Biology subjects

Fraza, C.

Publications and source records attributed to Fraza, C..

7 recordsLinked to original sources

bioRxiv2026

Protocol Update: The Normative Modelling Paradigm for Computational Psychiatry

Normative Modelling ( brain growth charting) is now a well-established method for computational psychiatry and involves charting centiles of variation across a population in terms of mappings between biology and behavior, providing statistical inferences at the level of the individual. These models have helped the field to move away from case-control analysis toward individual-level analysis. Correspondingly, normative modelling has now been applied to chart brain development and ageing in many populations and has been used to quantify individual deviations across various neurological and psychiatric conditions. This has been supported by large-scale models that are openly accessible for diverse brain imaging modalities. As normative modelling continues to grow, several recent methodological developments, such as non-Gaussian models, longitudinal models, and federated learning, have been implemented in different software tools, including the Predictive Clinical Neuroscience toolkit (PCNtoolkit). In this protocol update, we provide: (i) a revised overview of this methodological landscape; (ii) an update to our 2022 standardised analytical protocol for normative modelling of neuroimaging data, including options for federated and longitudinal normative models; (iii) practical guidance suited to both novice and experienced practitioners supported by open-source code examples implemented in the refactored version of PCNtoolkit; and (iv) updated models for cortical thickness, surface area, volumetric data, functional connectivity and diffusion-weighted imaging for use by the community.

neuroscience↗

bioRxiv2025

The Art of Not Knowing: Accommodating Structured Missingness in Biomedical Research

Missing data remain a ubiquitous and critical challenge in large-scale clinical studies. Despite advances in imputation, most existing methods fail to address structured missingness, where data are missing according a deterministic pattern and which arise due to systematic patterns introduced by experimental design, site protocols, or cohort differences. These patterns violate key assumptions of most imputation algorithms, yet their impact is rarely evaluated. We demonstrate that structured missingness is a fundamental challenge to drawing valid inferences from standard imputation techniques. First, we present a comprehensive framework for understanding and accommodating the effects of structured missingness. Next, we show through simulations and real-world psychometric data with structured missingness, that widely used algorithms optimised for numerical precision (e.g., Extra Trees, AutoComplete) underperform due to site effects, while donor-based methods (e.g., MICE, hierarchical MICE) better preserve multivariate structure. We propose a novel hierarchical approach that provides optimal performance in simulated and experimental data. Finally, we show that commonly used accuracy metrics, such as mean squared error can obscure these failures, and are therefore inadequate for the evaluation of structured missingness. In contrast, other divergence-based metrics offer a more sensitive and interpretable alternative. We apply this approach to harmonising psychometric data across cohorts, which provides excellent item-level alignment across different instruments. Our study highlights the need for a paradigm shift in handling missing data within biomedical research, moving beyond conventional imputation frameworks to develop tools that can account for structured missingness. This shift is essential for ensuring reliable inference in multi-site clinical studies, precision medicine, and large-scale population analyses.

neuroscience↗

bioRxiv2023

Using normative models pre-trained on cross-sectional data to evaluate longitudinal changes in neuroimaging data

Longitudinal neuroimaging studies offer valuable insight into intricate dynamics of brain development, ageing, and disease progression over time. However, prevailing analytical approaches rooted in our understanding of population variation are primarily tailored for cross-sectional studies. To fully harness the potential of longitudinal neuroimaging data, we have to develop and refine methodologies that are adapted to longitudinal designs, considering the complex interplay between population variation and individual dynamics. We build on normative modelling framework, which enables the evaluation of an individuals position compared to a population standard. We extend this framework to evaluate an individuals longitudinal change compared to the longitudinal change reflected by the (population) standard dynamics. Thus, we exploit the existing normative models pre-trained on over 58,000 individuals and adapt the framework so that they can also be used in the evaluation of longitudinal studies. Specifically, we introduce a quantitative metric termed "z-diff" score, which serves as an indicator of a temporal change of an individual compared to a population standard. Notably, our framework offers advantages such as flexibility in dataset size and ease of implementation. To illustrate our approach, we applied it to a longitudinal dataset of 98 patients diagnosed with early-stage schizophrenia who underwent MRI examinations shortly after diagnosis and one year later. Compared to cross-sectional analyses, which showed global thinning of grey matter at the first visit, our method revealed a significant normalisation of grey matter thickness in the frontal lobe over time. Furthermore, this result was not observed when using more traditional methods of longitudinal analysis, making our approach more sensitive to temporal changes. Overall, our framework presents a flexible and effective methodology for analysing longitudinal neuroimaging data, providing insights into the progression of a disease that would otherwise be missed when using more traditional approaches.

neuroscience↗

bioRxiv2022

Non-Gaussian Normative Modelling With Hierarchical Bayesian Regression

Normative modelling is an emerging technique for parsing heterogeneity in clinical cohorts. This can be implemented in practice using hierarchical Bayesian regression, which provides an elegant probabilistic solution to handle site variation in a federated learning framework. However, applications of this method to date have employed a Gaussian assumption, which may be restrictive in some applications. We have extended the hierarchical Bayesian regression framework to flexibly model non-Gaussian data with heteroskdastic skewness and kurtosis. To this end, we employ a flexible distribution from the sinh-arcsinh (SHASH) family, and introduce a novel reparameterisation and a Markov chain Monte Carlo sampling approach to perform inference in this model. Using a large neuroimaging dataset collected at 82 different sites, we show that the results achieved with this extension are equivalent or better than a warped Bayesian linear regression baseline model on most datasets, whilst providing better control over the parameters governing the shape of distributions that approach is able to model. We also demonstrate that the attained flexibility is useful for accurately modelling highly nonlinear relationships between aging and imaging derived phenotypes, which shows that the extension is important for pushing the field of normative modelling forward. All methods described here are available in the open-source pcntoolkit. HighlightsO_LIWe extended the Hierarchical Bayesian Regression framework for normative modelling C_LIO_LIOur extension allows modelling data with heteroskedastic skewness and kurtosis C_LIO_LIWe developed a reparameterization of the SHASH distribution, suitable for sampling C_LIO_LIWe provide the first implementation of the SHASH distribution in a fully Bayesian framework C_LIO_LIResults show that the extension outperforms current methods on various measures C_LI

neuroscience↗

bioRxiv2021

The Normative Modeling Framework for Computational Psychiatry

Normative modeling is an emerging and innovative framework for mapping individual differences at the level of a single subject or observation in relation to a reference model. It involves charting centiles of variation across a population in terms of mappings between biology and behavior which can then be used to make statistical inferences at the level of the individual. The fields of computational psychiatry and clinical neuroscience have been slow to transition away from patient versus "healthy" control analytic approaches, likely due to a lack of tools designed to properly model biological heterogeneity of mental disorders. Normative modeling provides a solution to address this issue and moves analysis away from case-control comparisons that rely on potentially noisy clinical labels. In this article, we define a standardized protocol to guide users through, from start to finish, normative modeling analysis using the Predictive Clinical Neuroscience toolkit (PCNtoolkit). We describe the input data selection process, provide intuition behind the various modeling choices, and conclude by demonstrating several examples of down-stream analyses the normative model results may facilitate, such as stratification of high-risk individuals, subtyping, and behavioral predictive modeling. The protocol takes approximately 1-3 hours to complete.

neuroscience↗

bioRxiv2021

Charting Brain Growth and Aging at High Spatial Precision

Defining reference models for population variation, and the ability to study individual deviations is essential for understanding inter-individual variability and its relation to the onset and progression of medical conditions. In this work, we assembled a reference cohort of neuroimaging data from 82 sites (N=58,836; ages 2-100) and use normative modeling to characterize lifespan trajectories of cortical thickness and subcortical volume. Models are validated against a manually quality checked subset (N=24,354) and we provide an interface for transferring to new data sources. We showcase the clinical value by applying the models to a transdiagnostic psychiatric sample (N=1,985), showing they can be used to quantify variability underlying multiple disorders whilst also refining case-control inferences. These models will be augmented with additional samples and imaging modalities as they become available. This provides a common reference platform to bind results from different studies and ultimately paves the way for personalized clinical decision making.

neuroscience↗

bioRxiv2021

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 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.

neuroscience↗