Maturity of gray matter structures and white matter connectomes, and their relationship with psychiatric symptoms in youth

Neurodevelopmental imprints of sociomarkers in adolescent brain connectomes

Neural consequences of social disparities are not yet rigorously investigated. How socioeconomic conditions influence children's connectome development remains unknown. This paper endeavors to gauge how precisely the connectome structure of the brain can predict an individual's social environment, thereby inversely assessing how social influences are engraved in the neural development of the Adolescent brain. Utilizing Adolescent Brain and Cognition Development (ABCD) data (9099 children residing in the United States), we found that social conditions both at the household and neighborhood levels are significantly associated with specific neural connections. Solely with brain connectome data, we train a linear support vector machine (SVM) to predict socio-economic conditions of those adolescents. The classification performance generally improves when the thresholds of the advantageous and disadvantageous environments compartmentalize the extreme cases. Among the tested thresholds, the 20th and 80th percentile thresholds using the dual combination of household income and neighborhood education yielded the highest Area Under the Precision-Recall Curve (AUPRC) of 0.8224. We identified 8 significant connections that critically contribute to predicting social environments in the parietal lobe and frontal lobe. Insights into social factors that contribute to early brain connectome development is critical to mitigate the disadvantages of children growing up in unfavorable neighborhoods.

Brain-age prediction: Systematic evaluation of site effects, and sample age range and size

Structural neuroimaging data have been used to compute an estimate of the biological age of the brain (brain-age) which has been associated with other biologically and behaviorally meaningful measures of brain development and aging. The ongoing research interest in brain-age has highlighted the need for robust and publicly available brain-age models pre-trained on data from large samples of healthy individuals. To address this need we have previously released a developmental brain-age model. Here we expand this work to develop, empirically validate, and disseminate a pre-trained brain-age model to cover most of the human lifespan. To achieve this, we selected the best-performing model after systematically examining the impact of seven site harmonization strategies, age range, and sample size on brain-age prediction in a discovery sample of brain morphometric measures from 35,683 healthy individuals (age range: 5-90 years; 53.59% female). The pre-trained models were tested for cross-dataset generalizability in an independent sample comprising 2101 healthy individuals (age range: 8-80 years; 55.35% female) and for longitudinal consistency in a further sample comprising 377 healthy individuals (age range: 9-25 years; 49.87% female). This empirical examination yielded the following findings: (1) the accuracy of age prediction from morphometry data was higher when no site harmonization was applied; (2) dividing the discovery sample into two age-bins (5-40 and 40-90 years) provided a better balance between model accuracy and explained age variance than other alternatives; (3) model accuracy for brain-age prediction plateaued at a sample size exceeding 1600 participants. These findings have been incorporated into CentileBrain (https://centilebrain.org/#/brainAGE2), an open-science, web-based platform for individualized neuroimaging metrics.

Clinical performance of automated machine learning: A systematic review

Introduction

Automated machine learning (autoML) removes technical and technological barriers to building artificial intelligence models. We aimed to summarise the clinical applications of autoML, assess the capabilities of utilised platforms, evaluate the quality of the evidence trialling autoML, and gauge the performance of autoML platforms relative to conventionally developed models, as well as each other.

Method

This review adhered to a prospectively registered protocol (PROSPERO identifier CRD42022344427). The Cochrane Library, Embase, MEDLINE and Scopus were searched from inception to 11 July 2022. Two researchers screened abstracts and full texts, extracted data and conducted quality assessment. Disagreement was resolved through discussion and if required, arbitration by a third researcher.

Results

There were 26 distinct autoML platforms featured in 82 studies. Brain and lung disease were the most common fields of study of 22 specialties. AutoML exhibited variable performance: area under the receiver operator characteristic curve (AUCROC) 0.35-1.00, F1-score 0.16-0.99, area under the precision-recall curve (AUPRC) 0.51-1.00. AutoML exhibited the highest AUCROC in 75.6% trials; the highest F1-score in 42.3% trials; and the highest AUPRC in 83.3% trials. In autoML platform comparisons, AutoPrognosis and Amazon Rekognition performed strongest with unstructured and structured data, respectively. Quality of reporting was poor, with a median DECIDE-AI score of 14 of 27.

Conclusion

A myriad of autoML platforms have been applied in a variety of clinical contexts. The performance of autoML compares well to bespoke computational and clinical benchmarks. Further work is required to improve the quality of validation studies. AutoML may facilitate a transition to data-centric development, and integration with large language models may enable AI to build itself to fulfil user-defined goals.

Efficacy of MRI data harmonization in the age of machine learning: a multicenter study across 36 datasets

Pooling publicly-available MRI data from multiple sites allows to assemble extensive groups of subjects, increase statistical power, and promote data reuse with machine learning techniques. The harmonization of multicenter data is necessary to reduce the confounding effect associated with non-biological sources of variability in the data. However, when applied to the entire dataset before machine learning, the harmonization leads to data leakage, because information outside the training set may affect model building, and potentially falsely overestimate performance. We propose a 1) measurement of the efficacy of data harmonization; 2) harmonizer transformer, i.e., an implementation of the ComBat harmonization allowing its encapsulation among the preprocessing steps of a machine learning pipeline, avoiding data leakage by design. We tested these tools using brain T1-weighted MRI data from 1740 healthy subjects acquired at 36 sites. After harmonization, the site effect was removed or reduced, and we showed the data leakage effect in predicting individual age from MRI data, highlighting that introducing the harmonizer transformer into a machine learning pipeline allows for avoiding data leakage by design.

Relative brain age is associated with socioeconomic status and anxiety/depression problems in youth

Brain age, a measure of biological aging in the brain, has been linked to psychiatric illness, principally in adult populations. Components of socioeconomic status (SES) associate with differences in brain structure and psychiatric risk across the lifespan. This study aimed to investigate the influence of SES on brain aging in childhood and adolescence, a period of rapid neurodevelopment and peak onset for many psychiatric disorders. We reanalyzed data from the Healthy Brain Network to examine the influence of SES components (occupational prestige, public assistance enrollment, parent education, and household income-to-needs ratio [INR]) on relative brain age (RBA). Analyses included 470 youth (5-17 years; 61.3% men), self-identifying as White (55%), African American (15%), Hispanic (9%), or multiracial (17.2%). Household income was 3.95 ± 2.33 (mean ± SD) times the federal poverty threshold. RBA quantified differences between chronological age and brain age using covariation patterns of morphological features and total volumes. We also examined associations between RBA and psychiatric symptoms (Child Behavior Checklist [CBCL]). Models covaried for sex, scan location, and parent psychiatric diagnoses. In a linear regression, lower RBA is associated with lower parent occupational prestige (p = .01), lower public assistance enrollment (p = .03), and more parent psychiatric diagnoses (p = .01), but not parent education or INR. Lower parent occupational prestige (p = .02) and lower RBA (p = .04) are associated with higher CBCL anxious/depressed scores. Our findings underscore the importance of including SES components in developmental brain research. Delayed brain aging may represent a potential biological pathway from SES to psychiatric risk. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization

Magnetic resonance imaging and computed tomography from multiple batches (e.g. sites, scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to obtain new insights into the human brain. However, significant confounding due to batch-related technical variation, called batch effects, is present in this data; direct application of downstream analyses to the data may lead to biased results. Image harmonization methods seek to remove these batch effects and enable increased generalizability and reproducibility of downstream results. In this review, we describe and categorize current approaches in statistical and deep learning harmonization methods. We also describe current evaluation metrics used to assess harmonization methods and provide a standardized framework to evaluate newly-proposed methods for effective harmonization and preservation of biological information. Finally, we provide recommendations to end-users to advocate for more effective use of current methods and to methodologists to direct future efforts and accelerate development of the field.

A systematic review of multimodal brain age studies: Uncovering a divergence between model accuracy and utility

Brain aging is a complex, multifaceted process that can be challenging to model in ways that are accurate and clinically useful. One of the most common approaches has been to apply machine learning to neuroimaging data with the goal of predicting age in a data-driven manner. Building on initial brain age studies that were derived solely from T1-weighted scans (i.e., unimodal), recent studies have incorporated features across multiple imaging modalities (i.e., "multimodal"). In this systematic review, we show that unimodal and multimodal models have distinct advantages. Multimodal models are the most accurate and sensitive to differences in chronic brain disorders. In contrast, unimodal models from functional magnetic resonance imaging were most sensitive to differences across a broad array of phenotypes. Altogether, multimodal imaging has provided us valuable insight for improving the accuracy of brain age models, but there is still much untapped potential with regard to achieving widespread clinical utility.

Transdiagnostic profiles of behaviour and communication relate to academic and socioemotional functioning and neural white matter organisation

BACKGROUND

Behavioural and language difficulties co-occur in multiple neurodevelopmental conditions. Our understanding of these problems has arguably been slowed by an overreliance on study designs that compare diagnostic groups and fail to capture the overlap across different neurodevelopmental disorders and the heterogeneity within them.

METHODS

We recruited a large transdiagnostic cohort of children with complex needs (N = 805) to identify distinct subgroups of children with common profiles of behavioural and language strengths and difficulties. We then investigated whether and how these data-driven groupings could be distinguished from a comparison sample (N = 158) on measures of academic and socioemotional functioning and patterns of global and local white matter connectome organisation. Academic skills were assessed via standardised measures of reading and maths. Socioemotional functioning was captured by the parent-rated version of the Strengths and Difficulties Questionnaire.

RESULTS

We identified three distinct subgroups of children, each with different levels of difficulties in structural language, pragmatic communication, and hot and cool executive functions. All three subgroups struggled with academic and socioemotional skills relative to the comparison sample, potentially representing three alternative but related developmental pathways to difficulties in these areas. The children with the weakest language skills had the most widespread difficulties with learning, whereas those with more pronounced difficulties with hot executive skills experienced the most severe difficulties in the socioemotional domain. Each data-driven subgroup could be distinguished from the comparison sample based on both shared and subgroup-unique patterns of neural white matter organisation. Children with the most pronounced deficits in language, cool executive, or hot executive function were differentiated from the comparison sample by altered connectivity in predominantly thalamocortical, temporal-parietal-occipital, and frontostriatal circuits, respectively.

CONCLUSIONS

These findings advance our understanding of commonly co-morbid behavioural and language problems and their relationship to behavioural outcomes and neurobiological substrates.

Systematic evaluation of machine learning algorithms for neuroanatomically-based age prediction in youth

Application of machine learning (ML) algorithms to structural magnetic resonance imaging (sMRI) data has yielded behaviorally meaningful estimates of the biological age of the brain (brain-age). The choice of the ML approach in estimating brain-age in youth is important because age-related brain changes in this age-group are dynamic. However, the comparative performance of the available ML algorithms has not been systematically appraised. To address this gap, the present study evaluated the accuracy (mean absolute error [MAE]) and computational efficiency of 21 machine learning algorithms using sMRI data from 2105 typically developing individuals aged 5-22 years from five cohorts. The trained models were then tested in two independent holdout datasets, one comprising 4078 individuals aged 9-10 years and another comprising 594 individuals aged 5-21 years. The algorithms encompassed parametric and nonparametric, Bayesian, linear and nonlinear, tree-based, and kernel-based models. Sensitivity analyses were performed for parcellation scheme, number of neuroimaging input features, number of cross-validation folds, number of extreme outliers, and sample size. Tree-based models and algorithms with a nonlinear kernel performed comparably well, with the latter being especially computationally efficient. Extreme Gradient Boosting (MAE of 1.49 years), Random Forest Regression (MAE of 1.58 years), and Support Vector Regression (SVR) with Radial Basis Function (RBF) Kernel (MAE of 1.64 years) emerged as the three most accurate models. Linear algorithms, with the exception of Elastic Net Regression, performed poorly. Findings of the present study could be used as a guide for optimizing methodology when quantifying brain-age in youth.

Automated Multiclass Artifact Detection in Diffusion MRI Volumes via 3D Residual Squeeze-and-Excitation Convolutional Neural Networks

Diffusion MRI (dMRI) is widely used to investigate neuronal and structural development of brain. dMRI data is often contaminated with various types of artifacts. Hence, artifact type identification in dMRI volumes is an essential pre-processing step prior to carrying out any further analysis. Manual artifact identification amongst a large pool of dMRI data is a highly labor-intensive task. Previous attempts at automating this process are often limited to a binary classification ("poor" vs. "good" quality) of the dMRI volumes or focus on detecting a single type of artifact (e.g., motion, Eddy currents, etc.). In this work, we propose a deep learning-based automated multiclass artifact classifier for dMRI volumes. Our proposed framework operates in 2 steps. In the first step, the model predicts labels associated with 3D mutually exclusive collectively exhaustive (MECE) sub-volumes or "slabs" extracted from whole dMRI volumes. In the second step, through a voting process, the model outputs the artifact class present in the whole volume under investigation. We used two different datasets for training and evaluating our model. Specifically, we utilized 2,494 poor-quality dMRI volumes from the Adolescent Brain Cognitive Development (ABCD) and 4,226 from the Healthy Brain Network (HBN) dataset. Our results demonstrate accurate multiclass volume-level main artifact type prediction with 96.61 and 97.52% average accuracies on the ABCD and HBN test sets, respectively. Finally, in order to demonstrate the effectiveness of the proposed framework in dMRI pre-processing pipelines, we conducted a proof-of-concept dMRI analysis exploring the relationship between whole-brain fractional anisotropy (FA) and participant age, to test whether the use of our model improves the brain-age association.

Brain age prediction using fMRI network coupling in youths and associations with psychiatric symptoms

OBJECTIVE

Magnetic resonance imaging (MRI) has shown that estimated brain age is deviant from chronological age in various common brain disorders. Brain age estimation could be useful for investigating patterns of brain maturation and integrity, aiding to elucidate brain mechanisms underlying these heterogeneous conditions. Here, we examined functional brain age in two large samples of children and adolescents and its relation to mental health.

METHODS

We used resting-state fMRI data from the Philadelphia Neurodevelopmental Cohort (PNC; n = 1126, age range 8-22 years) to estimate functional connectivity between brain networks, and utilized these as features for brain age prediction. We applied the prediction model to 1387 individuals (age range 8-22 years) in the Healthy Brain Network sample (HBN). In addition, we estimated brain age in PNC using a cross-validation framework. Next, we tested for associations between brain age gap and various aspects of psychopathology and cognitive performance.

RESULTS

Our model was able to predict age in the independent test samples, with a model performance of r = 0.54 for the HBN test set, supporting consistency in functional connectivity patterns between samples and scanners. Linear models revealed a significant association between brain age gap and psychopathology in PNC, where individuals with a lower estimated brain age, had a higher overall symptom burden. These associations were not replicated in HBN.

DISCUSSION

Our findings support the use of brain age prediction from fMRI-based connectivity. While requiring further extensions and validations, the approach may be instrumental for detecting brain phenotypes related to intrinsic connectivity and could assist in characterizing risk in non-typically developing populations.

Maturity of gray matter structures and white matter connectomes, and their relationship with psychiatric symptoms in youth

Brain predicted age difference, or BrainPAD, compares chronological age to an age estimate derived by applying machine learning (ML) to MRI brain data. BrainPAD studies in youth have been relatively limited, often using only a single MRI modality or a single ML algorithm. Here, we use multimodal MRI with a stacked ensemble ML approach that iteratively applies several ML algorithms (AutoML). Eligible participants in the Healthy Brain Network (N = 489) were split into training and test sets. Morphometry estimates, white matter connectomes, or both were entered into AutoML to develop BrainPAD models. The best model was then applied to a held‐out evaluation dataset, and associations with psychometrics were estimated. Models using morphometry and connectomes together had a mean absolute error of 1.18 years, outperforming models using a single MRI modality. Lower BrainPAD values were associated with more symptoms on the CBCL (p_corr = .012) and lower functioning on the Children's Global Assessment Scale (p_corr = .012). Higher BrainPAD values were associated with better performance on the Flanker task (p_corr = .008). Brain age prediction was more accurate using ComBat‐harmonized brain data (MAE = 0.26). Associations with psychometric measures remained consistent after ComBat harmonization, though only the association with CGAS reached statistical significance in the reduced sample. Our findings suggest that BrainPAD scores derived from unharmonized multimodal MRI data using an ensemble ML approach may offer a clinically relevant indicator of psychiatric and cognitive functioning in youth.