•We present a warped Bayesian Linear Regression (BLR) and demonstrate it on data from the UK Biobank.•The non-linearity of the model improves the fit and out of sample predictions for most ...variables.•Non-Gaussianity of the data can be included with the incorporation of the likelihood warping.•A trade-off between fit and complexity can be chosen optimally, without crossvalidation.•BLR is computationally less demanding than GPR and is therefore scalable to big datasets.
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 correctly model non-Gaussian predictive distributions and scale normative modelling elegantly to big data cohorts. In addition, this method provides 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.
•
Using methods of Drysdale et al. (2017) we have obtained extremely high canonical correlations and optimal 3 cluster solution
•
These, however, were not statistically significant after performing ...sufficiently rigorous statistical tests
•
We argue that the methods used in Drysdale et al. (2017) do not provide convincing evidence for biotypes of depression
•Extensive overview on pattern classification and stratification studies in ASD.•Compares pattern classification and stratifications approaches head-on.•Presents potential future directions for both ...approaches in ASD research.•Suggest promising avenues for clinical translation of these two approaches.
Pattern classification and stratification approaches have increasingly been used in research on Autism Spectrum Disorder (ASD) over the last ten years with the goal of translation towards clinical applicability. Here, we present an extensive scoping literature review on those two approaches. We screened a total of 635 studies, of which 57 pattern classification and 19 stratification studies were included. We observed large variance across pattern classification studies in terms of predictive performance from about 60% to 98% accuracy, which is among other factors likely linked to sampling bias, different validation procedures across studies, the heterogeneity of ASD and differences in data quality. Stratification studies were less prevalent with only two studies reporting replications and just a few showing external validation. While some identified strata based on cognition and intelligence reappear across studies, biology as a stratification marker is clearly underexplored. In summary, mapping biological differences at the level of the individual with ASD is a major challenge for the field now. Conceptualizing those mappings and individual trajectories that lead to the diagnosis of ASD, will become a major challenge in the near future.
Alterations in regional subcortical brain volumes have been investigated as part of the efforts of an international consortium, ENIGMA, to identify reliable neural correlates of major depressive ...disorder (MDD). Given that subcortical structures are comprised of distinct subfields, we sought to build significantly from prior work by precisely mapping localized MDD‐related differences in subcortical regions using shape analysis. In this meta‐analysis of subcortical shape from the ENIGMA‐MDD working group, we compared 1,781 patients with MDD and 2,953 healthy controls (CTL) on individual measures of shape metrics (thickness and surface area) on the surface of seven bilateral subcortical structures: nucleus accumbens, amygdala, caudate, hippocampus, pallidum, putamen, and thalamus. Harmonized data processing and statistical analyses were conducted locally at each site, and findings were aggregated by meta‐analysis. Relative to CTL, patients with adolescent‐onset MDD (≤ 21 years) had lower thickness and surface area of the subiculum, cornu ammonis (CA) 1 of the hippocampus and basolateral amygdala (Cohen's d = −0.164 to −0.180). Relative to first‐episode MDD, recurrent MDD patients had lower thickness and surface area in the CA1 of the hippocampus and the basolateral amygdala (Cohen's d = −0.173 to −0.184). Our results suggest that previously reported MDD‐associated volumetric differences may be localized to specific subfields of these structures that have been shown to be sensitive to the effects of stress, with important implications for mapping treatments to patients based on specific neural targets and key clinical features.
•Development and presentation of normative modeling approach based on hierarchical Bayesian modeling that can be applied to large multi-site neuroimaging data sets.•Comparison of performance of ...hierarchical Bayesian model including site as covariate to several common ways to harmonize for multi-site effects.•Presentation of normative modeling as site correction tool.
The potential of normative modeling to make individualized predictions from neuroimaging data has enabled inferences that go beyond the case-control approach. However, site effects are often confounded with variables of interest in a complex manner and can bias estimates of normative models, which has impeded the application of normative models to large multi-site neuroimaging data sets. In this study, we suggest accommodating for these site effects by including them as random effects in a hierarchical Bayesian model. We compared the performance of a linear and a non-linear hierarchical Bayesian model in modeling the effect of age on cortical thickness. We used data of 570 healthy individuals from the ABIDE (autism brain imaging data exchange) data set in our experiments. In addition, we used data from individuals with autism to test whether our models are able to retain clinically useful information while removing site effects. We compared the proposed single stage hierarchical Bayesian method to several harmonization techniques commonly used to deal with additive and multiplicative site effects using a two stage regression, including regressing out site and harmonizing for site with ComBat, both with and without explicitly preserving variance caused by age and sex as biological variation of interest, and with a non-linear version of ComBat. In addition, we made predictions from raw data, in which site has not been accommodated for. The proposed hierarchical Bayesian method showed the best predictive performance according to multiple metrics. Beyond that, the resulting z-scores showed little to no residual site effects, yet still retained clinically useful information. In contrast, performance was particularly poor for the regression model and the ComBat model in which age and sex were not explicitly modeled. In all two stage harmonization models, predictions were poorly scaled, suffering from a loss of more than 90% of the original variance. Our results show the value of hierarchical Bayesian regression methods for accommodating site variation in neuroimaging data, which provides an alternative to harmonization techniques. While the approach we propose may have broad utility, our approach is particularly well suited to normative modeling where the primary interest is in accurate modeling of inter-subject variation and statistical quantification of deviations from a reference model.
Many variables have been linked to different course trajectories of depression. These findings, however, are based on group comparisons with unknown translational value. This study evaluated the ...prognostic value of a wide range of clinical, psychological, and biological characteristics for predicting the course of depression and aimed to identify the best set of predictors. Eight hundred four unipolar depressed patients (major depressive disorder or dysthymia) patients were assessed on a set involving 81 demographic, clinical, psychological, and biological measures and were clinically followed-up for 2 years. Subjects were grouped according to (i) the presence of a depression diagnosis at 2-year follow-up (yes n = 397, no n = 407), and (ii) three disease course trajectory groups (rapid remission, n = 356, gradual improvement n = 273, and chronic n = 175) identified by a latent class growth analysis. A penalized logistic regression, followed by tight control over type I error, was used to predict depression course and to evaluate the prognostic value of individual variables. Based on the inventory of depressive symptomatology (IDS), we could predict a rapid remission course of depression with an AUROC of 0.69 and 62% accuracy, and the presence of an MDD diagnosis at follow-up with an AUROC of 0.66 and 66% accuracy. Other clinical, psychological, or biological variables did not significantly improve the prediction. Among the large set of variables considered, only the IDS provided predictive value for course prediction on an individual level, although this analysis represents only one possible methodological approach. However, accuracy of course prediction was moderate at best and further improvement is required for these findings to be clinically useful.
Clinical neuroimaging data availability has grown substantially in the last decade, providing the potential for studying heterogeneity in clinical cohorts on a previously unprecedented scale. ...Normative modeling is an emerging statistical tool for dissecting heterogeneity in complex brain disorders. However, its application remains technically challenging due to medical data privacy issues and difficulties in dealing with nuisance variation, such as the variability in the image acquisition process. Here, we approach the problem of estimating a reference normative model across a massive population using a massive multi-center neuroimaging dataset. To this end, we introduce a federated probabilistic framework using hierarchical Bayesian regression (HBR) to complete the life-cycle of normative modeling. The proposed model provides the possibilities to learn, update, and adapt the model parameters on decentralized neuroimaging data. Our experimental results confirm the superiority of HBR in deriving more accurate normative ranges on large multi-site neuroimaging datasets compared to the current standard methods. In addition, our approach provides the possibility to recalibrate and reuse the learned model on local datasets and even on datasets with very small sample sizes. The proposed method will facilitate applications of normative modeling as a medical tool for screening the biological deviations in individuals affected by complex illnesses such as mental disorders.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Clinical neuroimaging data availability has grown substantially in the last decade, providing the potential for studying heterogeneity in clinical cohorts on a previously unprecedented scale. ...Normative modeling is an emerging statistical tool for dissecting heterogeneity in complex brain disorders. However, its application remains technically challenging due to medical data privacy issues and difficulties in dealing with nuisance variation, such as the variability in the image acquisition process. Here, we approach the problem of estimating a reference normative model across a massive population using a massive multi-center neuroimaging dataset. To this end, we introduce a federated probabilistic framework using hierarchical Bayesian regression (HBR) to complete the life-cycle of normative modeling. The proposed model provides the possibilities to learn, update, and adapt the model parameters on decentralized neuroimaging data. Our experimental results confirm the superiority of HBR in deriving more accurate normative ranges on large multi-site neuroimaging datasets compared to the current standard methods. In addition, our approach provides the possibility to recalibrate and reuse the learned model on local datasets and even on datasets with very small sample sizes. The proposed method will facilitate applications of normative modeling as a medical tool for screening the biological deviations in individuals affected by complex illnesses such as mental disorders.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
•Patients with major depressive disorder (MDD) show variable clinical trajectories.•Generative embedding (GE) is used to predict clinical trajectories in MDD patients.•GE classifies patients with ...chronic depression vs. fast remission with 79% accuracy.•GE provides mechanistic interpretability and outperforms conventional measures.•Proof-of-concept that illustrates the potential of GE for clinical prediction.
Patients with major depressive disorder (MDD) show heterogeneous treatment response and highly variable clinical trajectories: while some patients experience swift recovery, others show relapsing-remitting or chronic courses. Predicting individual clinical trajectories at an early stage is a key challenge for psychiatry and might facilitate individually tailored interventions. So far, however, reliable predictors at the single-patient level are absent. Here, we evaluated the utility of a machine learning strategy – generative embedding (GE) – which combines interpretable generative models with discriminative classifiers. Specifically, we used functional magnetic resonance imaging (fMRI) data of emotional face perception in 85 MDD patients from the NEtherlands Study of Depression and Anxiety (NESDA) who had been followed up over two years and classified into three subgroups with distinct clinical trajectories. Combining a generative model of effective (directed) connectivity with support vector machines (SVMs), we could predict whether a given patient would experience chronic depression vs. fast remission with a balanced accuracy of 79%. Gradual improvement vs. fast remission could still be predicted above-chance, but less convincingly, with a balanced accuracy of 61%. Generative embedding outperformed classification based on conventional (descriptive) features, such as functional connectivity or local activation estimates, which were obtained from the same data and did not allow for above-chance classification accuracy. Furthermore, predictive performance of GE could be assigned to a specific network property: the trial-by-trial modulation of connections by emotional content. Given the limited sample size of our study, the present results are preliminary but may serve as proof-of-concept, illustrating the potential of GE for obtaining clinical predictions that are interpretable in terms of network mechanisms. Our findings suggest that abnormal dynamic changes of connections involved in emotional face processing might be associated with higher risk of developing a less favorable clinical course.
Abstract
There is currently no quantifiable method to predict long-term clinical outcomes in patients presenting with a first episode of psychosis. A major barrier to developing useful markers for ...this is biological heterogeneity, where many different pathological mechanisms may underly the same set of symptoms in different individuals. Normative modelling has been used to quantify this heterogeneity in established psychotic disorders by identifying regions of the cortex which are thinner than expected based on a normative healthy population range. These brain atypicalities are measured at the individual level and therefore potentially useful in a clinical setting. However, it is still unclear whether alterations in individual brain structure can be detected at the time of the first psychotic episode, and whether they are associated with subsequent clinical outcomes. We applied normative modelling of cortical thickness to a sample of first-episode psychosis patients, with the aim of quantifying heterogeneity and to use any pattern of cortical atypicality to predict symptoms and response to antipsychotic medication at timepoints from baseline up to 95 weeks (median follow-ups = 4). T1-weighted brain magnetic resonance images from the GAP and OPTiMiSE samples were processed with Freesurfer V6.0.0 yielding 148 cortical thickness features. An existing normative model of cortical thickness (
n
= 37,126) was adapted to integrate data from each clinical site and account for effects of gender and site. Our test sample consisted of control participants (
n
= 149, mean age = 26, SD = 6.7) and patient data (
n
= 295, mean age = 26, SD = 6.7), this sample was used for estimating deviations from the normative model and subsequent statistical analysis. For each individual, the 148 cortical thickness features were mapped to centiles of the normative distribution and converted to z-scores reflecting the distance from the population mean. Individual cortical thickness metrics of +/– 2.6 standard deviations from the mean were considered extreme deviations from the norm. We found that no more than 6.4% of psychosis patients had extreme deviations in a single brain region (regional overlap) demonstrating a high degree of heterogeneity. Mann-Whitney U tests were run on z-scores for each region and significantly lower z-scores were observed in FEP patients in the frontal, temporal, parietal and occipital lobes. Finally, linear mixed-effects modelling showed that negative deviations in cortical thickness in parietal and temporal regions at baseline are related to more severe negative symptoms over the medium-term. This study shows that even at the early stage of symptom onset normative modelling provides a framework to identify individualised cortical markers which can be used for early personalised intervention and stratification.