Age prediction on the basis of brain anatomical measures

Machine Learning and Deep Learning Approaches in Lifespan Brain Age Prediction: A Comprehensive Review

The concept of 'brain age', derived from neuroimaging data, serves as a crucial biomarker reflecting cognitive vitality and neurodegenerative trajectories. In the past decade, machine learning (ML) and deep learning (DL) integration has transformed the field, providing advanced models for brain age estimation. However, achieving precise brain age prediction across all ages remains a significant analytical challenge. This comprehensive review scrutinizes advancements in ML- and DL-based brain age prediction, analyzing 52 peer-reviewed studies from 2020 to 2024. It assesses various model architectures, highlighting their effectiveness and nuances in lifespan brain age studies. By comparing ML and DL, strengths in forecasting and methodological limitations are revealed. Finally, key findings from the reviewed articles are summarized and a number of major issues related to ML/DL-based lifespan brain age prediction are discussed. Through this study, we aim at the synthesis of the current state of brain age prediction, emphasizing both advancements and persistent challenges, guiding future research, technological advancements, and improving early intervention strategies for neurodegenerative diseases.

Complexity measures reveal age-dependent changes in electroencephalogram during working memory task

The alterations in electroencephalogram (EEG) signals are the complex outputs of functional factors, such as normal physiological aging, pathological process, which results in further cognitive decline. It is not clear that when brain aging initiates, but elderly people are vulnerable to be incipient of neurodegenerative diseases such as Alzheimer's disease. The EEG signals were recorded from 20 healthy middle age and 20 healthy elderly subjects while performing a working memory task. Higuchi's fractal dimension (HFD), Katz's fractal dimension (KFD), sample entropy and three Hjorth parameters were extracted to analyse the complexity of EEG signals. Four machine learning classifiers, multilayer perceptron (MLP), support vector machine (SVM), K-nearest neighbour (KNN), and logistic model tree (LMT) were employed to distinguish the EEG signals of middle age and elderly age groups. HFD, KFD and Hjorth complexity were found significantly correlated with age. MLP achieved the highest overall accuracy of 93.75%. For posterior region, the maximum accuracy of 92.50% was achieved using MLP. Since fractal dimension associated with the complexity of EEG signals, HFD, KFD and Hjorth complexity demonstrated the decreased complexity from middle age to elderly groups. The complexity features appear to be more appropriate indicators of monitoring EEG signal complexity in healthy aging.

A perspective on brain-age estimation and its clinical promise

Brain-age estimation has gained increased attention in the neuroscientific community owing to its potential use as a biomarker of brain health. The difference between estimated and chronological age based on neuroimaging data enables a unique perspective on brain development and aging, with multiple open questions still remaining in the brain-age research field. This Perspective presents an overview of current advancements in the field and envisions the future evolution of the brain-age framework before its potential deployment in hospital settings.

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.

Prediction of chronological age from resting-state EEG power in the first three years of life

The infant brain undergoes rapid and significant developmental changes in the first three years of life. Understanding these changes through the prediction of chronological age using neuroimaging data can provide insights into typical and atypical brain development. We utilized longitudinal resting-state EEG data from 457 typically developing infants, comprising 938 recordings, to develop age prediction models. The multilayer perceptron model demonstrated the highest accuracy with an R2 of 0.82 and a mean absolute error of 92.4 days. Aperiodic offset and periodic theta, alpha, and beta power were identified as key predictors of age via Shapley values. Application of the model to EEG data from infants later diagnosed with autism spectrum disorder or Down syndrome revealed significant underestimations of chronological age. This study establishes the feasibility of using EEG to assess brain maturation in early childhood and supports its potential as a clinical tool for early identification of alterations in brain development.

Beyond network connectivity: A classification approach to brain age prediction with resting-state fMRI

The brain is a complex, dynamic organ that shows differences in the same subject at various periods. Understanding how brain activity changes across age as a function of the brain networks has been greatly abetted by fMRI. Canonical analysis consists of determining how alterations in connectivity patterns (CPs) of certain regions are affected. An alternative approach is taken here by not considering connectivity but rather features computed from recordings at the regions of interest (ROIs). Using machine learning (ML) we assess how neural signals are altered by and prospectively predictive of age and sex via a methodology that is novel in drawing upon pairwise classification across six decades of subjects' chronological ages. ML is used to answer the equally important questions of what properties of the computed features are most predictive as well as which brain networks are most affected by aging. It was found that there is decreased differentiation among the neural signals of older subjects that are separated in age by the same number of years as younger subjects. Furthermore, the burstiness of the signals change at different rates between males and females. The findings provide insight into brain aging via an ROI-based analysis, the consideration of several feature groups, and a novel classification-based ML pipeline. There is also a contribution to understanding the effects of data aggregated from different recording centers on the conclusions of fMRI studies.

Structural indices of brain aging in methamphetamine use disorder

BACKGROUND

Methamphetamine use is surging globally. It has been linked to premature stroke, Parkinsonism, and dementia, suggesting that it may accelerate brain aging.

METHODS

We performed a retrospective study to determine if structural indices of brain aging were more prevalent prior to old age (26 - 54 years) in individuals with Methamphetamine Use Disorder (MUD), who were in early abstinence (M ± SD = 22.1 ± 25.6 days) than in healthy control (HC) participants. We compared T1-weighted MRI brain scans in age- and sex-matched groups (n = 89/group) on three structural features of brain aging: the brain volume/cerebrospinal fluid (BV/CSF) index, volume of white matter hypointensities/lesions, and choroid plexus volume.

RESULTS

The MUD group had a lower mean BV/CSF index and larger volumes of white matter hypointensities and choroid plexus (p-values < 0.01). Regression analyses showed significant age-by-group effects, indicating different age trajectories of the BV/CSF index and choroid plexus volume, consistent with abnormal global brain atrophy and choroid plexus pathology in the MUD group. Significant age and group main effects reflected a larger volume of white matter hypointensities for older participants across groups and for the MUD group irrespective of age. None of the three measures of brain aging correlated significantly with recent use or duration of recent abstinence from methamphetamine.

CONCLUSIONS

Premature brain pathology, which may reflect cerebrovascular damage and dysfunction of the choroid plexus, occurs in people with MUD. Such pathology may affect cognition and thereby efficacy of behavioral treatments for MUD.

Brain age prediction across the human lifespan using multimodal MRI data

Measuring differences between an individual's age and biological age with biological information from the brain have the potential to provide biomarkers of clinically relevant neurological syndromes that arise later in human life. To explore the effect of multimodal brain magnetic resonance imaging (MRI) features on the prediction of brain age, we investigated how multimodal brain imaging data improved age prediction from more imaging features of structural or functional MRI data by using partial least squares regression (PLSR) and longevity data sets (age 6-85 years). First, we found that the age-predicted values for each of these ten features ranged from high to low: cortical thickness (R = 0.866, MAE = 7.904), all seven MRI features (R = 0.8594, MAE = 8.24), four features in structural MRI (R = 0.8591, MAE = 8.24), fALFF (R = 0.853, MAE = 8.1918), gray matter volume (R = 0.8324, MAE = 8.931), three rs-fMRI feature (R = 0.7959, MAE = 9.744), mean curvature (R = 0.7784, MAE = 10.232), ReHo (R = 0.7833, MAE = 10.122), ALFF (R = 0.7517, MAE = 10.844), and surface area (R = 0.719, MAE = 11.33). In addition, the significance of the volume and size of brain MRI data in predicting age was also studied. Second, our results suggest that all multimodal imaging features, except cortical thickness, improve brain-based age prediction. Third, we found that the left hemisphere contributed more to the age prediction, that is, the left hemisphere showed a greater weight in the age prediction than the right hemisphere. Finally, we found a nonlinear relationship between the predicted age and the amount of MRI data. Combined with multimodal and lifespan brain data, our approach provides a new perspective for chronological age prediction and contributes to a better understanding of the relationship between brain disorders and aging.

Structure-decoupled functional connectome-based brain age prediction provides higher association to cognition

Brain age prediction as well as the prediction difference has been well examined to be a potential biomarker for brain disease or abnormal aging process. However, less knowledge was reported for the cognitive association within normal population. In this study, we proposed a novel approach to brain age prediction by structure-decoupled functional connectome. The original functional connectome was decomposed and decoupled into a structure-decoupled functional connectome using structural connectome harmonics. Our method was applied to a large dataset of normal aging individuals and achieved a high correlation between predicted and chronological age (r = 0.77). Both the original FC and structure-decoupled FC could be well-trained in a brain age prediction model. Significant remarkable relationships between the brain age prediction difference (predicted age minus chronological age) and cognitive scores were discovered. However, the brain age-predicted difference driven by structure-decoupled FC showed a stronger correction to the two cognitive scores (MMSE: r = -0.27, P -value = 0.002; MoCA: r = -0.32, P -value = 0.0003). Our findings suggest that our structure-decoupled functional connectivity approach could provide a more individual-specific functional network, leading to improved brain age prediction performance and a better understanding of cognitive decline in aging.

Ordinal Classification with Distance Regularization for Robust Brain Age Prediction

Age is one of the major known risk factors for Alzheimer's Disease (AD). Detecting AD early is crucial for effective treatment and preventing irreversible brain damage. Brain age, a measure derived from brain imaging reflecting structural changes due to aging, may have the potential to identify AD onset, assess disease risk, and plan targeted interventions. Deep learning-based regression techniques to predict brain age from magnetic resonance imaging (MRI) scans have shown great accuracy recently. However, these methods are subject to an inherent regression to the mean effect, which causes a systematic bias resulting in an overestimation of brain age in young subjects and underestimation in old subjects. This weakens the reliability of predicted brain age as a valid biomarker for downstream clinical applications. Here, we reformulate the brain age prediction task from regression to classification to address the issue of systematic bias. Recognizing the importance of preserving ordinal information from ages to understand aging trajectory and monitor aging longitudinally, we propose a novel ORdinal Distance Encoded Regularization (ORDER) loss that incorporates the order of age labels, enhancing the model's ability to capture age-related patterns. Extensive experiments and ablation studies demonstrate that this framework reduces systematic bias, outperforms state-of-art methods by statistically significant margins, and can better capture subtle differences between clinical groups in an independent AD dataset. Our implementation is publicly available at https://github.com/jaygshah/Robust-Brain-Age-Prediction.

Prediction of brain age using structural magnetic resonance imaging: A comparison of accuracy and test-retest reliability of publicly available software packages

Brain age prediction algorithms using structural magnetic resonance imaging (MRI) aim to assess the biological age of the human brain. The difference between a person's chronological age and the estimated brain age is thought to reflect deviations from a normal aging trajectory, indicating a slower or accelerated biological aging process. Several pre-trained software packages for predicting brain age are publicly available. In this study, we perform a comparison of such packages with respect to (1) predictive accuracy, (2) test-retest reliability, and (3) the ability to track age progression over time. We evaluated the six brain age prediction packages: brainageR, DeepBrainNet, brainage, ENIGMA, pyment, and mccqrnn. The accuracy and test-retest reliability were assessed on MRI data from 372 healthy people aged between 18.4 and 86.2 years (mean 38.7 ± 17.5 years). All packages showed significant correlations between predicted brain age and chronological age (r = 0.66-0.97, p < 0.001), with pyment displaying the strongest correlation. The mean absolute error was between 3.56 (pyment) and 9.54 years (ENIGMA). brainageR, pyment, and mccqrnn were superior in terms of reliability (ICC values between 0.94-0.98), as well as predicting age progression over a longer time span. Of the six packages, pyment and brainageR consistently showed the highest accuracy and test-retest reliability.

Predicting 'Brainage' in late childhood to adolescence (6-17yrs) using structural MRI, morphometric similarity, and machine learning

Brain development is regularly studied using structural MRI. Recently, studies have used a combination of statistical learning and large-scale imaging databases of healthy children to predict an individual's age from structural MRI. This data-driven, predicted 'Brainage' typically differs from the subjects chronological age, with this difference a potential measure of individual difference. Few studies have leveraged higher-order or connectomic representations of structural MRI data for this Brainage approach. We leveraged morphometric similarity as a network-level approach to structural MRI to generate predictive models of age. We benchmarked these novel Brainage approaches using morphometric similarity against more typical, single feature (i.e., cortical thickness) approaches. We showed that these novel methods did not outperform cortical thickness or cortical volume measures. All models were significantly biased by age, but robust to motion confounds. The main results show that, whilst morphometric similarity mapping may be a novel way to leverage additional information from a T1-weighted structural MRI beyond individual features, in the context of a Brainage framework, morphometric similarity does not provide more accurate predictions of age. Morphometric similarity as a network-level approach to structural MRI may be poorly positioned to study individual differences in brain development in healthy participants in this way.

Replication and Refinement of Brain Age Model for adolescent development

The discrepancy between chronological age and estimated brain age, known as the brain age gap, may serve as a biomarker to reveal brain development and neuropsychiatric problems. This has motivated many studies focusing on the accurate estimation of brain age using different features and models, of which the generalizability is yet to be tested. Our recent study has demonstrated that conventional machine learning models can achieve high accuracy on brain age prediction during development using only a small set of selected features from multimodal brain imaging data. In the current study, we tested the replicability of various brain age models on the Adolescent Brain Cognitive Development (ABCD) cohort. We proposed a new refined model to improve the robustness of brain age prediction. The direct replication test for existing brain age models derived from the age range of 8-22 years onto the ABCD participants at baseline (9 to 10 years old) and year-two follow-up (11 to 12 years old) indicate that pre-trained models could capture the overall mean age failed precisely estimating brain age variation within a narrow range. The refined model, which combined broad prediction of the pre-trained model and granular information with the narrow age range, achieved the best performance with a mean absolute error of 0.49 and 0.48 years on the baseline and year-two data, respectively. The brain age gap yielded by the refined model showed significant associations with the participants' information processing speed and verbal comprehension ability on baseline data.

Age-dependent changes in brain iron deposition and volume in deep gray matter nuclei using quantitative susceptibility mapping

BACKGROUND

Microstructural changes in deep gray matter (DGM) nuclei are related to physiological behavior, cognition, and memory. Therefore, it is critical to study age-dependent trajectories of biomarkers in DGM nuclei for understanding brain development and aging, as well as predicting cognitive or neurodegenerative diseases.

OBJECTIVES

We aimed to (1) characterize age-dependent trajectories of mean susceptibility, adjusted volume, and total iron content simultaneously in DGM nuclei using quantitative susceptibility mapping (QSM); (2) examine potential contributions of sex related effects to the different age-dependence trajectories of volume and iron deposition; and (3) evaluate the ability of brain age prediction by combining mean magnetic susceptibility and volume of DGM nuclei.

METHODS

Magnetic susceptibilities and volumetric values of DGM nuclei were obtained from 220 healthy participants (aged 10-70 years) scanned on a 3T MRI system. Regions of interest (ROIs) were drawn manually on the QSM images. Univariate regression analysis between age and each of the MRI measurements in a single ROI was performed. Pearson correlation coefficients were calculated between magnetic susceptibility and adjusted volume in a single ROI. The statistical significance of sex differences in age-dependent trajectories of magnetic susceptibilities and adjusted volumes were determined using one-way ANCOVA. Multiple regression analysis was used to evaluate the ability to estimate brain age using a combination of the mean susceptibilities and adjusted volumes in multiple DGM nuclei.

RESULTS

Mean susceptibility and total iron content increased linearly, quadratically, or exponentially with age in all six DGM nuclei. Negative linear correlation was observed between adjusted volume and age in the head of the caudate nucleus (CN; R² = 0.196, p < 0.001). Quadratic relationships were found between adjusted volume and age in the putamen (PUT; R² = 0.335, p < 0.001), globus pallidus (GP; R² = 0.062, p = 0.001), and dentate nucleus (DN; R² = 0.077, p < 0.001). Males had higher mean magnetic susceptibility than females in the PUT (p = 0.001), red nucleus (RN; p = 0.002), and substantia nigra (SN; p < 0.001). Adjusted volumes of the CN (p < 0.001), PUT (p = 0.030), GP (p = 0.007), SN (p = 0.021), and DN (p < 0.001) were higher in females than those in males throughout the entire age range (10-70 years old). The total iron content of females was higher than that of males in the CN (p < 0.001), but lower than that of males in the PUT (p = 0.014) and RN (p = 0.043) throughout the entire age range (10-70 years old). Multiple regression analyses revealed that the combination of the mean susceptibility value of the PUT, and the volumes of the CN and PUT had the strongest associations with brain age (R² = 0.586).

CONCLUSIONS

QSM can be used to simultaneously investigate age- and sex- dependent changes in magnetic susceptibility and volume of DGM nuclei, thus enabling a comprehensive understanding of the developmental trajectories of iron accumulation and volume in DGM nuclei during brain development and aging.

Comparison of Machine Learning Models for Brain Age Prediction Using Six Imaging Modalities on Middle-Aged and Older Adults

Machine learning (ML) has transformed neuroimaging research by enabling accurate predictions and feature extraction from large datasets. In this study, we investigate the application of six ML algorithms (Lasso, relevance vector regression, support vector regression, extreme gradient boosting, category boost, and multilayer perceptron) to predict brain age for middle-aged and older adults, which is a crucial area of research in neuroimaging. Despite the plethora of proposed ML models, there is no clear consensus on how to achieve better performance in brain age prediction for this population. Our study stands out by evaluating the impact of both ML algorithms and image modalities on brain age prediction performance using a large cohort of cognitively normal adults aged 44.6 to 82.3 years old (N = 27,842) with six image modalities. We found that the predictive performance of brain age is more reliant on the image modalities used than the ML algorithms employed. Specifically, our study highlights the superior performance of T1-weighted MRI and diffusion-weighted imaging and demonstrates that multi-modality-based brain age prediction significantly enhances performance compared to unimodality. Moreover, we identified Lasso as the most accurate ML algorithm for predicting brain age, achieving the lowest mean absolute error in both single-modality and multi-modality predictions. Additionally, Lasso also ranked highest in a comprehensive evaluation of the relationship between BrainAGE and the five frequently mentioned BrainAGE-related factors. Notably, our study also shows that ensemble learning outperforms Lasso when computational efficiency is not a concern. Overall, our study provides valuable insights into the development of accurate and reliable brain age prediction models for middle-aged and older adults, with significant implications for clinical practice and neuroimaging research. Our findings highlight the importance of image modality selection and emphasize Lasso as a promising ML algorithm for brain age prediction.

The foundation and architecture of precision medicine in neurology and psychiatry

Neurological and psychiatric diseases have high degrees of genetic and pathophysiological heterogeneity, irrespective of clinical manifestations. Traditional medical paradigms have focused on late-stage syndromic aspects of these diseases, with little consideration of the underlying biology. Advances in disease modeling and methodological design have paved the way for the development of precision medicine (PM), an established concept in oncology with growing attention from other medical specialties. We propose a PM architecture for central nervous system diseases built on four converging pillars: multimodal biomarkers, systems medicine, digital health technologies, and data science. We discuss Alzheimer's disease (AD), an area of significant unmet medical need, as a case-in-point for the proposed framework. AD can be seen as one of the most advanced PM-oriented disease models and as a compelling catalyzer towards PM-oriented neuroscience drug development and advanced healthcare practice.

Predicting 'Brainage' in the Developmental Period using Structural MRI, Morphometric Similarity, and Machine Learning

Brain development is regularly studied using structural MRI. Recently, studies have used a combination of statistical learning and large-scale imaging databases of healthy-children to predict an individual's age from structural MRI. This data-driven, 'brainage' typically differs from the subjects chronological age, with this difference a potential measure of individual difference. Few studies have leveraged higher-order or connectomic representations of structural MRI data for this brainage approach. We leveraged morphometric similarity as a network-level approach to structural MRI to generate predictive models of age. We benchmarked these novel brain-age approaches using morphometric similarity against more typical, single feature (i.e. cortical thickness) approaches. We showed that these novel methods did not outperform cortical thickness or cortical volume measures. All models were significantly biased by age, but robust to motion confounds. The main results show that, whilst morphometric similarity mapping may be a novel way to leverage additional information from a T1-weighted structural MRI beyond individual features, in the context of a brain-age framework, morphometric similarity does not explain more variance than individual structural features. Morphometric similarity as a network-level approach to structural MRI may be poorly positioned to study individual differences in brain development in healthy individuals.

Fear of Missing Out, Emotional Intelligence and Attachment in Older Adults in Argentina

In recent years, the rise of social networks has changed relationships and lifestyles around the world. This has led to the emergence of the Fear of Missing Out (FoMO), which consists of the need to constantly check social media and the anguish that comes from feeling a lack of rewarding experiences. The impact derived from the use of technologies in a digital environment has been widely studied in young people but not so much in older adults. The main aim of this study was to analyze FoMO levels in older adults and their relationships with sociodemographic and formative factors. Another aim of this study was to analyze whether the dimensions of emotional intelligence, the different forms of attachment and psychological symptomatology affect the FoMO levels of older adults. A total of 690 older adults from Argentina aged between 60 and 90 years (M = 69.01; SD = 5.48) participated, 54.5% of whom were women, responding using a geolocated online questionnaire. The main results confirmed that older people show FoMO levels similar to other general samples. In addition, results show several predictor variables with respect to FoMO: emotional attention, insecure attachment, depression and difficulties in interpersonal relationships. The implications of the results observed in older adults are discussed.

Association of Maternal Depression During Pregnancy and Recent Stress With Brain Age Among Adult Offspring

IMPORTANCE

Maternal mental health problems during pregnancy are associated with altered neurodevelopment in offspring, but the long-term relationship between these prenatal risk factors and offspring brain structure in adulthood remains incompletely understood due to a paucity of longitudinal studies.

OBJECTIVE

To evaluate the association between exposure to maternal depression in utero and offspring brain age in the third decade of life, and to evaluate recent stressful life events as potential moderators of this association.

DESIGN, SETTING, AND PARTICIPANTS

This cohort study examined the 30-year follow-up of a Czech prenatal birth cohort with a within-participant design neuroimaging component in young adulthood conducted from 1991 to 2022. Participants from the European Longitudinal Study of Pregnancy and Childhood prenatal birth cohort were recruited for 2 magnetic resonance imaging (MRI) follow-ups, one between ages 23 and 24 years (early 20s) and another between ages 28 and 30 years (late 20s).

EXPOSURES

Maternal depression during pregnancy; stressful life events in the past year experienced by the young adult offspring.

MAIN OUTCOMES AND MEASURES

Gap between estimated neuroanatomical vs chronological age at MRI scan (brain age gap estimation [BrainAGE]) calculated once in participants' early 20s and once in their late 20s, and pace of aging calculated as the differences between BrainAGE at the 2 MRI sessions in young adulthood.

RESULTS

A total of 260 individuals participated in the second neuroimaging follow-up (mean [SD] age, 29.5 [0.6] years; 135 [52%] male); MRI data for both time points and a history of maternal depression were available for 110 participants (mean [SD] age, 29.3 [0.6] years; 56 [51%] male). BrainAGE in participants' early 20s was correlated with BrainAGE in their late 20s (r = 0.7, P < .001), and a previously observed association between maternal depression during pregnancy and BrainAGE in their early 20s persisted in their late 20s (adjusted R2 = 0.04; P = .04). However, no association emerged between maternal depression during pregnancy and the pace of aging between the 2 MRI sessions. The stability of the associations between maternal depression during pregnancy and BrainAGE was also supported by the lack of interactions with recent stress. In contrast, more recent stress was associated with greater pace of aging between the 2 MRI sessions, independent of maternal depression (adjusted R2 = 0.09; P = .01).

CONCLUSIONS AND RELEVANCE

The findings of this cohort study suggest that maternal depression and recent stress may have independent associations with brain age and the pace of aging, respectively, in young adulthood. Prevention and treatment of depression in pregnant mothers may have long-term implications for offspring brain development.

Multimodal brain age prediction fusing morphometric and imaging data and association with cardiovascular risk factors

Introduction

The difference between the chronological and biological brain age, called the brain age gap (BAG), has been identified as a promising biomarker to detect deviation from normal brain aging and to indicate the presence of neurodegenerative diseases. Moreover, the BAG has been shown to encode biological information about general health, which can be measured through cardiovascular risk factors. Current approaches for biological brain age estimation, and therefore BAG estimation, either depend on hand-crafted, morphological measurements extracted from brain magnetic resonance imaging (MRI) or on direct analysis of brain MRI images. The former can be processed with traditional machine learning models while the latter is commonly processed with convolutional neural networks (CNNs). Using a multimodal setting, this study aims to compare both approaches in terms of biological brain age prediction accuracy and biological information captured in the BAG.

Methods

T1-weighted MRI, containing brain tissue information, and magnetic resonance angiography (MRA), providing information about brain arteries, from 1,658 predominantly healthy adults were used. The volumes, surface areas, and cortical thickness of brain structures were extracted from the T1-weighted MRI data, while artery density and thickness within the major blood flow territories and thickness of the major arteries were extracted from MRA data. Independent multilayer perceptron and CNN models were trained to estimate the brain age from the hand-crafted features and image data, respectively. Next, both approaches were fused to assess the benefits of combining image data and hand-crafted features for brain age prediction.

Results

The combined model achieved a mean absolute error of 4 years between the chronological and predicted biological brain age. Among the independent models, the lowest mean absolute error was observed for the CNN using T1-weighted MRI data (4.2 years). When evaluating the BAGs obtained using the different approaches and imaging modalities, diverging associations between cardiovascular risk factors were found. For example, BAGs obtained from the CNN models showed an association with systolic blood pressure, while BAGs obtained from hand-crafted measurements showed greater associations with obesity markers.

Discussion

In conclusion, the use of more diverse sources of data can improve brain age estimation modeling and capture more diverse biological deviations from normal aging.

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.

Neuroimaging-Based Brain Age Estimation: A Promising Personalized Biomarker in Neuropsychiatry

It is now possible to estimate an individual's brain age via brain scans and machine-learning models. This validated technique has opened up new avenues for addressing clinical questions in neurology, and, in this review, we summarize the many clinical applications of brain-age estimation in neuropsychiatry and general populations. We first provide an introduction to typical neuroimaging modalities, feature extraction methods, and machine-learning models that have been used to develop a brain-age estimation framework. We then focus on the significant findings of the brain-age estimation technique in the field of neuropsychiatry as well as the usefulness of the technique for addressing clinical questions in neuropsychiatry. These applications may contribute to more timely and targeted neuropsychiatric therapies. Last, we discuss the practical problems and challenges described in the literature and suggest some future research directions.

Brain Age Prediction: A Comparison between Machine Learning Models Using Brain Morphometric Data

Brain structural morphology varies over the aging trajectory, and the prediction of a person's age using brain morphological features can help the detection of an abnormal aging process. Neuroimaging-based brain age is widely used to quantify an individual's brain health as deviation from a normative brain aging trajectory. Machine learning approaches are expanding the potential for accurate brain age prediction but are challenging due to the great variety of machine learning algorithms. Here, we aimed to compare the performance of the machine learning models used to estimate brain age using brain morphological measures derived from structural magnetic resonance imaging scans. We evaluated 27 machine learning models, applied to three independent datasets from the Human Connectome Project (HCP, n = 1113, age range 22-37), the Cambridge Centre for Ageing and Neuroscience (Cam-CAN, n = 601, age range 18-88), and the Information eXtraction from Images (IXI, n = 567, age range 19-86). Performance was assessed within each sample using cross-validation and an unseen test set. The models achieved mean absolute errors of 2.75-3.12, 7.08-10.50, and 8.04-9.86 years, as well as Pearson's correlation coefficients of 0.11-0.42, 0.64-0.85, and 0.63-0.79 between predicted brain age and chronological age for the HCP, Cam-CAN, and IXI samples, respectively. We found a substantial difference in performance between models trained on the same data type, indicating that the choice of model yields considerable variation in brain-predicted age. Furthermore, in three datasets, regularized linear regression algorithms achieved similar performance to nonlinear and ensemble algorithms. Our results suggest that regularized linear algorithms are as effective as nonlinear and ensemble algorithms for brain age prediction, while significantly reducing computational costs. Our findings can serve as a starting point and quantitative reference for future efforts at improving brain age prediction using machine learning models applied to brain morphometric data.

A domain adaptation benchmark for T1-weighted brain magnetic resonance image segmentation

Accurate brain segmentation is critical for magnetic resonance imaging (MRI) analysis pipelines. Machine-learning-based brain MR image segmentation methods are among the state-of-the-art techniques for this task. Nevertheless, the segmentations produced by machine learning models often degrade in the presence of expected domain shifts between the test and train sets data distributions. These domain shifts are expected due to several factors, such as scanner hardware and software differences, technology updates, and differences in MRI acquisition parameters. Domain adaptation (DA) methods can make machine learning models more resilient to these domain shifts. This paper proposes a benchmark for investigating DA techniques for brain MR image segmentation using data collected across sites with scanners from different vendors (Philips, Siemens, and General Electric). Our work provides labeled data, publicly available source code for a set of baseline and DA models, and a benchmark for assessing different brain MR image segmentation techniques. We applied the proposed benchmark to evaluate two segmentation tasks: skull-stripping; and white-matter, gray-matter, and cerebrospinal fluid segmentation, but the benchmark can be extended to other brain structures. Our main findings during the development of this benchmark are that there is not a single DA technique that consistently outperforms others, and hyperparameter tuning and computational times for these methods still pose a challenge before broader adoption of these methods in the clinical practice.

Geometric deep learning reveals a structuro-temporal understanding of healthy and pathologic brain aging

Background

Brain age has historically been investigated primarily at the whole brain level. The ability to deconstruct the brain into its composite parts and explore brain age at the sub-structure level offers unique advantages. These include the exploration of dynamic and interconnected relationships between different brain structures in healthy and pathologic aging. To achieve this, individual brain structures can be rendered as surface representations on which morphologic analysis is carried out. Combining the advantages of deep learning with the strengths of surface analysis, we investigate the aging process at the individual structure level with the hypothesis being that pathologic aging does not uniformly affect the aging process of individual structures.

Methods

MRI data, age at scan time and diagnosis of dementia were collected from seven publicly available data repositories. The data from 17,440 unique subjects were collected, representing a total of 26,276 T1-weighted MRI accounting for longitudinal acquisitions. Surfaces were extracted for the cortex and seven subcortical structures. Deep learning networks were trained to estimate a subject's age either using several structures together or a single structure. We conducted a cross-sectional analysis to assess the difference between the predicted and actual ages for all structures between healthy subjects, individuals with mild cognitive impairment (MCI) or Alzheimer's disease dementia (ADD). We then performed a longitudinal analysis to assess the difference in the aging pace for each structure between stable healthy controls and healthy controls converting to either MCI or ADD.

Findings

Using an independent cohort of healthy subjects, age was well estimated for all structures. Cross-sectional analysis identified significantly larger predicted age for all structures in patients with either MCI and ADD compared to healthy subjects. Longitudinal analysis revealed varying degrees of involvement of individual subcortical structures for both age difference across groups and aging pace across time. These findings were most notable in the whole brain, cortex, hippocampus and amygdala.

Conclusion

Although similar patterns of abnormal aging were found related to MCI and ADD, the involvement of individual subcortical structures varied greatly and was consistently more pronounced in ADD patients compared to MCI patients.

What do neuroanatomical networks reveal about the ontology of human cognitive abilities?

Over the last decades, cognitive psychology has come to a fair consensus about the human intelligence ontological structure. However, it remains an open question whether anatomical properties of the brain support the same ontology. The present study explored the ontological structure derived from neuroanatomical networks associated with performance on 15 cognitive tasks indicating various abilities. Results suggest that the brain-derived (neurometric) ontology partly agrees with the cognitive performance-derived (psychometric) ontology complemented with interpretable differences. Moreover, the cortical areas associated with different inferred abilities are segregated, with little or no overlap. Nevertheless, these spatially segregated cortical areas are integrated via denser white matter structural connections as compared with the general brain connectome. The integration of ability-related cortical networks constitutes a neural counterpart to the psychometric construct of general intelligence, while the consistency and difference between psychometric and neurometric ontologies represent crucial pieces of knowledge for theory building, clinical diagnostics, and treatment.

•

Psychometric and neurometric cognitive ontologies are partly equivalent

•

Ability-related brain areas are ontologically segregated with little to no overlap

•

However, ability-related brain areas are densely interconnected by fiber tracts

Deformation Fields: A new source of information to predict Brain Age

OBJECTIVE

The modelling of healthy ageing critically requires the identification of methods that detect subtle changes in this process. In the last few years multiple machine learning models have been proposed that learn age patterns from Magnetic Resonance Images (MRI). Current standard information sources rely on local volumetric information of brain tissues, namely white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF). Information about patterns of brain deformation remains underexplored. In this paper an assessment is performed to understand better the predictive value of the deformation fields.

APPROACH

A shallow approach was used to compare the predictive value of deformation fields with the brain tissues (GM, WM and CSF). Images were compressed into a lower dimension space using Principal Components Analysis and then, a Relevant Vector Regression (RVR) learned the age patterns from the components. A model was trained per modality (deformation fields, GM, WM and CSF) and the performance between the models was compared. To evaluate whether the deformation fields increased the predictive power of GM, a model fusion approach was explored in which the final estimator was an RVR. Each model was validated using a cross-validation approach and was also evaluated on an external dataset.

MAIN RESULTS

We found that models trained with deformation patterns have higher predictive value than the ones trained with WM or CSF. Furthermore, deformation fields had a significantly better performance on the test set and also yield the lower difference between the validation and test set. Moreover, the predictions based on the combination of deformation patterns with GM volume yields better results than GM volumetric information alone.

SIGNIFICANCE

These findings suggest that deformation fields have a higher predictive power than WM and CSF and are robustly invariant across a set of confounding variables. Therefore, deformation fields should be considered in BrainAge models.

Brain age estimation using multi-feature-based networks

Studying brain aging improves our understanding in differentiating typical and atypical aging. Directly utilizing traditional morphological features for brain age estimation did not show significant performance in healthy controls (HCs), which may be due to the negligence of the information of structural similarities among cortical regions. For this issue, the multi-feature-based network (MFN) built upon morphological features can be employed to describe these similarities. Based on this, we hypothesized that the MFN is more efficient and robust than traditional morphological features in brain age estimating. In this work, we used six different types of morphological features (i.e., cortical volume, cortical thickness, curvature index, folding index, local gyrification index, and surface area) to build individual MFN for brain age estimation. The efficacy of MFN was estimated on 2501 HCs with T1-weighted structural magnetic resonance imaging (sMRI) data and compared with traditional morphological features. We attained a mean absolute error (MAE) of 3.73 years using the proposed method on an independent test set, whereas a mean absolute error of 5.30 years was derived from morphological features. Our experimental results demonstrated that the MFN is an efficient and robust metric for estimating brain age.

Multimodal Magnetic Resonance Imaging Reveals Aberrant Brain Age Trajectory During Youth in Schizophrenia Patients

Accelerated brain aging had been widely reported in patients with schizophrenia (SZ). However, brain aging trajectories in SZ patients have not been well-documented using three-modal magnetic resonance imaging (MRI) data. In this study, 138 schizophrenia patients and 205 normal controls aged 20–60 were included and multimodal MRI data were acquired for each individual, including structural MRI, resting state-functional MRI and diffusion tensor imaging. The brain age of each participant was estimated by features extracted from multimodal MRI data using linear multiple regression. The correlation between the brain age gap and chronological age in SZ patients was best fitted by a positive quadratic curve with a peak chronological age of 47.33 years. We used the peak to divide the subjects into a youth group and a middle age group. In the normal controls, brain age matched chronological age well for both the youth and middle age groups, but this was not the case for schizophrenia patients. More importantly, schizophrenia patients exhibited increased brain age in the youth group but not in the middle age group. In this study, we aimed to investigate brain aging trajectories in SZ patients using multimodal MRI data and revealed an aberrant brain age trajectory in young schizophrenia patients, providing new insights into the pathophysiological mechanisms of schizophrenia.

Multimodal biological brain age prediction using magnetic resonance imaging and angiography with the identification of predictive regions

Biological brain age predicted using machine learning models based on high-resolution imaging data has been suggested as a potential biomarker for neurological and cerebrovascular diseases. In this work, we aimed to develop deep learning models to predict the biological brain age using structural magnetic resonance imaging and angiography datasets from a large database of 2074 adults (21-81 years). Since different imaging modalities can provide complementary information, combining them might allow to identify more complex aging patterns, with angiography data, for instance, showing vascular aging effects complementary to the atrophic brain tissue changes seen in T1-weighted MRI sequences. We used saliency maps to investigate the contribution of cortical, subcortical, and arterial structures to the prediction. Our results show that combining T1-weighted and angiography MR data led to a significantly improved brain age prediction accuracy, with a mean absolute error of 3.85 years comparing the predicted and chronological age. The most predictive brain regions included the lateral sulcus, the fourth ventricle, and the amygdala, while the brain arteries contributing the most to the prediction included the basilar artery, the middle cerebral artery M2 segments, and the left posterior cerebral artery. Our study proposes a framework for brain age prediction using multimodal imaging, which gives accurate predictions and allows identifying the most predictive regions for this task, which can serve as a surrogate for the brain regions that are most affected by aging.

The accuracy of T1-weighted voxel-wise and region-wise metrics for brain age estimation

INTRODUCTION

The brain age score has recently been introduced for robust monitoring of brain morphological alterations throughout the lifespan, prediction of mortality risk, and early detection of neurological disorders.

METHODS

We assessed the brain age prediction accuracy of the widely used T1-weighted voxel-wise and region-wise metrics (i.e., T1-weighted magnetic resonance imaging [MRI]-wise metrics)) separately and their integration. We assessed 788 healthy individuals (age, 18-94 years) in a training set to build a brain age estimation framework based on different T1-weighted MRI-wise metrics (15 different metrics in total) and then validated each T1-weighted MRI-wise metric in an independent test set comprising 88 healthy individuals. We also assessed the accuracy of each T1-weighted MRI-wise metric in a clinical set of 70 patients with mild cognitive impairment and another of 30 patients with Alzheimer's disease.

RESULTS

Integration of gray matter voxel-wise maps and all region-wise metrics achieved the highest brain age prediction accuracy (mean absolute error, 4.63 years). These metrics on their own achieved lower accuracy (mean absolute error, 4.97 years and 5.75 years, respectively).

DISCUSSION

For tracing brain atrophy levels in neurological disorders at the clinical level, integration of voxel-wise and region-wise metrics may contribute to a more sensitive brain age framework than when these metrics are used on their own.

The "cognitive clock": A novel indicator of brain health

INTRODUCTION

We identified a "cognitive clock," a novel indicator of brain health that provides person-specific estimates of cognitive age, and tested the hypothesis that cognitive age is a better predictor of brain health than chronological age in two independent datasets.

METHODS

The initial analyses were based on 1057 participants from the Rush Memory and Aging Project and the Religious Orders Study who began without impairment and underwent cognitive assessments up to 24 years. A shape invariant model characterized the latent pattern of cognitive decline, conceptualized here as the "cognitive clock," and yielded person-specific estimates of cognitive age. Survival analyses examined cognitive versus chronological age for predicting Alzheimer's disease dementia, mild cognitive impairment and mortality, and regression analyses examined associations of cognitive versus chronological age with neuropathology and brain atrophy. Finally, we applied the cognitive clock to an independent validation sample of 2592 participants from the Chicago Health and Aging Project, a biracial population-based study, to confirm the predictive utility of cognitive age.

RESULTS

The "cognitive clock" showed that cognition remained stable until a cognitive age of about 80, then declined moderately until 90, then declined precipitously. In the initial dataset, cognitive age was a better predictor of dementia, mild cognitive impairment and mortality than chronological age, and was more strongly associated with neuropathology and brain atrophy. Application of the cognitive clock to the independent validation sample provided further support for the utility of cognitive age as a strong prognostic indicator of adverse outcomes.

DISCUSSION

Cognitive age is a robust prognostic indicator of adverse health outcomes and may serve as a useful biomarker in aging research.

Machine learning for brain age prediction: Introduction to methods and clinical applications

The rise of machine learning has unlocked new ways of analysing structural neuroimaging data, including brain age prediction. In this state-of-the-art review, we provide an introduction to the methods and potential clinical applications of brain age prediction. Studies on brain age typically involve the creation of a regression machine learning model of age-related neuroanatomical changes in healthy people. This model is then applied to new subjects to predict their brain age. The difference between predicted brain age and chronological age in a given individual is known as ‘brain-age gap’. This value is thought to reflect neuroanatomical abnormalities and may be a marker of overall brain health. It may aid early detection of brain-based disorders and support differential diagnosis, prognosis, and treatment choices. These applications could lead to more timely and more targeted interventions in age-related disorders.

MRI of healthy brain aging: A review

We present a review of the characterization of healthy brain aging using MRI with an emphasis on morphology, lesions, and quantitative MR parameters. A scope review found 6612 articles encompassing the keywords "Brain Aging" and "Magnetic Resonance"; papers involving functional MRI or not involving imaging of healthy human brain aging were discarded, leaving 2246 articles. We first consider some of the biogerontological mechanisms of aging, and the consequences of aging in terms of cognition and onset of disease. Morphological changes with aging are reviewed for the whole brain, cerebral cortex, white matter, subcortical gray matter, and other individual structures. In general, volume and cortical thickness decline with age, beginning in mid-life. Prevalent silent lesions such as white matter hyperintensities, microbleeds, and lacunar infarcts are also observed with increasing frequency. The literature regarding quantitative MR parameter changes includes T₁ , T₂ , T₂ *, magnetic susceptibility, spectroscopy, magnetization transfer, diffusion, and blood flow. We summarize the findings on how each of these parameters varies with aging. Finally, we examine how the aforementioned techniques have been used for age prediction. While relatively large in scope, we present a comprehensive review that should provide the reader with sound understanding of what MRI has been able to tell us about how the healthy brain ages.

Geometric deep learning on brain shape predicts sex and age

The complex relationship between the shape and function of the human brain remains elusive despite extensive studies of cortical folding over many decades. The analysis of cortical gyrification presents an opportunity to advance our knowledge about this relationship, and better understand the etiology of a variety of pathologies involving diverse degrees of cortical folding abnormalities. Hypothesis-driven surface-based approaches have been shown to be particularly efficient in their ability to accurately describe unique features of the folded sheet topology of the cortical ribbon. However, the utility of these approaches has been blunted by their reliance on manually defined features aiming to capture the relevant geometric properties of cortical folding. In this paper, we propose an entirely novel, data-driven deep-learning based method to analyze the brain's shape that eliminates this reliance on manual feature definition. This method builds on the emerging field of geometric deep-learning and uses traditional convolutional neural network architecture uniquely adapted to the surface representation of the cortical ribbon. This method is a complete departure from prior brain MRI CNN investigations, all of which have relied on three dimensional MRI data and interpreted features of the MRI signal for prediction. MRI data from 6410 healthy subjects obtained from 11 publicly available data repositories were used for analysis. Ages ranged from 6 to 89 years. Both inner and outer cortical surfaces were extracted using Freesurfer and then registered into MNI space. For purposes of method development, both a classification and regression challenge were introduced for network learning including sex and age prediction, respectively. Two independent graph convolutional neural networks (gCNNs) were trained, the first of which to predict subject's self-identified sex, the second of which to predict subject's age. Class Activation Maps (CAM) and Regression Activation Maps (RAM) were constructed respectively to map the topographic distribution of the most influential brain regions involved in the decision process for each gCNN. Using this approach, the gCNN was able to predict a subject's sex with an average accuracy of 87.99 % and achieved a Person's coefficient of correlation of 0.93 with an average absolute error 4.58 years when predicting a subject's age. We believe this shape-based convolutional classifier offers a novel, data-driven approach to define biomedically relevant features from the brain at both the population and single subject levels and therefore lays a critical foundation for future precision medicine applications.

Predicting brain age using machine learning algorithms: A comprehensive evaluation

Machine learning (ML) algorithms play a vital role in brain age estimation frameworks. The impact of regression algorithms on prediction accuracy in the brain age estimation frameworks have not been comprehensively evaluated. Here, we sought to assess the efficiency of different regression algorithms on brain age estimation. To this end, we built a brain age estimation framework based on a large set of cognitively healthy (CH) individuals (N = 788) as a training set followed by different regression algorithms (18 different algorithms in total). We then quantified each regression-algorithm on independent test sets composed of 88 CH individuals, 70 mild cognitive impairment patients as well as 30 Alzheimers disease patients. The prediction accuracy in the independent test set (i.e., CH set) varied in regression algorithms (mean absolute error (MAE) from 4.63 to 7.14 yrs, R2 from 0.76 to 0.88). The highest and lowest prediction accuracies were achieved by Quadratic Support Vector Regression algorithm (MAE = 4.63 yrs, R2 = 0.88, 95% CI = [-1.26, 1.42]) and Binary Decision Tree algorithm (MAE = 7.14 yrs, R2 = 0.76, 95% CI = [-1.50, 2.62]), respectively. Our experimental results demonstrate that prediction accuracy in brain age frameworks is affected by regression algorithms, indicating that advanced machine learning algorithms can lead to more accurate brain age predictions in clinical settings.

Accelerated aging in the brain, epigenetic aging in blood, and polygenic risk for schizophrenia

Schizophrenia patients show signs of accelerated aging in cognitive and physiological domains. Both schizophrenia and accelerated aging, as measured by MRI brain images and epigenetic clocks, are correlated with increased mortality. However, the association between these aging measures have not yet been studied in schizophrenia patients. In schizophrenia patients and healthy subjects, accelerated aging was assessed in brain tissue using a longitudinal MRI (N = 715 scans; mean scan interval 3.4 year) and in blood using two epigenetic age clocks (N = 172). Differences ('gaps') between estimated ages and chronological ages were calculated, as well as the acceleration rate of brain aging. The correlations between these aging measures as well as with polygenic risk scores for schizophrenia (PRS; N = 394) were investigated. Brain aging and epigenetic aging were not significantly correlated. Polygenic risk for schizophrenia was significantly correlated with brain age gap, brain age acceleration rate, and negatively correlated with DNAmAge gap, but not with PhenoAge gap. However, after controlling for disease status and multiple comparisons correction, these effects were no longer significant. Our results imply that the (accelerated) aging observed in the brain and blood reflect distinct biological processes. Our findings will require replication in a larger cohort.

Brain age prediction in schizophrenia: Does the choice of machine learning algorithm matter?

Brain-predicted age difference (brainPAD) has been used in schizophrenia to assess individual-level deviation in the biological age of the patients' brain (i.e., brain-age) from normative reference brain structural datasets. There is marked inter-study variation in brainPAD in schizophrenia which is commonly attributed to sample heterogeneity. However, the potential contribution of the different machine learning algorithms used for brain-age estimation has not been systematically evaluated. Here, we aimed to assess variation in brain-age estimated by six commonly used algorithms [ordinary least squares regression, ridge regression, least absolute shrinkage and selection operator regression, elastic-net regression, linear support vector regression, and relevance vector regression] when applied to the same brain structural features from the same sample. To assess reproducibility we used data from two publically available samples of healthy individuals (n = 1092 and n = 492) and two further samples, from the Icahn School of Medicine at Mount Sinai (ISMMS) and the Center of Biomedical Research Excellence (COBRE), comprising both patients with schizophrenia (n = 90 and n = 76) and healthy individuals (n = 200 and n = 87). Performance similarity across algorithms was compared within each sample using correlation analyses and hierarchical clustering. Across all samples ordinary least squares regression, the only algorithm without a penalty term, performed markedly worse. All other algorithms showed comparable performance but they still yielded variable brain-age estimates despite being applied to the same data. Although brainPAD was consistently higher in patients with schizophrenia, it varied by algorithm from 3.8 to 5.2 years in the ISMMS sample and from to 4.5 to 11.7 years in the COBRE sample. Algorithm choice introduces variations in brain-age and may confound inter-study comparisons when assessing brainPAD in schizophrenia.

Individual variation underlying brain age estimates in typical development

Typical brain development follows a protracted trajectory throughout childhood and adolescence. Deviations from typical growth trajectories have been implicated in neurodevelopmental and psychiatric disorders. Recently, the use of machine learning algorithms to model age as a function of structural or functional brain properties has been used to examine advanced or delayed brain maturation in healthy and clinical populations. Termed 'brain age', this approach often relies on complex, nonlinear models that can be difficult to interpret. In this study, we use model explanation methods to examine the cortical features that contribute to brain age modelling on an individual basis. In a large cohort of n = 768 typically-developing children (aged 3-21 years), we build models of brain development using three different machine learning approaches. We employ SHAP, a model-agnostic technique to identify sample-specific feature importance, to identify regional cortical metrics that explain errors in brain age prediction. We find that, on average, brain age prediction and the cortical features that explain model predictions are consistent across model types and reflect previously reported patterns of regions brain development. However, while several regions are found to contribute to brain age prediction error, we find little spatial correspondence between individual estimates of feature importance, even when matched for age, sex and brain age prediction error. We also find no association between brain age error and cognitive performance in this typically-developing sample. Overall, this study shows that, while brain age estimates based on cortical development are relatively robust and consistent across model types and preprocessing strategies, significant between-subject variation exists in the features that explain erroneous brain age predictions on an individual level.

Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data

Brain morphology varies across the ageing trajectory and the prediction of a person's age using brain features can aid the detection of abnormalities in the ageing process. Existing studies on such “brain age prediction” vary widely in terms of their methods and type of data, so at present the most accurate and generalisable methodological approach is unclear. Therefore, we used the UK Biobank data set (N = 10,824, age range 47–73) to compare the performance of the machine learning models support vector regression, relevance vector regression and Gaussian process regression on whole‐brain region‐based or voxel‐based structural magnetic resonance imaging data with or without dimensionality reduction through principal component analysis. Performance was assessed in the validation set through cross‐validation as well as an independent test set. The models achieved mean absolute errors between 3.7 and 4.7 years, with those trained on voxel‐level data with principal component analysis performing best. Overall, we observed little difference in performance between models trained on the same data type, indicating that the type of input data had greater impact on performance than model choice. All code is provided online in the hope that this will aid future research.

Improving Individual Brain Age Prediction Using an Ensemble Deep Learning Framework

Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R ² = 0.88; support vector regression, MAE = 4.42 years, R ² = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R ² = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.

Disentangled-Multimodal Adversarial Autoencoder: Application to Infant Age Prediction With Incomplete Multimodal Neuroimages

Effective fusion of structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) data has the potential to boost the accuracy of infant age prediction thanks to the complementary information provided by different imaging modalities. However, functional connectivity measured by fMRI during infancy is largely immature and noisy compared to the morphological features from sMRI, thus making the sMRI and fMRI fusion for infant brain analysis extremely challenging. With the conventional multimodal fusion strategies, adding fMRI data for age prediction has a high risk of introducing more noises than useful features, which would lead to reduced accuracy than that merely using sMRI data. To address this issue, we develop a novel model termed as disentangled-multimodal adversarial autoencoder (DMM-AAE) for infant age prediction based on multimodal brain MRI. Specifically, we disentangle the latent variables of autoencoder into common and specific codes to represent the shared and complementary information among modalities, respectively. Then, cross-reconstruction requirement and common-specific distance ratio loss are designed as regularizations to ensure the effectiveness and thoroughness of the disentanglement. By arranging relatively independent autoencoders to separate the modalities and employing disentanglement under cross-reconstruction requirement to integrate them, our DMM-AAE method effectively restrains the possible interference cross modalities, while realizing effective information fusion. Taking advantage of the latent variable disentanglement, a new strategy is further proposed and embedded into DMM-AAE to address the issue of incompleteness of the multimodal neuroimages, which can also be used as an independent algorithm for missing modality imputation. By taking six types of cortical morphometric features from sMRI and brain functional connectivity from fMRI as predictors, the superiority of the proposed DMM-AAE is validated on infant age (35 to 848 days after birth) prediction using incomplete multimodal neuroimages. The mean absolute error of the prediction based on DMM-AAE reaches 37.6 days, outperforming state-of-the-art methods. Generally, our proposed DMM-AAE can serve as a promising model for prediction with multimodal data.

Patch-wise brain age longitudinal reliability

We recently introduced a patch‐wise technique to estimate brain age from anatomical T1‐weighted magnetic resonance imaging (T1w MRI) data. Here, we sought to assess its longitudinal reliability by leveraging a unique dataset of 99 longitudinal MRI scans from a single, cognitively healthy volunteer acquired over a period of 17 years (aged 29–46 years) at multiple sites. We built a robust patch‐wise brain age estimation framework on the basis of 100 cognitively healthy individuals from the MindBoggle dataset (aged 19–61 years) using the Desikan‐Killiany‐Tourville atlas, then applied the model to the volunteer dataset. The results show a high prediction accuracy on the independent test set (R² = .94, mean absolute error of 0.63 years) and no statistically significant difference between manufacturers, suggesting that the patch‐wise technique has high reliability and can be used for longitudinal multi‐centric studies.

Are language skills related to structural features in Broca's and Wernicke's area?

This study used structural magnetic resonance imaging to examine whether specific anatomical features of Broca's and Wernicke's areas are related to language functions in typically developing older subjects with no specific language expertize. Data from 231 subjects from the Zurich LHAB-study are used for this study. For these subjects, we obtained several psychometric measures from which we calculated performance measures reflecting specific psychological functions (language comprehension, verbal fluency, perceptual speed, visual memory, recognition of regularities, and logical thinking). From the MRI measurements, we calculated the cortical thickness and cortical surface of Broca's and Wernicke's areas. Applying multiple regression analyses, we identified a moderately strong relationship between language comprehension and the brain metrics from Broca's and Wernicke's areas and showed that approximately 10% of the variance in language comprehension performance is explained by the linear combination of all perisylvian brain metrics. The other psychological functions (verbal fluency, perceptual speed, visual memory, recognition of regularities, and logical thinking) are not related to these brain metrics. Subsequent detailed analyses revealed that the cortical thickness of Wernicke's area, in particular, contributed most to this structure-function relationship. The better performance in the language comprehension tests was related to a thicker cortex in Wernicke's area. Thus, this study demonstrates a structure-function relationship between the anatomical features of the perisylvian language areas and language comprehension, suggesting that particular anatomical features are associated with better language performance.

Supervised machine learning tools: a tutorial for clinicians

In an increasingly data-driven world, artificial intelligence is expected to be a key tool for converting big data into tangible benefits and the healthcare domain is no exception to this. Machine learning aims to identify complex patterns in multi-dimensional data and use these uncovered patterns to classify new unseen cases or make data-driven predictions. In recent years, deep neural networks have shown to be capable of producing results that considerably exceed those of conventional machine learning methods for various classification and regression tasks. In this paper, we provide an accessible tutorial of the most important supervised machine learning concepts and methods, including deep learning, which are potentially the most relevant for the medical domain. We aim to take some of the mystery out of machine learning and depict how machine learning models can be useful for medical applications. Finally, this tutorial provides a few practical suggestions for how to properly design a machine learning model for a generic medical problem.

An automated machine learning approach to predict brain age from cortical anatomical measures

The use of machine learning (ML) algorithms has significantly increased in neuroscience. However, from the vast extent of possible ML algorithms, which one is the optimal model to predict the target variable? What are the hyperparameters for such a model? Given the plethora of possible answers to these questions, in the last years, automated ML (autoML) has been gaining attention. Here, we apply an autoML library called Tree-based Pipeline Optimisation Tool (TPOT) which uses a tree-based representation of ML pipelines and conducts a genetic programming-based approach to find the model and its hyperparameters that more closely predicts the subject's true age. To explore autoML and evaluate its efficacy within neuroimaging data sets, we chose a problem that has been the focus of previous extensive study: brain age prediction. Without any prior knowledge, TPOT was able to scan through the model space and create pipelines that outperformed the state-of-the-art accuracy for Freesurfer-based models using only thickness and volume information for anatomical structure. In particular, we compared the performance of TPOT (mean absolute error [MAE]: 4.612 ± .124 years) and a relevance vector regression (MAE 5.474 ± .140 years). TPOT also suggested interesting combinations of models that do not match the current most used models for brain prediction but generalise well to unseen data. AutoML showed promising results as a data-driven approach to find optimal models for neuroimaging applications.

From a deep learning model back to the brain-Identifying regional predictors and their relation to aging

We present a Deep Learning framework for the prediction of chronological age from structural magnetic resonance imaging scans. Previous findings associate increased brain age with neurodegenerative diseases and higher mortality rates. However, the importance of brain age prediction goes beyond serving as biomarkers for neurological disorders. Specifically, utilizing convolutional neural network (CNN) analysis to identify brain regions contributing to the prediction can shed light on the complex multivariate process of brain aging. Previous work examined methods to attribute pixel/voxel-wise contributions to the prediction in a single image, resulting in "explanation maps" that were found noisy and unreliable. To address this problem, we developed an inference scheme for combining these maps across subjects, thus creating a population-based, rather than a subject-specific map. We applied this method to a CNN ensemble trained on predicting subjects' age from raw T1 brain images in a lifespan sample of 10,176 subjects. Evaluating the model on an untouched test set resulted in mean absolute error of 3.07 years and a correlation between chronological and predicted age of r = 0.98. Using the inference method, we revealed that cavities containing cerebrospinal fluid, previously found as general atrophy markers, had the highest contribution for age prediction. Comparing maps derived from different models within the ensemble allowed to assess differences and similarities in brain regions utilized by the model. We showed that this method substantially increased the replicability of explanation maps, converged with results from voxel-based morphometry age studies and highlighted brain regions whose volumetric variability correlated the most with the prediction error.