809682 hasConcept C111472728 @default.
• W3149809682 hasConcept C118552586 @default.
• W3149809682 hasConcept C124101348 @default.
• W3149809682 hasConcept C138885662 @default.
• W3149809682 hasConcept C149782125 @default.
• W3149809682 hasConcept C154945302 @default.
• W3149809682 hasConcept C15744967 @default.
• W3149809682 hasConcept C160234255 @default.
• W3149809682 hasConcept C33923547 @default.
• W3149809682 hasConcept C37903108 @default.
• W3149809682 hasConcept C41008148 @default.
• W3149809682 hasConcept C44725695 @default.
• W3149809682 hasConcept C58693492 @default.
• W3149809682 hasConcept C75684735 @default.
• W3149809682 hasConceptScore W3149809682C105795698 @default.
• W3149809682 hasConceptScore W3149809682C107673813 @default.
• W3149809682 hasConceptScore W3149809682C111472728 @default.
• W3149809682 hasConceptScore W3149809682C118552586 @default.
• W3149809682 hasConceptScore W3149809682C124101348 @default.
• W3149809682 hasConceptScore W3149809682C138885662 @default.
• W3149809682 hasConceptScore W3149809682C149782125 @default.
• W3149809682 hasConceptScore W3149809682C154945302 @default.
• W3149809682 hasConceptScore W3149809682C15744967 @default.
• W3149809682 hasConceptScore W3149809682C160234255 @default.
• W3149809682 hasConceptScore W3149809682C33923547 @default.
• W3149809682 hasConceptScore W3149809682C37903108 @default.
• W3149809682 hasConceptScore W3149809682C41008148 @default.
• W3149809682 hasConceptScore W3149809682C44725695 @default.
• W3149809682 hasConceptScore W3149809682C58693492 @default.
• W3149809682 hasConceptScore W3149809682C75684735 @default.
• W3149809682 hasLocation W31498096821 @default.
• W3149809682 hasLocation W31498096822 @default.
• W3149809682 hasLocation W31498096823 @default.
• W3149809682 hasLocation W31498096824 @default.
• W3149809682 hasOpenAccess W3149809682 @default.
• W3149809682 hasPrimaryLocation W31498096821 @default.
• W3149809682 hasRelatedWork W1491323266 @default.
• W3149809682 hasRelatedWork W1529240532 @default.
• W3149809682 hasRelatedWork W2002018901 @default.
• W3149809682 hasRelatedWork W2005820577 @default.
• W3149809682 hasRelatedWork W2134762404 @default.
• W3149809682 hasRelatedWork W2158495165 @default.
• W3149809682 hasRelatedWork W2772689174 @default.
• W3149809682 hasRelatedWork W3142112636 @default.
• W3149809682 hasRelatedWork W4210400087 @default.
• W3149809682 hasRelatedWork W4233907568 @default.
• W3149809682 isParatext "false" @default.
• W3149809682 isRetracted "false" @default.
• W3149809682 magId "3149809682" @default.
• W3149809682 workType "article" @default.