Evidence for embracing normative modeling

Artificial Intelligence in Obsessive-Compulsive Disorder: A Systematic Review

Purpose of Review

Obsessive-compulsive disorder (OCD) is a chronic and disabling condition, often leading to significant functional impairments. Despite its early onset, there is an average delay of 17 years from symptom onset to diagnosis and treatment, resulting in poorer outcomes. This systematic review aims to synthesize current findings on the application of AI in OCD, highlighting opportunities for early symptom detection, scalable therapy training, clinical decision support, novel therapeutics, computer vision-based approaches, and multimodal biomarker discovery.

Recent Findings

While previous reviews focused on biomarker-based OCD detection and treatment using machine learning (ML), the findings of the current review add information about novel applications of deep learning technology, specifically generative artificial intelligence (GenAI) and natural language processing (NLP). Among the included 13 articles, most studies (84.6%) utilized secondary data analyses, primarily through GenAI/NLP. Nearly 77% of these studies were published in the past two years, with high quality of evidence. The primary focus areas were enhancing treatment and management, and timely OCD detection (both 38.5%); followed by AI tool development for broader mental health applications.

Summary

AI technologies offer transformative potential for improvements related to OCD if diagnosis occurs earlier after onset; thereby lessening the consequential economic burden. Prioritizing investment in ethically sound AI research could significantly improve OCD outcomes in mental health care.

Supplementary Information

The online version contains supplementary material available at 10.1007/s40501-025-00359-8.

ComBatLS: A Location- and Scale-Preserving Method for Multi-Site Image Harmonization

Recent study has leveraged massive datasets and advanced harmonization methods to construct normative models of neuroanatomical features and benchmark individuals' morphology. However, current harmonization tools do not preserve the effects of biological covariates including sex and age on features' variances; this failure may induce error in normative scores, particularly when such factors are distributed unequally across sites. Here, we introduce a new extension of the popular ComBat harmonization method, ComBatLS, that preserves biological variance in features' locations and scales. We use UK Biobank data to show that ComBatLS robustly replicates individuals' normative scores better than other ComBat methods when subjects are assigned to sex-imbalanced synthetic "sites." Additionally, we demonstrate that ComBatLS significantly reduces sex biases in normative scores compared to traditional methods. Finally, we show that ComBatLS successfully harmonizes consortium data collected across over 50 studies. R implementation of ComBatLS is available at https://github.com/andy1764/ComBatFamily.

Delineating the Heterogeneity of Alzheimer's Disease and Mild Cognitive Impairment Using Normative Models of Dynamic Brain Functional Networks

BACKGROUND

Alzheimer's disease (AD), which has been identified as the most common type of dementia, presents considerable heterogeneity in its clinical manifestations. Early intervention at the stage of mild cognitive impairment (MCI) holds potential in AD prevention. However, characterizing the heterogeneity of neurobiological abnormalities and identifying MCI subtypes pose significant challenges.

METHODS

We constructed sex-specific normative age models of dynamic brain functional networks and mapped the deviations of the brain characteristics for individuals from multiple datasets, including 295 patients with AD, 441 patients with MCI, and 1160 normal control participants. Then, based on these individual deviation patterns, subtypes for both AD and MCI were identified using the clustering method, and their similarities and differences were comprehensively assessed.

RESULTS

Individuals with AD and MCI were clustered into 2 subtypes, and these subtypes exhibited significant differences in their intrinsic brain functional phenotypes and spatial atrophy patterns, as well as in disease progression and cognitive decline trajectories. The subtypes with positive deviations in AD and MCI shared similar deviation patterns, as did those with negative deviations. There was a potential transformation of MCI with negative deviation patterns into AD, and participants with MCI had a more severe cognitive decline rate.

CONCLUSIONS

In this study, we quantified neurophysiological heterogeneity by analyzing deviation patterns from the dynamic functional connectome normative model and identified disease subtypes of AD and MCI using a comprehensive resting-state functional magnetic resonance imaging multicenter dataset. The findings provide new insights for developing early prevention and personalized treatment strategies for AD.

A Clinical Neuroimaging Platform for Rapid, Automated Lesion Detection and Personalized Post-Stroke Outcome Prediction

Predicting long-term functional outcomes for individuals with stroke is a significant challenge. Solving this challenge will open new opportunities for improving stroke management by informing acute interventions and guiding personalized rehabilitation strategies. The location of the stroke is a key predictor of outcomes, yet no clinically deployed tools incorporate lesion location information for outcome prognostication. This study responds to this critical need by introducing a fully automated, three-stage neuroimaging processing and machine learning pipeline that predicts personalized outcomes from clinical imaging in adult ischemic stroke patients. In the first stage, our system automatically processes raw DICOM inputs, registers the brain to a standard template, and uses deep learning models to segment the stroke lesion. In the second stage, lesion location and automatically derived network features are input into statistical models trained to predict long-term impairments from a large independent cohort of lesion patients. In the third stage, a structured PDF report is generated using a large language model that describes the stroke's location, the arterial distribution, and personalized prognostic information. We demonstrate the viability of this approach in a proof-of-concept application predicting select cognitive outcomes in a stroke cohort. Brain-behavior models were pre-trained to predict chronic impairment on 28 different cognitive outcomes in a large cohort of patients with focal brain lesions (N=604). The automated pipeline used these models to predict outcomes from clinically acquired MRIs in an independent ischemic stroke cohort (N=153). Starting from raw clinical DICOM images, we show that our pipeline can generate outcome predictions for individual patients in less than 3 minutes with 96% concordance relative to methods requiring manual processing. We also show that prediction accuracy is enhanced using models that incorporate lesion location, lesion-associated network information, and demographics. Our results provide a strong proof-of-concept and lay the groundwork for developing imaging-based clinical tools for stroke outcome prognostication.

Characterizing the heterogeneity of neurodegenerative diseases through EEG normative modeling

Neurodegenerative diseases like Parkinson's (PD) and Alzheimer's (AD) exhibit considerable heterogeneity of functional brain features within patients, complicating diagnosis and treatment. Here, we use electroencephalography (EEG) and normative modeling to investigate neurophysiological mechanisms underpinning this heterogeneity. Resting-state EEG data from 14 clinical units included healthy adults (n = 499) and patients with PD (n = 237) and AD (n = 197), aged over 40. Spectral and source connectivity analyses provided features for normative modeling, revealing significant, frequency-dependent EEG deviations with high heterogeneity in PD and AD. Around 30% of patients exhibited spectral deviations, while ~80% showed functional source connectivity deviations. Notably, the spatial overlap of deviant features did not exceed 60% for spectral and 25% for connectivity analysis. Furthermore, patient-specific deviations correlated with clinical measures, with greater deviations linked to worse UPDRS for PD (⍴ = 0.24, p = 0.025) and MMSE for AD (⍴ = -0.26, p = 0.01). These results suggest that EEG deviations could enrich individualized clinical assessment in Precision Neurology.

Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational Study

BACKGROUND

Brain-related disorders are characterized by observable behavioral symptoms, for example, social withdrawal. Smartphones can passively collect behavioral data reflecting digital activities such as communication app usage and calls. These data are collected objectively in real time, avoiding recall bias, and may, therefore, be a useful tool for measuring behaviors related to social functioning. Despite promising clinical utility, analyzing smartphone data is challenging as datasets often include a range of temporal features prone to missingness.

OBJECTIVE

Hidden Markov models (HMMs) provide interpretable, lower-dimensional temporal representations of data, allowing for missingness. This study aimed to investigate the HMM as a method for modeling smartphone time series data.

METHODS

We applied an HMM to an aggregate dataset of smartphone measures designed to assess phone-related social functioning in healthy controls (HCs) and participants with schizophrenia, Alzheimer disease (AD), and memory complaints. We trained the HMM on a subset of HCs (91/348, 26.1%) and selected a model with socially active and inactive states. Then, we generated hidden state sequences per participant and calculated their "total dwell time," that is, the percentage of time spent in the socially active state. Linear regression models were used to compare the total dwell time to social and clinical measures in a subset of participants with available measures, and logistic regression was used to compare total dwell times between diagnostic groups and HCs. We primarily reported results from a 2-state HMM but also verified results in HMMs with more hidden states and trained on the whole participant dataset.

RESULTS

We identified lower total dwell times in participants with AD (26/257, 10.1%) versus withheld HCs (156/257, 60.7%; odds ratio 0.95, 95% CI 0.92-0.97; false discovery rate [FDR]-corrected P<.001), as well as in participants with memory complaints (57/257, 22.2%; odds ratio 0.97, 95% CI 0.96-0.99; FDR-corrected P=.004). The result in the AD group was very robust across HMM variations, whereas the result in the memory complaints group was less robust. We also observed an interaction between the AD group and total dwell time when predicting social functioning (FDR-corrected P=.02). No significant relationships regarding total dwell time were identified for participants with schizophrenia (18/257, 7%; P>.99).

CONCLUSIONS

We found the HMM to be a practical, interpretable method for digital phenotyping analysis, providing an objective phenotype that is a possible indicator of social functioning.

Rethinking MRI as a measurement device through modular and portable pipelines

The premise of MRI as a reliable measurement device is limited by proprietary barriers and inconsistent implementations, which prevent the establishment of measurement uncertainties. As a result, biomedical studies that rely on these methods are plagued by systematic variance, undermining the perceived promise of quantitative imaging biomarkers (QIBs) and hindering their clinical translation. This review explores the added value of open-source measurement pipelines in minimizing variability sources that would otherwise remain unknown. First, we introduce a tiered benchmarking framework (from black-box to glass-box) that exposes how opacity at different workflow stages propagates measurement uncertainty. Second, we provide a concise glossary to promote consistent terminology for strategies that enhance reproducibility before acquisition or enable valid post-hoc pooling of QIBs. Building on this foundation, we present two illustrative measurement workflows that decouple workflow logic from the orchestration of computational processes in an MRI measurement pipeline, rooted in the core principles of modularity and portability. Designed as accessible entry points for implementation, these examples serve as practical guides, helping users adapt the frameworks to their specific needs and facilitating collaboration. Through critical evaluation of existing approaches, we discuss how standardized workflows can help identify outstanding challenges in translating glass-box frameworks into clinical scanner environments. Ultimately, achieving this goal will require coordinated efforts from QIB developers, regulators, industry partners, and clinicians alike.

Heterogeneity of morphometric similarity networks in health and schizophrenia

Reduced structural network connectivity is proposed as a biomarker for chronic schizophrenia. This study assessed regional morphometric similarity as an indicator of cortical inter-regional connectivity, employing longitudinal normative modeling to evaluate whether decreases are consistent across individuals with schizophrenia. Normative models were trained and validated using data from healthy controls (n = 4310). Individual deviations from these norms were measured at baseline and follow-up, and categorized as infra-normal, normal, or supra-normal. Additionally, we assessed the change over time in the total number of infra- or supra-normal regions for each individual. At baseline, patients exhibited reduced morphometric similarity within the default mode network compared to healthy controls. The proportion of patients with infra- or supra-normal values in any region at both baseline and follow-up was low (<6%) and similar to that of healthy controls. Mean intra-group changes in the number of infra- or supra-normal regions over time were minimal (<1) for both the schizophrenia and control groups, with no significant differences observed between them. Normative modeling with multiple timepoints enables the identification of patients with significant static decreases and dynamic changes of morphometric similarity over time and provides further insight into the pervasiveness of morphometric similarity abnormalities across individuals with chronic schizophrenia.

Estimating Brain Similarity Networks with Diffusion MRI

Structural similarity has emerged as a promising tool in mapping the network organization of an individual, living human brain. Here, we propose diffusion similarity networks (DSNs), which employ rotationally invariant spherical harmonic features derived from diffusion magnetic resonance imaging (dMRI), to map gray matter structural organization. Compared to prior approaches, DSNs showed clearer laminar, cytoarchitectural, and micro-architectural organization; greater sensitivity to age, cognition, and sex; higher heritability in a large dataset of healthy young adults; and straightforward extension to non-cortical regions. We show DSNs are correlated with functional, structural, and gene expression connectomes and their gradients align with the sensory-fugal and sensorimotor-association axes of the cerebral cortex, including neuronal oscillatory dynamics, metabolism, immunity, and dopaminergic and glutaminergic receptor densities. DSNs can be easily integrated into conventional dMRI analysis, adding information complementary to structural white matter connectivity, and could prove useful in investigating a wide array of neurological and psychiatric conditions.

Normative Modeling Reveals Age-Atypical Cortical Thickness Differences Between Hepatic Steatosis and Fibrosis in Non-Alcoholic Fatty Liver Disease

OBJECTIVES

To investigate individual variations and outliers in cortical thickness among non-alcoholic fatty liver disease (NAFLD) patients, ranging from hepatic steatosis to fibrosis, using neuroanatomical normative modeling.

MATERIALS AND METHODS

A cross-sectional study with 2637 health check-up subjects was conducted. Among NAFLD patients, hepatic steatosis (n = 556) and fibrosis (n = 57) were determined by hepatic steatosis index and fibrosis-4 score, respectively. Cortical thickness in 148 different brain regions was assessed using T1-weighted MRI scans. A publicly available neuroanatomical normative model analyzed cortical thickness distributions with data from around 58,000 participants. The hierarchical Bayesian regression was used to estimate cortical thickness deviation for each region, taking age, sex, and sites into account. On the basis of a normal adaptation set, Z-scores below -1.96 or above +1.96 per region were classified as outliers. The total outlier count (tOC) was then calculated to quantify regional heterogeneity. Mass univariate analysis was conducted to compare steatosis and fibrosis groups, and the spatial patterns of regional heterogeneity were qualitatively analyzed.

RESULTS

Patients with hepatic fibrosis had a higher number of positive outlier regions (mean 6.3 ± 10.3) than hepatic steatosis (mean 4.2 ± 6.2, p = 0.02). Mass univariate group difference testing of 148 brain regions revealed patients with hepatic fibrosis had 6 cortical areas thicker than hepatic steatosis. Two groups showed shared regional heterogeneity in the temporal cortex.

CONCLUSION

Distinct brain atrophy patterns were observed in NAFLD patients compared to the normal group, with more frequent temporal cortex outliers in both hepatic steatosis and fibrosis. Hepatic fibrosis showed slightly increased cortical thickness relative to steatosis.

Human lifespan changes in the brain's functional connectome

Functional connectivity of the human brain changes through life. Here, we assemble task-free functional and structural magnetic resonance imaging data from 33,250 individuals at 32 weeks of postmenstrual age to 80 years from 132 global sites. We report critical inflection points in the nonlinear growth curves of the global mean and variance of the connectome, peaking in the late fourth and late third decades of life, respectively. After constructing a fine-grained, lifespan-wide suite of system-level brain atlases, we show distinct maturation timelines for functional segregation within different systems. Lifespan growth of regional connectivity is organized along a spatiotemporal cortical axis, transitioning from primary sensorimotor regions to higher-order association regions. These findings elucidate the lifespan evolution of the functional connectome and can serve as a normative reference for quantifying individual variation in development, aging and neuropsychiatric disorders.

Mapping ADHD Heterogeneity and Biotypes through Topological Deviations in Morphometric Similarity Networks

Attention-deficit/hyperactivity disorder (ADHD) is characterized by considerable clinical heterogeneity. This study investigates whether normative modelling of topological properties derived from brain morphometry similarity networks can provide robust stratification markers for ADHD children. Leveraging multisite neurodevelopmental datasets (discovery: 446 ADHD, 708 controls; validation: 554 ADHD, 123 controls), we constructed morphometric similarity networks and developed normative models for three topological metrics: degree centrality, nodal efficiency, and participation coefficient. Through semi-supervised clustering, we delineated putative biotypes and examined their clinical profiles. We further contextualized brain profiles of these biotypes in terms of their neurochemical and functional correlates using large-scale databases, and assessed model generalizability in an independent cohort. ADHD exhibited atypical hub organization across all three topological metrics, with significant case-control differences primarily localized to a covarying multi-metric component in the orbitofrontal cortex. Three biotypes emerged: one characterized by severe overall symptoms and longitudinally persistent emotional dysregulation, accompanied by pronounced topological alterations in the medial prefrontal cortex and pallidum; a second by predominant hyperactivity/impulsivity accompanied by changes in the anterior cingulate cortex and pallidum; and a third by marked inattention with alterations in the superior frontal gyrus. These neural profiles of each biotype showed distinct neurochemical and functional correlates. Critically, the core findings were replicated in an independent validation cohort. Our comprehensive approach reveals three distinct ADHD biotypes with unique clinical-neural patterns, advancing our understanding of ADHD's neurobiological heterogeneity and laying the groundwork for personalized treatment.

A generalizable normative deep autoencoder for brain morphological anomaly detection: application to the multi-site StratiBip dataset on bipolar disorder in an external validation framework

The heterogeneity of psychiatric disorders makes researching disorder-specific neurobiological markers an ill-posed problem. Here, we face the need for disease stratification models by presenting a generalizable multivariate normative modelling framework for characterizing brain morphology, applied to bipolar disorder (BD). We used deep autoencoders in an anomaly detection framework, combined for the first time with a confounder removal step that integrates training and external validation. The model was trained with healthy control (HC) data from the human connectome project and applied to multi-site external data of HC and BD individuals. We found that brain deviating scores were greater, more heterogeneous, and with increased extreme values in the BD group, with volumes prominently from the basal ganglia, hippocampus, and adjacent regions emerging as significantly deviating. Similarly, individual brain deviating maps based on modified z scores expressed higher abnormalities occurrences, but their overall spatial overlap was lower compared to HCs. Our generalizable framework enabled the identification of brain deviating patterns differing between the subject and the group levels, a step forward towards the development of more effective and personalized clinical decision support systems and patient stratification in psychiatry.

Multifactorial influences on childhood insomnia: Genetic, socioeconomic, brain development and psychopathology insights

Insomnia is the most prevalent sleep disturbance during childhood and can result in extensively detrimental effects. Children's insomnia involves a complex interplay of biological, neurodevelopmental, social-environmental, and behavioral variables, yet remains insufficiently addressed. This study aimed to investigate the multifactorial etiology of childhood insomnia from its genetic architecture and social-environmental variables to its neural instantiation and the relationship to mental health. This cohort study uses 4340 participants at baseline and 2717 participants at 2-year follow-up from the Adolescent Brain Cognitive Development (ABCD) Study. We assessed the joint effects of polygenic risk score (PRS) and socioeconomic status (SES) on insomnia symptoms and then investigated the underlying neurodevelopmental mechanisms. Structural equation model (SEM) was applied to investigate the directional relationships among these variables. SES and PRS affected children's insomnia symptoms independently and additively (SES: β = -0.089, P = 1.91 × 10-8; PRS: β = 0.041, P = 0.008), which was further indirectly mediated by the deviation of inferior precentral sulcus (β = 0.0027, P = 0.0071). SEM revealed that insomnia (β = 0.457, P < 0.001) and precentral development (β = -0.039, P = 0.009) significantly mediated the effect of SES_PRS (accumulated risks of PRS and SES) on psychopathology symptoms. Furthermore, baseline insomnia symptoms, SES_PRS, and precentral deviation significantly predicted individual total psychopathology syndromes (r = 0.346, P < 0.001). These findings suggest the additive effects of genetic and socioenvironmental factors on childhood insomnia via precentral development and highlight potential targets in early detection and intervention for childhood insomnia.

Neurofind: using deep learning to make individualised inferences in brain-based disorders

Within precision psychiatry, there is a growing interest in normative models given their ability to parse heterogeneity. While they are intuitive and informative, the technical expertise and resources required to develop normative models may not be accessible to most researchers. Here we present Neurofind, a new freely available tool that bridges this gap by wrapping sound and previously tested methods on data harmonisation and advanced normative models into a web-based platform that requires minimal input from the user. We explain how Neurofind was developed, how to use the Neurofind website in four simple steps ( www.neurofind.ai ), and provide exemplar applications. Neurofind takes as input structural MRI images and outputs two main metrics derived from independent normative models: (1) Outlier Index Score, a deviation score from the normative brain morphology, and (2) Brain Age, the predicted age based on an individual's brain morphometry. The tool was trained on 3362 images of healthy controls aged 20-80 from publicly available datasets. The volume of 101 cortical and subcortical regions was extracted and modelled with an adversarial autoencoder for the Outlier index model and a support vector regression for the Brain age model. To illustrate potential applications, we applied Neurofind to 364 images from three independent datasets of patients diagnosed with Alzheimer's disease and schizophrenia. In Alzheimer's disease, 55.2% of patients had very extreme Outlier Index Scores, mostly driven by larger deviations in temporal-limbic structures and ventricles. Patients were also homogeneous in how they deviated from the norm. Conversely, only 30.1% of schizophrenia patients were extreme outliers, due to deviations in the hippocampus and pallidum, and patients tended to be more heterogeneous than controls. Both groups showed signs of accelerated brain ageing.

Judged by your neighbors: Brain structural normativity profiles for large and heterogeneous samples

The detection of norm deviations is fundamental to clinical decision making and impacts our ability to diagnose and treat diseases effectively. Current normative modeling approaches rely on generic comparisons and quantify deviations in relation to the population average. However, generic models interpolate subtle nuances and risk the loss of critical information, thereby compromising effective personalization of health care strategies. To acknowledge the substantial heterogeneity among patients and support the paradigm shift of precision medicine, we introduce Nearest Neighbor Normativity (N3), which is a strategy to refine normativity evaluations in diverse and heterogeneous clinical study populations. We address current methodological shortcomings by accommodating several equally normative population prototypes, comparing individuals from multiple perspectives and designing specifically tailored control groups. Applied to brain structure in 36,896 individuals, the N3 framework provides empirical evidence for its utility and significantly outperforms traditional methods in the detection of pathological alterations. Our results underscore N3's potential for individual assessments in medical practice, where norm deviations are not merely a benchmark, but an important metric supporting the realization of personalized patient care.

Normative Cerebral Perfusion Across the Lifespan

Cerebral perfusion plays a crucial role in maintaining brain function and is tightly coupled with neuronal activity. While previous studies have examined cerebral perfusion trajectories across development and aging, precise characterization of its lifespan dynamics has been limited by small sample sizes and methodological inconsistencies. In this study, we construct the first comprehensive normative model of cerebral perfusion across the human lifespan (birth to 85 years) using a large multi-site dataset of over 12,000 high-quality arterial spin labeling (ASL) MRI scans. Leveraging generalized additive models for location, scale, and shape (GAMLSS), we mapped nonlinear growth trajectories of cerebral perfusion at global, network, and regional levels. We observed a rapid postnatal increase in cerebral perfusion, peaking at approximately 7.1 years, followed by a gradual decline into adulthood. Sex differences were evident, with distinct regional maturation patterns rather than uniform differences across all brain regions. Beyond normative modeling, we quantified individual deviations from expected CBF patterns in neurodegenerative and psychiatric conditions, identifying disease-specific perfusion abnormalities across four brain disorders. Using longitudinal data, we established typical and atypical cerebral perfusion trajectories, highlighting the prognostic value of perfusion-based biomarkers for detecting disease progression. Our findings provide a robust normative framework for cerebral perfusion, facilitating precise characterization of brain health across the lifespan and enhancing the early identification of neurovascular dysfunction in clinical populations.

Applications of MRI in Schizophrenia: Current Progress in Establishing Clinical Utility

Schizophrenia is a severe mental illness that significantly impacts the lives of affected individuals and with increasing mortality rates. Early detection and intervention are crucial for improving outcomes but the lack of validated biomarkers poses great challenges in such efforts. The use of magnetic resonance imaging (MRI) in schizophrenia enables the investigation of the disorder's etiological and neuropathological substrates in vivo. After decades of research, promising findings of MRI have been shown to aid in screening high-risk individuals and predicting illness onset, and predicting symptoms and treatment outcomes of schizophrenia. The integration of machine learning and deep learning techniques makes it possible to develop intelligent diagnostic and prognostic tools with extracted or selected imaging features. In this review, we aimed to provide an overview of current progress and prospects in establishing clinical utility of MRI in schizophrenia. We first provided an overview of MRI findings of brain abnormalities that might underpin the symptoms or treatment response process in schizophrenia patients. Then, we summarized the ongoing efforts in the computer-aided utility of MRI in schizophrenia and discussed the gap between MRI research findings and real-world applications. Finally, promising pathways to promote clinical translation were provided. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 3.

Spectral normative modeling of brain structure

Normative modeling in neuroscience aims to characterize interindividual variation in brain phenotypes and thus establish reference ranges, or brain charts, against which individual brains can be compared. Normative models are typically limited to coarse spatial scales due to computational constraints, limiting their spatial specificity. They additionally depend on fixed regions from fixed parcellation atlases, restricting their adaptability to alternative parcellation schemes. To overcome these key limitations, we propose spectral normative modeling (SNM), which leverages brain eigenmodes for efficient spatial reconstruction to generate normative ranges for arbitrary new regions of interest. Benchmarking against conventional counterparts, SNM achieves a 98.3% speedup in computing accurate normative ranges across spatial scales, from millimeters to the whole brain. We demonstrate its utility by elucidating high-resolution individual cortical atrophy patterns and characterizing the heterogeneous nature of neurodegeneration in Alzheimer's disease. SNM lays the groundwork for a new generation of spatially precise brain charts, offering substantial potential to drive advances in individualized precision medicine.

A multimodal neural signature of face processing in autism within the fusiform gyrus

Atypical face processing is commonly reported in autism. Its neural correlates have been explored extensively across single neuroimaging modalities within key regions of the face processing network, such as the fusiform gyrus (FFG). Nonetheless, it is poorly understood how variation in brain anatomy and function jointly impacts face processing and social functioning. Here we leveraged a large multimodal sample to study the cross-modal signature of face processing within the FFG across four imaging modalities (structural magnetic resonance imaging (MRI), resting-state functional magnetic resonance imaging, task-functional magnetic resonance imaging and electroencephalography) in 204 autistic and nonautistic individuals aged 7-30 years (case-control design). We combined two methodological innovations-normative modeling and linked independent component analysis-to integrate individual-level deviations across modalities and assessed how multimodal components differentiated groups and informed social functioning in autism. Groups differed significantly in a multimodal component driven by bilateral resting-state functional MRI, bilateral structure, right task-functional MRI and left electroencephalography loadings in face-selective and retinotopic FFG. Multimodal components outperformed unimodal ones in differentiating groups. In autistic individuals, multimodal components were associated with cognitive and clinical features linked to social, but not nonsocial, functioning. These findings underscore the importance of elucidating multimodal neural associations of social functioning in autism, offering potential for the identification of mechanistic and prognostic biomarkers.

Predicting Antidepressant Treatment Response From Cortical Structure on MRI: A Mega-Analysis From the ENIGMA-MDD Working Group

Accurately predicting individual antidepressant treatment response could expedite the lengthy trial-and-error process of finding an effective treatment for major depressive disorder (MDD). We tested and compared machine learning-based methods that predict individual-level pharmacotherapeutic treatment response using cortical morphometry from multisite longitudinal cohorts. We conducted an international analysis of pooled data from six sites of the ENIGMA-MDD consortium (n = 262 MDD patients; age = 36.5 ± 15.3 years; 154 (59%) female; mean response rate = 57%). Treatment response was defined as a ≥ 50% reduction in symptom severity score after 4-12 weeks post-initiation of antidepressant treatment. Structural MRI was acquired before, or < 14 days after, treatment initiation. The cortex was parcellated using FreeSurfer, from which cortical thickness and surface area were measured. We tested several machine learning pipeline configurations, which varied in (i) the way we presented the cortical data (i.e., average values per region of interest, as a vector containing voxel-wise cortical thickness and surface area measures, and as cortical thickness and surface area projections), (ii) whether we included clinical data, and the (iii) machine learning model (i.e., gradient boosting, support vector machine, and neural network classifiers) and (iv) cross-validation methods (i.e., k-fold and leave-one-site-out) we used. First, we tested if the overall predictive performance of the pipelines was better than chance, with a corrected 10-fold cross-validation permutation test. Second, we compared if some machine learning pipeline configurations outperformed others. In an exploratory analysis, we repeated our first analysis in three subpopulations, namely patients (i) from a single site, (ii) with comparable response rates, and (iii) showing the least (first quartile) and the most (fourth quartile) treatment response, which we call the extreme (non-)responders subpopulation. Finally, we explored the effect of including subcortical volumetric data on model performance. Overall, performance predicting antidepressant treatment response was not significantly better than chance (balanced accuracy = 50.5%; p = 0.66) and did not vary with alternative pipeline configurations. Exploratory analyses revealed that performance across models was only significantly better than chance in the extreme (non-)responders subpopulation (balanced accuracy = 63.9%, p = 0.001). Including subcortical data did not alter the observed model performance. Cortical structural MRI alone could not reliably predict individual pharmacotherapeutic treatment response in MDD. None of the used machine learning pipeline configurations outperformed the others. In exploratory analyses, we found that predicting response in the extreme (non-)responders subpopulation was feasible on both cortical data alone and combined with subcortical data, which suggests that specific MDD subpopulations may exhibit response-related patterns in structural data. Future work may use multimodal data to predict treatment response in MDD.

A 10-Year Longitudinal Study of Brain Cortical Thickness in People with First-Episode Psychosis Using Normative Models

BACKGROUND

Clinical forecasting models have potential to optimize treatment and improve outcomes in psychosis, but predicting long-term outcomes is challenging and long-term follow-up data are scarce. In this 10-year longitudinal study, we aimed to characterize the temporal evolution of cortical correlates of psychosis and their associations with symptoms.

DESIGN

Structural magnetic resonance imaging (MRI) from people with first-episode psychosis and controls (n = 79 and 218) were obtained at enrollment, after 12 months (n = 67 and 197), and 10 years (n = 23 and 77), within the Thematically Organized Psychosis (TOP) study. Normative models for cortical thickness estimated on public MRI datasets (n = 42 983) were applied to TOP data to obtain deviation scores for each region and timepoint. Positive and Negative Syndrome Scale (PANSS) scores were acquired at each timepoint along with registry data. Linear mixed effects models assessed effects of diagnosis, time, and their interactions on cortical deviations plus associations with symptoms.

RESULTS

LMEs revealed conditional main effects of diagnosis and time × diagnosis interactions in a distributed cortical network, where negative deviations in patients attenuate over time. In patients, symptoms also attenuate over time. LMEs revealed effects of anterior cingulate on PANSS total, and insular and orbitofrontal regions on PANSS negative scores.

CONCLUSIONS

This long-term longitudinal study revealed a distributed pattern of cortical differences which attenuated over time together with a reduction in symptoms. These findings are not in line with a simple neurodegenerative account of schizophrenia, and deviations from normative models offer a promising avenue to develop biomarkers to track clinical trajectories over time.

Lifespan Normative Models of White Matter Fractional Anisotropy: Applications to Early Psychosis

This study presents large-scale normative models of white matter (WM) organization across the lifespan, using diffusion MRI data from over 25,000 healthy individuals aged 0-100 years. These models capture lifespan trajectories and inter-individual variation in fractional anisotropy (FA), a marker of white matter integrity. By addressing non-Gaussian data distributions, race, and site effects, the models offer reference baselines across diverse ages, ethnicities, and scanning conditions. We applied these FA models to the HCP Early Psychosis cohort and performed a multivariate analysis to map symptoms onto deviations from multimodal normative models using multi-view sparse canonical correlation analysis (msCCA). Our results reveal extensive white matter heterogeneity in psychosis, which is not captured by group-level analyses, with key regions identified, including the right uncinate fasciculus and thalami. These normative models offer valuable tools for individualized WM deviation identification, improving precision in psychiatric assessments. All models are publicly available for community use.

Predicting an individual's functional connectivity from their structural connectome: Evaluation of evidence, recommendations, and future prospects

Several recent studies have optimized deep neural networks to learn high-dimensional relationships linking structural and functional connectivity across the human connectome. However, the extent to which these models recapitulate individual-specific characteristics of resting-state functional brain networks remains unclear. A core concern relates to whether current individual predictions outperform simple benchmarks such as group averages and null conditions. Here, we consider two measures to statistically evaluate whether functional connectivity predictions capture individual effects. We revisit our previously published functional connectivity predictions for 1,000 healthy adults and provide multiple lines of evidence supporting that our predictions successfully capture subtle individual-specific variation in connectivity. While predicted individual effects are statistically significant and outperform several benchmarks, we find that effect sizes are small (i.e., 8%-11% improvement relative to group-average benchmarks). As such, initial expectations about individual prediction performance expressed by us and others may require moderation. We conclude that individual predictions can significantly outperform appropriate benchmark conditions and we provide several recommendations for future studies in this area. Future studies should statistically assess the individual prediction performance of their models using one of the measures and benchmarks provided here.

Normative modeling of brain MRI data identifies small subcortical volumes and associations with cognitive function in youth with fetal alcohol spectrum disorder (FASD)

AIM

To quantify regional subcortical brain volume anomalies in youth with fetal alcohol spectrum disorder (FASD), assess the relative sensitivity and specificity of abnormal volumes in FASD vs. a comparison group, and examine associations with cognitive function.

METHOD

Participants: 47 children with FASD and 39 typically-developing comparison participants, ages 8-17 years, who completed physical evaluations, cognitive and behavioral testing, and an MRI brain scan. A large normative MRI dataset that controlled for sex, age, and intracranial volume was used to quantify the developmental status of 7 bilateral subcortical regional volumes. Z-scores were calculated based on volumetric differences from the normative sample. T-tests compared subcortical volumes across groups. Percentages of atypical volumes are reported as are sensitivity and specificity in discriminating groups. Lastly, Pearson correlations examined the relationships between subcortical volumes and neurocognitive performance.

RESULTS

Participants with FASD demonstrated lower mean volumes across a majority of subcortical regions relative to the comparison group with prominent group differences in the bilateral hippocampi and bilateral caudate. More individuals with FASD (89%) had one or more abnormally small volume compared to 72% of the comparison group. The bilateral hippocampi, bilateral putamen, and right pallidum were most sensitive in discriminating those with FASD from the comparison group. Exploratory analyses revealed associations between subcortical volumes and cognitive functioning that differed across groups.

CONCLUSION

In this sample, youth with FASD had a greater number of atypically small subcortical volumes than individuals without FASD. Findings suggest MRI may have utility in identifying individuals with structural brain anomalies resulting from PAE.

Modulation of RNA processing genes during sleep-dependent memory

Memory consolidation in Drosophila can be sleep-dependent or sleep-independent, depending on the availability of food. The anterior posterior (ap) alpha'/beta' (α'/β') neurons of the mushroom body (MB) are required for sleep-dependent memory consolidation in flies fed after training. These neurons are also involved in the increase of sleep after training, suggesting a coupling of sleep and memory. To better understand the mechanisms underlying sleep and memory consolidation initiation, we analyzed the transcriptome of ap α'/β' neurons 1 hr after appetitive memory conditioning. A small number of genes, enriched in RNA processing functions, were differentially expressed in flies fed after training relative to trained and starved flies or untrained flies. Knockdown of each of these differentially expressed genes in the ap α'/β' neurons revealed notable sleep phenotypes for Polr1F and Regnase-1, both of which decrease in expression after conditioning. Knockdown of Polr1F, a regulator of ribosome RNA transcription, in adult flies promotes sleep and increases pre-ribosome RNA expression as well as overall translation, supporting a function for Polr1F downregulation in sleep-dependent memory. Conversely, while constitutive knockdown of Regnase-1, an mRNA decay protein localized to the ribosome, reduces sleep, adult specific knockdown suggests that effects of Regnase-1 on sleep are developmental in nature. We further tested the role of each gene in memory consolidation. Knockdown of Polr1F does not affect memory, which may be expected from its downregulation during memory consolidation. Regnase-1 knockdown in ap α'/β' neurons impairs all memory, including short-term, implicating Regnase-1 in memory, but leaving open the question of why it is downregulated during sleep-dependent memory. Overall, our findings demonstrate that the expression of RNA processing genes is modulated during sleep-dependent memory and, in the case of Polr1F, this modulation likely contributes to increased sleep.

Applying normative atlases in deep brain stimulation: a comprehensive review

Deep brain stimulation (DBS) has emerged as a crucial therapeutic strategy for various neurological and psychiatric disorders. Precise target localization is essential for optimizing therapeutic outcomes, necessitating advanced neuroimaging techniques. Normative atlases provide standardized references for accurate electrode placement, enhancing treatment customization and efficacy. This comprehensive review explores the application of normative atlases in DBS, emphasizing their role in target identification, patient-specific electrode placement, and predicting stimulation outcomes. Challenges, such as variability across atlases and technical complexities, are addressed alongside future directions and innovations, including advancements in neuroimaging technologies and the integration of machine learning (ML) and artificial intelligence (AI). Normative atlases play a pivotal role in enhancing DBS precision and patient outcomes, promising a future of personalized and effective therapies in neurology and psychiatry.

MuscleMap: An Open-Source, Community-Supported Consortium for Whole-Body Quantitative MRI of Muscle

Disorders affecting the neurological and musculoskeletal systems represent international health priorities. A significant impediment to progress in trials of new therapies is the absence of responsive, objective, and valid outcome measures sensitive to early disease changes. A key finding in individuals with neuromuscular and musculoskeletal disorders is the compositional changes to muscles, evinced by the expression of fatty infiltrates. Quantification of skeletal muscle composition by MRI has emerged as a sensitive marker for the severity of these disorders; however, little is known about the composition of healthy muscles across the lifespan. Knowledge of what is 'typical' age-related muscle composition is essential to accurately identify and evaluate what is 'atypical'. This innovative project, known as the MuscleMap, will achieve the first important steps towards establishing a world-first, normative reference MRI dataset of skeletal muscle composition with the potential to provide valuable insights into various diseases and disorders, ultimately improving patient care and advancing research in the field.

Personalizing progressive changes to brain structure in Alzheimer's disease using normative modeling

INTRODUCTION

Neuroanatomical normative modeling captures individual variability in Alzheimer's disease (AD). Here we used normative modeling to track individuals' disease progression in people with mild cognitive impairment (MCI) and patients with AD.

METHODS

Cortical and subcortical normative models were generated using healthy controls (n ≈ 58k). These models were used to calculate regional z scores in 3233 T1-weighted magnetic resonance imaging time-series scans from 1181 participants. Regions with z scores < -1.96 were classified as outliers mapped on the brain and summarized by total outlier count (tOC).

RESULTS

tOC increased in AD and in people with MCI who converted to AD and also correlated with multiple non-imaging markers. Moreover, a higher annual rate of change in tOC increased the risk of progression from MCI to AD. Brain outlier maps identified the hippocampus as having the highest rate of change.

DISCUSSION

Individual patients' atrophy rates can be tracked by using regional outlier maps and tOC.

HIGHLIGHTS

Neuroanatomical normative modeling was applied to serial Alzheimer's disease (AD) magnetic resonance imaging (MRI) data for the first time. Deviation from the norm (outliers) of cortical thickness or brain volume was computed in 3233 scans. The number of brain-structure outliers increased over time in people with AD. Patterns of change in outliers varied markedly between individual patients with AD. People with mild cognitive impairment whose outliers increased over time had a higher risk of progression from AD.

COVID-19 lockdown effects on adolescent brain structure suggest accelerated maturation that is more pronounced in females than in males

Adolescence is a period of substantial social-emotional development, accompanied by dramatic changes to brain structure and function. Social isolation due to lockdowns that were imposed because of the COVID-19 pandemic had a detrimental impact on adolescent mental health, with the mental health of females more affected than males. We assessed the impact of the COVID-19 pandemic lockdowns on adolescent brain structure with a focus on sex differences. We collected MRI structural data longitudinally from adolescents prior to and after the pandemic lockdowns. The pre-COVID data were used to create a normative model of cortical thickness change with age during typical adolescent development. Cortical thickness values in the post-COVID data were compared to this normative model. The analysis revealed accelerated cortical thinning in the post-COVID brain, which was more widespread throughout the brain and greater in magnitude in females than in males. When measured in terms of equivalent years of development, the mean acceleration was found to be 4.2 y in females and 1.4 y in males. Accelerated brain maturation as a result of chronic stress or adversity during development has been well documented. These findings suggest that the lifestyle disruptions associated with the COVID-19 pandemic lockdowns caused changes in brain biology and had a more severe impact on the female than the male brain.

Brain topology underlying executive functions across the lifespan: focus on the default mode network

Introduction

While traditional neuroimaging approaches to the study of executive functions (EFs) have typically employed task-evoked paradigms, resting state studies are gaining popularity as a tool for investigating inter-individual variability in the functional connectome and its relationship to cognitive performance outside of the scanner.

Method

Using resting state functional magnetic resonance imaging data from the Human Connectome Project Lifespan database, the present study capitalized on graph theory to chart cross-sectional variations in the intrinsic functional organization of the frontoparietal (FPN) and the default mode (DMN) networks in 500 healthy individuals (from 10 to 100 years of age), to investigate the neural underpinnings of EFs across the lifespan.

Results

Topological properties of both the FPN and DMN were associated with EF performance but not with a control task of picture naming, providing specificity in support for a tight link between neuro-functional and cognitive-behavioral efficiency within the EF domain. The topological organization of the DMN, however, appeared more sensitive to age-related changes relative to that of the FPN.

Discussion

The DMN matures earlier in life than the FPN and it ıs more susceptible to neurodegenerative changes. Because its activity is stronger in conditions of resting state, the DMN might be easier to measure in noncompliant populations and in those at the extremes of the life-span curve, namely very young or elder participants. Here, we argue that the study of its functional architecture in relation to higher order cognition across the lifespan might, thus, be of greater interest compared with what has been traditionally thought.

Multivariate brain-cognition associations in euthymic bipolar disorder

BACKGROUND

People with bipolar disorder (BD) tend to show widespread cognitive impairment compared to healthy controls. Impairments in processing speed (PS), attention and executive function (EF) may represent 'core' impairments that have a role in wider cognitive dysfunction. Cognitive impairments appear to relate to structural brain abnormalities in BD, but whether core deficits are related to particular brain regions is unclear and much of the research on brain-cognition associations is limited by univariate analysis and small samples.

METHODS

Euthymic BD patients (n = 56) and matched healthy controls (n = 26) underwent T1-weighted MRI scans and completed neuropsychological tests of PS, attention and EF. We utilised public datasets to develop normative models of cortical thickness (n = 5977) to generate robust estimations of cortical abnormalities in patients. Canonical correlation analysis was used to assess multivariate brain-cognition associations in BD, controlling for age, sex and premorbid IQ.

RESULTS

BD showed impairments on tests of PS, attention and EF, and abnormal cortical thickness in several brain regions compared to healthy controls. Impairments in tests of PS and EF were most strongly associated with cortical thickness in the left inferior temporal, right entorhinal and right temporal pole areas.

CONCLUSION

Impairments in PS, attention and EF can be observed in euthymic BD and may be related to abnormal cortical thickness in temporal regions. Future research should continue to leverage normative modelling and multivariate methods to examine complex brain-cognition associations in BD. Future research may benefit from exploring covariance between traditional brain structural morphological metrics such as cortical thickness, cortical volume and surface area.

Dissecting Heterogeneity in Functional Network Connectivity Aberrations in Antipsychotic Medication-Naïve First Episode Psychosis Patients - A Normative Modeling Study

Importance

While there is a general consensus that functional connectome pathology is a key mechanism underlying psychosis spectrum disorders, the literature is plagued with inconsistencies and translation into clinical practice is non-existent. This is perhaps because group-level findings may not be accurate reflections of pathology at the individual patient level.

Objective

To characterize inter-individual heterogeneity in functional networks and investigate if normative values can be leveraged to identify biologically less heterogeneous subgroups of patients.

Design Setting and Participants

We used data collected in a case-control study conducted at the University of Alabama at Birmingham (UAB). We recruited antipsychotic medication-naïve first-episode psychosis patients from UAB outpatient, inpatient, and emergency room settings.

Main Outcomes and Measures

Individual-level patterns of deviations from a normative reference range in resting-state functional networks using the Yeo-17 atlas for parcellations.

Results

Statistical analyses included 108 medication-naïve first-episode psychosis patients. We found that there is a high level of inter-individual heterogeneity in resting-state network connectivity deviations from the normative reference range. Interestingly 48% of patients did not have any functional connectivity deviations, and no more than 11.1% of patients shared functional deviations between the same regions of interest. In a post hoc analysis, we grouped patients based on deviations into four theoretically possible groups. We discovered that all four groups do exist in our experimental data and showed that subgroups based on deviation profiles were significantly less heterogeneous compared to the overall group (positive deviation group: z= -2.88, p = 0.002; negative deviation group: z= -3.36, p<0.001).

Conclusions and Relevance

Our findings experimentally demonstrate that there is a high level of inter-individual heterogeneity in resting-state network pathology in first-episode psychosis patients which support the idea that group-level findings are not accurate reflections of pathology at the individual level. We also demonstrated that normative functional connectivity deviations may have utility for identifying biologically less heterogeneous subgroups of patients, even though they are not distinguishable clinically. Our findings constitute a significant step towards making precision psychiatry a reality, where patients are selected for treatments based on their individual biological characteristics.

KEY POINTS

Question: How heterogeneous is individual-level resting-state functional network pathology in patients suffering from a first psychotic episode? Can normative reference values in functional network connectivity be leveraged to identify biologically more homogenous subgroups of patients?Findings: We report that functional network pathology is highly heterogeneous, with no more than 11% of patients sharing functional deviations between the same regions of interest.Meaning: Normative modeling is a tool that can map individual neurobiological differences and enables the classification of a clinically heterogenous patient group into subgroups that are neurobiologically less heterogenous.

Normative Modeling of Thalamic Nuclear Volumes and Characterization of Lateralized Volume Alterations in Alzheimer's Disease Versus Schizophrenia

BACKGROUND

Thalamic nuclei facilitate a wide range of complex behaviors, emotions, and cognition and have been implicated in neuropsychiatric disorders including Alzheimer's disease (AD) and schizophrenia (SCZ). The aim of this work was to establish novel normative models of thalamic nuclear volumes and their laterality indices and investigate their changes in SCZ and AD.

METHODS

Volumes of bilateral whole thalami and 10 thalamic nuclei were generated from T1 magnetic resonance imaging data using a state-of-the-art novel segmentation method in healthy control participants (n = 2374) and participants with early mild cognitive impairment (n = 211), late mild cognitive impairment (n = 113), AD (n = 88), and SCZ (n = 168). Normative models for each nucleus were generated from healthy control participants while controlling for sex, intracranial volume, and site. Extreme z-score deviations (|z| > 1.96) and z-score distributions were compared across phenotypes. z Scores were associated with clinical descriptors.

RESULTS

Increased infranormal and decreased supranormal z scores were observed in SCZ and AD. z Score shifts representing reduced volumes were observed in most nuclei in SCZ and AD, with strong overlap in the bilateral pulvinar, medial dorsal, and centromedian nuclei. Shifts were larger in AD, with evidence of a left-sided preference in early mild cognitive impairment while a predilection for right thalamic nuclei was observed in SCZ. The right medial dorsal nucleus was associated with disorganized thought and daily auditory verbal hallucinations.

CONCLUSIONS

In AD, thalamic nuclei are more severely and symmetrically affected, while in SCZ, the right thalamic nuclei are more affected. We highlight the right medial dorsal nucleus, which may mediate multiple symptoms of SCZ and is affected early in the disease course.

Identifying epileptogenic abnormality by decomposing intracranial EEG and MEG power spectra

BACKGROUND

Accurate identification of abnormal electroencephalographic (EEG) activity is pivotal for diagnosing and treating epilepsy. Recent studies indicate that decomposing brain activity into periodic (oscillatory) and aperiodic (trend across all frequencies) components can illuminate the drivers of spectral activity changes.

NEW METHODS

We analysed intracranial EEG (iEEG) data from 234 subjects, creating a normative map. This map was compared to a cohort of 63 patients with refractory focal epilepsy under consideration for neurosurgery. The normative map was computed using three approaches: (i) relative complete band power, (ii) relative band power with the aperiodic component removed, and (iii) the aperiodic exponent. Abnormalities were calculated for each approach in the patient cohort. We evaluated the spatial profiles, assessed their ability to localize abnormalities, and replicated the findings using magnetoencephalography (MEG).

RESULTS

Normative maps of relative complete band power and relative periodic band power exhibited similar spatial profiles, while the aperiodic normative map revealed higher exponent values in the temporal lobe. Abnormalities estimated through complete band power effectively distinguished between good and bad outcome patients. Combining periodic and aperiodic abnormalities enhanced performance, like the complete band power approach.

COMPARISON WITH EXISTING METHODS AND CONCLUSIONS

Sparing cerebral tissue with abnormalities in both periodic and aperiodic activity may result in poor surgical outcomes. Both periodic and aperiodic components do not carry sufficient information in isolation. The relative complete band power solution proved to be the most reliable method for this purpose. Future studies could investigate how cerebral location or pathology influences periodic or aperiodic abnormalities.

ComBatLS: A location- and scale-preserving method for multi-site image harmonization

Recent work has leveraged massive datasets and advanced harmonization methods to construct normative models of neuroanatomical features and benchmark individuals' morphology. However, current harmonization tools do not preserve the effects of biological covariates including sex and age on features' variances; this failure may induce error in normative scores, particularly when such factors are distributed unequally across sites. Here, we introduce a new extension of the popular ComBat harmonization method, ComBatLS, that preserves biological variance in features' locations and scales. We use UK Biobank data to show that ComBatLS robustly replicates individuals' normative scores better than other ComBat methods when subjects are assigned to sex-imbalanced synthetic "sites". Additionally, we demonstrate that ComBatLS significantly reduces sex biases in normative scores compared to traditional methods. Finally, we show that ComBatLS successfully harmonizes consortium data collected across over 50 studies. R implementation of ComBatLS is available at https://github.com/andy1764/ComBatFamily.

Multimodal Neuroimaging Summary Scores as Neurobiological Markers of Psychosis

BACKGROUND AND HYPOTHESIS

Structural brain alterations are well-established features of schizophrenia but they do not effectively predict disease/disease risk. Similar to polygenic risk scores in genetics, we integrated multifactorial aspects of brain structure into a summary "Neuroscore" and examined its potential as a marker of disease.

STUDY DESIGN

We extracted measures from T1-weighted scans and diffusion tensor imaging (DTI) models from three studies with schizophrenia and healthy individuals. We calculated individual-level summary scores (Neuroscores) for T1-weighted and DTI measures and a combined score (Multimodal Neuroscore-MM). We assessed each score's ability to differentiate schizophrenia cases from controls and its relationship to clinical symptomatology, intelligence quotient (IQ), and medication dosage. We assessed Neuroscore specificity by performing all analyses in a more inclusive psychosis sample and by using scores generated from MDD effect sizes.

STUDY RESULTS

All Neuroscores significantly differentiated schizophrenia cases from controls (T1 d = 0.56, DTI d = 0.29, MM d = 0.64) to a greater degree than individual brain regions. Higher Neuroscores (ie, increased liability) were associated with lower IQ (T1 β = -0.26, DTI β = -0.15, MM β = -0.30). Higher T1-weighted Neuroscores were associated with higher positive and negative symptom severity (Positive β = 0.21, Negative β = 0.16); Higher Multimodal Neuroscores were associated with higher positive symptom severity (β = 0.30). SZ Neuroscores outperformed MDD Neuroscores in predicting IQ (T1: z = 3.5, q = 0.0007; MM: z = 1.8, q = 0.05).

CONCLUSIONS

Neuroscores are a step toward leveraging widespread structural brain alterations in psychosis to identify robust neurobiological markers of disease. Future studies will assess ways to improve neuroscore calculation, including developing the optimal methods to calculate neuroscores and considering disorder overlap.

Dissecting task-based fMRI activity using normative modelling: an application to the Emotional Face Matching Task

Functional neuroimaging has contributed substantially to understanding brain function but is dominated by group analyses that index only a fraction of the variation in these data. It is increasingly clear that parsing the underlying heterogeneity is crucial to understand individual differences and the impact of different task manipulations. We estimate large-scale (N = 7728) normative models of task-evoked activation during the Emotional Face Matching Task, which enables us to bind heterogeneous datasets to a common reference and dissect heterogeneity underlying group-level analyses. We apply this model to a heterogenous patient cohort, to map individual differences between patients with one or more mental health diagnoses relative to the reference cohort and determine multivariate associations with transdiagnostic symptom domains. For the face>shapes contrast, patients have a higher frequency of extreme deviations which are spatially heterogeneous. In contrast, normative models for faces>baseline have greater predictive value for individuals' transdiagnostic functioning. Taken together, we demonstrate that normative modelling of fMRI task-activation can be used to illustrate the influence of different task choices and map replicable individual differences, and we encourage its application to other neuroimaging tasks in future studies.

Quantifying impairment and disease severity using AI models trained on healthy subjects

Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploits the decrease in confidence of these models when presented with impaired or diseased patients to quantify their deviation from the healthy population. We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients. The gold-standard Fugl-Meyer Assessment (FMA) requires in-person administration by a trained assessor for 30-45 minutes, which restricts monitoring frequency and precludes physicians from adapting rehabilitation protocols to the progress of each patient. The COBRA score, computed automatically in under one minute, is shown to be strongly correlated with the FMA on an independent test cohort for two different data modalities: wearable sensors (ρ = 0.814, 95% CI [0.700,0.888]) and video (ρ = 0.736, 95% C.I [0.584, 0.838]). To demonstrate the generalizability of the approach to other conditions, the COBRA score was also applied to quantify severity of knee osteoarthritis from magnetic-resonance imaging scans, again achieving significant correlation with an independent clinical assessment (ρ = 0.644, 95% C.I [0.585,0.696]).

Spatiotemporal patterns in cortical development: Age, puberty, and individual variability from 9 to 13 years of age

Humans and nonhuman primate studies suggest that timing and tempo of cortical development varies neuroanatomically along a sensorimotor-to-association (S-A) axis. Prior human studies have reported a principal S-A axis across various modalities, but largely rely on cross-sectional samples with wide age-ranges. Here, we investigate developmental changes and individual variability in cortical organization along the S-A axis between the ages of 9-13 years using a large, longitudinal sample (N = 2487-3747, 46-50% female) from the Adolescent Brain Cognitive Development Study (ABCD Study®). This work assesses multiple aspects of neurodevelopment indexed by changes in cortical thickness, cortical microarchitecture, and resting-state functional fluctuations. First, we evaluated S-A organization in age-related changes and, then, computed individual-level S-A alignment in brain changes and assessing differences therein due to age, sex, and puberty. Varying degrees of linear and quadratic age-related brain changes were identified along the S-A axis. Yet, these patterns of cortical development were overshadowed by considerable individual variability in S-A alignment. Even within individuals, there was little correspondence between S-A patterning across the different aspects of neurodevelopment investigated (i.e., cortical morphology, microarchitecture, function). Some of the individual variation in developmental patterning of cortical morphology and microarchitecture was explained by age, sex, and pubertal development. Altogether, this work contextualizes prior findings that regional age differences do progress along an S-A axis at a group level, while highlighting broad variation in developmental change between individuals and between aspects of cortical development, in part due to sex and puberty.

Significance Statement

Understanding normative patterns of adolescent brain change, and individual variability therein, is crucial for disentangling healthy and abnormal development. We used longitudinal human neuroimaging data to study several aspects of neurodevelopment during early adolescence and assessed their organization along a sensorimotor-to-association (S-A) axis across the cerebral cortex. Age differences in brain changes were linear and curvilinear along this S-A axis. However, individual-level sensorimotor-association alignment varied considerably, driven in part by differences in age, sex, and pubertal development.

Deep Normative Tractometry for Identifying Joint White Matter Macro- and Micro-structural Abnormalities in Alzheimer's Disease

This study introduces the Deep Normative Tractometry (DNT) framework, that encodes the joint distribution of both macrostructural and microstructural profiles of the brain white matter tracts through a variational autoencoder (VAE). By training on data from healthy controls, DNT learns the normative distribution of tract data, and can delineate along-tract micro- and macro-structural abnormalities. Leveraging a large sample size via generative pre-training, we assess DNT's generalizability using transfer learning on data from an independent cohort acquired in India. Our findings demonstrate DNT's capacity to detect widespread diffusivity abnormalities along tracts in mild cognitive impairment and Alzheimer's disease, aligning closely with results from the Bundle Analytics (BUAN) tractometry pipeline. By incorporating tract geometry information, DNT may be able to distinguish disease-related abnormalities in anisotropy from tract macrostructure, and shows promise in enhancing fine-scale mapping and detection of white matter alterations in neurodegenerative conditions.

Amygdala Volume is Associated with ADHD Risk and Severity Beyond Comorbidities in Adolescents: Clinical Testing of Brain Chart Reference Standards

Understanding atypicalities in ADHD brain correlates is a step towards better understanding ADHD etiology. Efforts to map atypicalities at the level of brain structure have been hindered by the absence of normative reference standards. Recent publication of brain charts allows for assessment of individual variation relative to age- and sex-adjusted reference standards and thus estimation not only of case-control differences but also of intraindividual prediction.

METHODS

Aim was to examine, whether brain charts can be applied in a sample of adolescents (N = 140, 38% female) to determine whether atypical brain subcortical and total volumes are associated with ADHD at-risk status and severity of parent-rated symptoms, accounting for self-rated anxiety and depression, and parent-rated oppositional defiant disorder (ODD) as well as motion.

RESULTS

Smaller bilateral amygdala volume was associated with ADHD at-risk status, beyond effects of comorbidities and motion, and smaller bilateral amygdala volume was associated with inattention and hyperactivity/impulsivity, beyond effects of comorbidities except for ODD symptoms, and motion.

CONCLUSIONS

Individual differences in amygdala volume meaningfully add to estimating ADHD risk and severity. Conceptually, amygdalar involvement is consistent with behavioral and functional imaging data on atypical reinforcement sensitivity as a marker of ADHD-related risk. Methodologically, results show that brain chart reference standards can be applied to address clinically informative, focused and specific questions.

Age-atypical brain functional networks in autism spectrum disorder: a normative modeling approach

BACKGROUND

Despite extensive research into the neural basis of autism spectrum disorder (ASD), the presence of substantial biological and clinical heterogeneity among diagnosed individuals remains a major barrier. Commonly used case‒control designs assume homogeneity among subjects, which limits their ability to identify biological heterogeneity, while normative modeling pinpoints deviations from typical functional network development at individual level.

METHODS

Using a world-wide multi-site database known as Autism Brain Imaging Data Exchange, we analyzed individuals with ASD and typically developed (TD) controls (total n = 1218) aged 5-40 years, generating individualized whole-brain network functional connectivity (FC) maps of age-related atypicality in ASD. We then used local polynomial regression to estimate a networkwise normative model of development and explored correlations between ASD symptoms and brain networks.

RESULTS

We identified a subset exhibiting highly atypical individual-level FC, exceeding 2 standard deviation from the normative value. We also identified clinically relevant networks (mainly default mode network) at cohort level, since the outlier rates decreased with age in TD participants, but increased in those with autism. Moreover, deviations were linked to severity of repetitive behaviors and social communication symptoms.

CONCLUSIONS

Individuals with ASD exhibit distinct, highly individualized trajectories of brain functional network development. In addition, distinct developmental trajectories were observed among ASD and TD individuals, suggesting that it may be challenging to identify true differences in network characteristics by comparing young children with ASD to their TD peers. This study enhances understanding of the biological heterogeneity of the disorder and can inform precision medicine.

Population-level normative models reveal race- and socioeconomic-related variability in cortical thickness of threat neurocircuitry

The inequitable distribution of economic resources and exposure to adversity between racial groups contributes to mental health disparities within the United States. Consideration of the potential neurodevelopmental consequences, however, has been limited particularly for neurocircuitry known to regulate the emotional response to threat. Characterizing the consequences of inequity on threat neurocircuitry is critical for robust and generalizable neurobiological models of psychiatric illness. Here we use data from the Adolescent Brain and Cognitive Development Study 4.0 release to investigate the contributions of individual and neighborhood-level economic resources and exposure to discrimination. We investigate the potential appearance of race-related differences using both standard methods and through population-level normative modeling. We show that, in a sample of white and Black adolescents, racial inequities in socioeconomic factors largely contribute to the appearance of race-related differences in cortical thickness of threat neurocircuitry. The race-related differences are preserved through the use of population-level models and such models also preserve associations between cortical thickness and specific socioeconomic factors. The present findings highlight that such socioeconomic inequities largely underlie race-related differences in brain morphology. The present findings provide important new insight for the generation of generalizable neurobiological models of psychiatric illness.

Heterogeneity of morphometric similarity networks in health and schizophrenia

Introduction

Morphometric similarity is a recently developed neuroimaging phenotype of inter-regional connectivity by quantifying the similarity of a region to other regions based on multiple MRI parameters. Altered average morphometric similarity has been reported in psychotic disorders at the group level, with considerable heterogeneity across individuals. We used normative modeling to address cross-sectional and longitudinal inter-individual heterogeneity of morphometric similarity in health and schizophrenia.

Methods

Morphometric similarity for 62 cortical regions was obtained from baseline and follow-up T1-weighted scans of healthy individuals and patients with chronic schizophrenia. Cortical regions were classified into seven predefined brain functional networks. Using Bayesian Linear Regression and taking into account age, sex, image quality and scanner, we trained and validated normative models in healthy controls from eleven datasets (n = 4310). Individual deviations from the norm (z-scores) in morphometric similarity were computed for each participant for each network and region at both timepoints. A z-score ≧ than 1.96 was considered supra-normal and a z-score ≦ -1.96 infra-normal. As a longitudinal metric, we calculated the change over time of the total number of infra- or supra-normal regions per participant.

Results

At baseline, patients with schizophrenia had decreased morphometric similarity of the default mode network and increased morphometric similarity of the somatomotor network when compared with healthy controls. The percentage of patients with infra- or supra-normal values for any region at baseline and follow-up was low (<6%) and did not differ from healthy controls. Mean intra-group changes over time in the total number of infra- or supra-normal regions were small in schizophrenia and healthy control groups (<1) and there were no significant between-group differences.

Conclusions

In a case-control setting, a decrease of morphometric similarity within the default mode network may be a robust finding implicated in schizophrenia. However, normative modeling suggests that significant reductions and changes over time of regional morphometric similarity are evident only in a minority of patients.

Normative modelling of molecular-based functional circuits captures clinical heterogeneity transdiagnostically in psychiatric patients

Advanced methods such as REACT have allowed the integration of fMRI with the brain's receptor landscape, providing novel insights transcending the multiscale organisation of the brain. Similarly, normative modelling has allowed translational neuroscience to move beyond group-average differences and characterise deviations from health at an individual level. Here, we bring these methods together for the first time. We used REACT to create functional networks enriched with the main modulatory, inhibitory, and excitatory neurotransmitter systems and generated normative models of these networks to capture functional connectivity deviations in patients with schizophrenia, bipolar disorder (BPD), and ADHD. Substantial overlap was seen in symptomatology and deviations from normality across groups, but these could be mapped into a common space linking constellations of symptoms through to underlying neurobiology transdiagnostically. This work provides impetus for developing novel biomarkers that characterise molecular- and systems-level dysfunction at the individual level, facilitating the transition towards mechanistically targeted treatments.

Initiating PeriCBD to probe perinatal influences on neurodevelopment during 3-10 years in China

Adverse perinatal factors can interfere with the normal development of the brain, potentially resulting in long-term effects on the comprehensive development of children. Presently, the understanding of cognitive and neurodevelopmental processes under conditions of adverse perinatal factors is substantially limited. There is a critical need for an open resource that integrates various perinatal factors with the development of the brain and mental health to facilitate a deeper understanding of these developmental trajectories. In this Data Descriptor, we introduce a multicenter database containing information on perinatal factors that can potentially influence children's brain-mind development, namely, periCBD, that combines neuroimaging and behavioural phenotypes with perinatal factors at county/region/central district hospitals. PeriCBD was designed to establish a platform for the investigation of individual differences in brain-mind development associated with perinatal factors among children aged 3-10 years. Ultimately, our goal is to help understand how different adverse perinatal factors specifically impact cognitive development and neurodevelopment. Herein, we provide a systematic overview of the data acquisition/cleaning/quality control/sharing, processes of periCBD.

Normative modeling of thalamic nuclear volumes

Thalamic nuclei have been implicated in neurodegenerative and neuropsychiatric disorders. Normative models for thalamic nuclear volumes have not been proposed thus far. The aim of this work was to establish normative models of thalamic nuclear volumes and subsequently investigate changes in thalamic nuclei in cognitive and psychiatric disorders. Volumes of the bilateral thalami and 12 nuclear regions were generated from T1 MRI data using a novel segmentation method (HIPS-THOMAS) in healthy control subjects (n=2374) and non-control subjects (n=695) with early and late mild cognitive impairment (EMCI, LMCI), Alzheimer's disease (AD), Early psychosis and Schizophrenia, Bipolar disorder, and Attention deficit hyperactivity disorder. Three different normative modelling methods were evaluated while controlling for sex, intracranial volume, and site. Z-scores and extreme z-score deviations were calculated and compared across phenotypes. GAMLSS models performed the best. Statistically significant shifts in z-score distributions consistent with atrophy were observed for most phenotypes. Shifts of progressively increasing magnitude were observed bilaterally from EMCI to AD with larger shifts in the left thalamic regions. Heterogeneous shifts were observed in psychiatric diagnoses with a predilection for the right thalamic regions. Here we present the first normative models of thalamic nuclear volumes and highlight their utility in evaluating heterogenous disorders such as Schizophrenia.

Treatment Response Prediction in Major Depressive Disorder Using Multimodal MRI and Clinical Data: Secondary Analysis of a Randomized Clinical Trial

OBJECTIVE

Response to antidepressant treatment in major depressive disorder varies substantially between individuals, which lengthens the process of finding effective treatment. The authors sought to determine whether a multimodal machine learning approach could predict early sertraline response in patients with major depressive disorder. They assessed the predictive contribution of MR neuroimaging and clinical assessments at baseline and after 1 week of treatment.

METHODS

This was a preregistered secondary analysis of data from the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study, a multisite double-blind, placebo-controlled randomized clinical trial that included 296 adult outpatients with unmedicated recurrent or chronic major depressive disorder. MR neuroimaging and clinical data were collected before and after 1 week of treatment. Performance in predicting response and remission, collected after 8 weeks, was quantified using balanced accuracy (bAcc) and area under the receiver operating characteristic curve (AUROC) scores.

RESULTS

A total of 229 patients were included in the analyses (mean age, 38 years [SD=13]; 66% female). Internal cross-validation performance in predicting response to sertraline (bAcc=68% [SD=10], AUROC=0.73 [SD=0.03]) was significantly better than chance. External cross-validation on data from placebo nonresponders (bAcc=62%, AUROC=0.66) and placebo nonresponders who were switched to sertraline (bAcc=65%, AUROC=0.68) resulted in differences that suggest specificity for sertraline treatment compared with placebo treatment. Finally, multimodal models outperformed unimodal models.

CONCLUSIONS

The study results confirm that early sertraline treatment response can be predicted; that the models are sertraline specific compared with placebo; that prediction benefits from integrating multimodal MRI data with clinical data; and that perfusion imaging contributes most to these predictions. Using this approach, a lean and effective protocol could individualize sertraline treatment planning to improve psychiatric care.