The Developmental Brain Age Is Associated With Adversity, Depression, and Functional Outcomes Among Adolescents

Open AccessPublished:September 20, 2021DOI:https://doi.org/10.1016/j.bpsc.2021.09.004

      Abstract

      Background

      Most psychiatric disorders emerge in the second decade of life. In the present study, we examined whether environmental adversity, developmental antecedents, major depressive disorder, and functional impairment correlate with deviation from normative brain development in adolescence.

      Methods

      We trained a brain age prediction model using 189 structural magnetic resonance imaging brain features in 1299 typically developing adolescents (age range 9–19 years, mean = 13.5, SD = 3.04), validated the model in a holdout set of 322 adolescents (mean = 13.5, SD = 3.07), and used it to predict age in an independent risk-enriched cohort of 150 adolescents (mean = 13.6, SD = 2.82). We tested associations between the brain age gap and adversity, early antecedents, depression, and functional impairment.

      Results

      We accurately predicted chronological age in typically developing adolescents (mean absolute error = 1.53 years). The model generalized to the validation set (mean absolute error = 1.55 years, 1.98 bias adjusted) and to the independent at-risk sample (mean absolute error = 1.49 years, 1.86 bias adjusted). The brain age estimate was reliable in repeated scans (intraclass correlation = 0.94). Experience of environmental adversity (β = 0.18; 95% CI, 0.04 to 0.31; p = .02), diagnosis of major depressive disorder (β = 0.61; 95% CI, 0.23 to 0.99; p = .01), and functional impairment (β = 0.16; 95% CI, 0.05 to 0.27; p = .01) were associated with a positive brain age gap.

      Conclusions

      Risk factors, diagnosis, and impact of mental illness are associated with an older-appearing brain during development.

      Keywords

      Most psychiatric disorders emerge in the first 2 decades of life (
      • Kessler R.C.
      • Berglund P.
      • Demler O.
      • Jin R.
      • Merikangas K.R.
      • Walters E.E.
      Lifetime prevalence and age-of-onset distributions of DSM-IV disorders in the National Comorbidity Survey Replication.
      ,
      • Caspi A.
      • Houts R.M.
      • Ambler A.
      • Danese A.
      • Elliott M.L.
      • Hariri A.
      • et al.
      Longitudinal assessment of mental health disorders and comorbidities across 4 decades among participants in the Dunedin Birth Cohort Study.
      ). The highest risk of mental illness onset coincides with a period of rapid brain development. Cortical gray matter volume shows a nonlinear decline during adolescence, driven by reductions in cortical thickness and surface area (
      • Tamnes C.K.
      • Herting M.M.
      • Goddings A.L.
      • Meuwese R.
      • Blakemore S.J.
      • Dahl R.E.
      • et al.
      Development of the cerebral cortex across adolescence: A multisample study of inter-related longitudinal changes in cortical volume, surface area, and thickness.
      ,
      • Walhovd K.B.
      • Fjell A.M.
      • Giedd J.
      • Dale A.M.
      • Brown T.T.
      Through thick and thin: A need to reconcile contradictory results on trajectories in human cortical development.
      ). Cortical white matter volume increases from childhood until mid- to late adolescence (
      • Mills K.L.
      • Goddings A.L.
      • Herting M.M.
      • Meuwese R.
      • Blakemore S.J.
      • Crone E.A.
      • et al.
      Structural brain development between childhood and adulthood: Convergence across four longitudinal samples.
      ). Aberrations or exaggerations of these typical developmental changes are likely related to the etiology of mental illness (
      • Huttenlocher P.R.
      • Dabholkar A.S.
      Regional differences in synaptogenesis in human cerebral cortex.
      ,
      • Paus T.
      • Keshavan M.
      • Giedd J.N.
      Why do many psychiatric disorders emerge during adolescence?.
      ,
      • Whitaker K.J.
      • Vértes P.E.
      • Romero-Garcia R.
      • Váša F.
      • Moutoussis M.
      • Prabhu G.
      • et al.
      Adolescence is associated with genomically patterned consolidation of the hubs of the human brain connectome.
      ). Thus, it is paramount to determine how biological and environmental factors impact developmental trajectories (
      • Casey B.J.
      • Cannonier T.
      • Conley M.I.
      • Cohen A.O.
      • Barch D.M.
      • Heitzeg M.M.
      • et al.
      The Adolescent Brain Cognitive Development (ABCD) study: Imaging acquisition across 21 sites.
      ). Deviation from expected trajectories can be captured with an innovative approach capable of assessing neuroanatomical maturity (
      • Franke K.
      • Luders E.
      • May A.
      • Wilke M.
      • Gaser C.
      Brain maturation: Predicting individual BrainAGE in children and adolescents using structural MRI.
      ,
      • Brown T.T.
      • Kuperman J.M.
      • Chung Y.
      • Erhart M.
      • McCabe C.
      • Hagler Jr., D.J.
      • et al.
      Neuroanatomical assessment of biological maturity.
      ,
      • Chung Y.
      • Addington J.
      • Bearden C.E.
      • Cadenhead K.
      • Cornblatt B.
      • Mathalon D.H.
      • et al.
      Use of machine learning to determine deviance in neuroanatomical maturity associated with future psychosis in youths at clinically high risk.
      ).
      Advances in machine learning (ML) algorithms combined with the availability of large open-access databases of brain scans have made it possible to predict a person’s age from their magnetic resonance imaging (MRI) data (
      • Cole J.H.
      • Franke K.
      Predicting age using neuroimaging: Innovative brain ageing biomarkers.
      ). By analyzing scans from typically developing individuals, ML determines the relationship between neuroanatomy and chronological age, across the age range, thereby mapping normative developmental trajectories. The ML algorithm is then able to make brain age predictions on new, previously unseen data. The difference between a person’s predicted brain age and their chronological age results in the brain age gap (
      • Franke K.
      • Gaser C.
      Ten years of BrainAGE as a neuroimaging biomarker of brain aging: What insights have we gained?.
      ). A wide gap suggests deviation from a normative brain developmental trajectory (Figure 1A).
      Figure thumbnail gr1
      Figure 1Brain age prediction and data partitioning. (A) Brain age prediction scatterplot. The diagonal line represents perfect prediction accuracy. Dots represent individual age predictions from structural magnetic resonance imaging. Dots above the line represent predicted age older than chronological age. Dots below the line represent a prediction of a younger-appearing brain. (B) Age and sex distributions of all datasets. (C) Data splits representing training, validation, and testing data. Typically developing control participants used for model training and validation. Trained model applied in independent at-risk sample (Families Overcoming Risks and Building Opportunities for Well-being [FORBOW]). ABIDE, Autism Brain Imaging Data Exchange; CMI, Child Mind Institute: Healthy Brain Network; CORR, Consortium for Reliability and Reproducibility; CV, cross-validation; NIH, The NIH MRI Study of Normal Brain Development; PING, Pediatric Imaging, Neurocognition, and Genetics.
      A positive brain age gap, suggestive of an older-appearing brain, has been associated with cognitive impairment, traumatic brain injury, Alzheimer’s disease, and increased mortality (
      • Cole J.H.
      • Franke K.
      Predicting age using neuroimaging: Innovative brain ageing biomarkers.
      ,
      • Franke K.
      • Gaser C.
      Ten years of BrainAGE as a neuroimaging biomarker of brain aging: What insights have we gained?.
      ,
      • Cole J.H.
      • Ritchie S.J.
      • Bastin M.E.
      • Valdés Hernández M.C.
      • Muñoz Maniega S.
      • Royle N.
      • et al.
      Brain age predicts mortality.
      ) in adults. An increased brain age gap has also been associated with severe mental illness (SMI), including both mood (
      • Han L.K.M.
      • Dinga R.
      • Hahn T.
      • Ching C.R.K.
      • Eyler L.T.
      • Aftanas L.
      • et al.
      Brain aging in major depressive disorder: Results from the ENIGMA major depressive disorder working group.
      ) and psychotic (
      • Schnack H.G.
      • van Haren N.E.M.
      • Nieuwenhuis M.
      • Hulshoff Pol H.E.
      • Cahn W.
      • Kahn R.S.
      Accelerated brain aging in schizophrenia: A longitudinal pattern recognition study.
      ) disorders. A recent analysis of over 40,000 scans has revealed that clinical groups, including those with major depressive disorder (MDD), bipolar disorder, and schizophrenia, exhibited a positive brain age gap when compared with healthy control subjects (
      • Kaufmann T.
      • van der Meer D.
      • Doan N.T.
      • Schwarz E.
      • Lund M.J.
      • Agartz I.
      • et al.
      Common brain disorders are associated with heritable patterns of apparent aging of the brain.
      ). While the brain age concept is well established in adults, less is known about how the brain age gap relates to mental illness in adolescence.
      Prior work has established the validity of brain age prediction in the developmental context, with a reliable differentiation between age groups (childhood, early adolescence, middle adolescence, late adolescence) (
      • Franke K.
      • Luders E.
      • May A.
      • Wilke M.
      • Gaser C.
      Brain maturation: Predicting individual BrainAGE in children and adolescents using structural MRI.
      ,
      • Brown T.T.
      • Kuperman J.M.
      • Chung Y.
      • Erhart M.
      • McCabe C.
      • Hagler Jr., D.J.
      • et al.
      Neuroanatomical assessment of biological maturity.
      ). The brain age gap has been associated with cognitive performance in typically developing adolescents (
      • Lewis J.D.
      • Evans A.C.
      • Tohka J.
      Brain Development Cooperative Group, Pediatric Imaging, Neurocognition, and Genetics Study
      T1 white/gray contrast as a predictor of chronological age, and an index of cognitive performance.
      ). However, applications in mental health contexts have been more limited. Previous work suggests that a positive brain age gap relates to psychosis risk (
      • Chung Y.
      • Addington J.
      • Bearden C.E.
      • Cadenhead K.
      • Cornblatt B.
      • Mathalon D.H.
      • et al.
      Use of machine learning to determine deviance in neuroanatomical maturity associated with future psychosis in youths at clinically high risk.
      ). Preliminary evidence also suggests longitudinal changes in the brain age gap in MDD (
      • de Nooij L.
      • Harris M.A.
      • Hawkins E.L.
      • Clarke T.K.
      • Shen X.
      • Chan S.W.Y.
      • et al.
      Longitudinal trajectories of brain age in young individuals at familial risk of mood disorder from the Scottish Bipolar Family Study.
      ). Building on the prior literature, we wanted to examine whether the brain age gap may work as a general biomarker of deviation from typical development. To do that, we examined the association between the brain age gap and multiple adverse exposures and outcomes.
      In the present study we created a model optimized for predicting brain age in typically developing adolescents. We then applied the model in a high-risk sample of adolescents to calculate the brain age gap for each individual. Considering that there is no single indicator of ill mental health in the developmental context, we implemented a multiprong approach (
      • Polanczyk G.
      • Moffitt T.E.
      • Arseneault L.
      • Cannon M.
      • Ambler A.
      • Keefe R.S.E.
      • et al.
      Etiological and clinical features of childhood psychotic symptoms: Results from a birth cohort.
      ). First, we examined the association between multiple negative environmental factors, such as low socioeconomic status and maltreatment, and the brain age gap. Second, we investigated the association between early transdiagnostic symptoms for mental illness and the brain age gap. Third, we examined whether presence of MDD was associated with a wider brain age gap. Finally, we tested the relationship between functional impairment and the brain age gap. Given the prior evidence, we expected that all indicators would reflect in a positive brain age gap.

      Methods and Materials

       Samples

      The current study includes data collected through data sharing platforms as well as an in-house cohort (Families Overcoming Risks and Building Opportunities for Well-being [FORBOW]). Table 1 provides detailed characteristics of each cohort. The study protocol was approved by the Research Ethics Board at Nova Scotia Health. Each cohort collected data with the participants’ informed consent and approval by local institutional review and ethics boards. Inclusion criteria for all cohorts included participants ages 9–19 years, passing automated MRI quality control. Figure 1B shows sample size, age, and sex distribution of the included cohorts. To model normative development, the training and validation sets (Figure 1C) only included control participants free from psychiatric disorders, with IQ above 75, where provided. An independent cohort (FORBOW), enriched for risk for mental illness, was used for hypothesis testing. FORBOW inclusion criterion was age 9–19 to capture development during adolescence. FORBOW exclusion criteria were 1) personal history of psychotic illness or autism spectrum disorder, 2) any serious medical or neurologic disorders, 3) MRI contraindications, and 4) full-scale intelligence quotient below 75 on the Wechsler Abbreviated Scale of Intelligence (
      • Wechsler D.
      ). See Table S1 for FORBOW demographics.
      Table 1Summary of the Included Cohorts
      CohortDescriptionWebsiteAge, Years, Mean ± SDSex, Male, n (%)Reference
      ABIDEABIDE is a product of an international multisite collaboration, openly sharing neuroimaging data. We only included typically developing controls.http://preprocessed-connectomes-project.org/abide/13.38 ± 2.49183 (78%)Craddock et al. (
      • Craddock C.
      • Benhajali Y.
      • Chu C.
      • Chouinard F.
      • Evans A.
      • Jakab A.
      • et al.
      The neuro bureau preprocessing initiative: Open sharing of preprocessed neuroimaging data and derivatives.
      )
      ABIDE IIABIDE II has aggregated a significant number of additional datasets to promote discovery science.http://fcon_1000.projects.nitrc.org/indi/abide/abide_II.html11.64 ± 2.34163 (63%)Di Martino et al. (
      • Di Martino A.
      • O’Connor D.
      • Chen B.
      • Alaerts K.
      • Anderson J.S.
      • Assaf M.
      • et al.
      Enhancing studies of the connectome in autism using the autism brain imaging data exchange II.
      )
      CMIThe CMI has launched an ongoing initiative focused on collecting and sharing a large biobank of multimodal brain imaging data from New York City area youth.http://fcon_1000.projects.nitrc.org/indi/cmi_healthy_brain_network/sharing_neuro.html12.64 ± 2.6794 (53%)Alexander et al. (
      • Alexander L.M.
      • Escalera J.
      • Ai L.
      • Andreotti C.
      • Febre K.
      • Mangone A.
      • et al.
      An open resource for transdiagnostic research in pediatric mental health and learning disorders.
      )
      CoRRCoRR was created as an open science resource focused on test-retest reliability of MRI connectivity work. The data, including structural images, were gathered across the world and shared through the International Neuroimaging Data-sharing Initiative.http://fcon_1000.projects.nitrc.org/indi/CoRR/html15.39 ± 3.13193 (49%)Zuo et al. (
      • Zuo X.N.
      • Anderson J.S.
      • Bellec P.
      • Birn R.M.
      • Biswal B.B.
      • Blautzik J.
      • et al.
      An open science resource for establishing reliability and reproducibility in functional connectomics.
      )
      NIHThe NIH pediatric study utilized a uniform acquisition protocol and epidemiological sampling to form an MRI database of typically developing children. The data were shared with researchers and the clinical medicine community in the mid-2000s.https://www.bic.mni.mcgill.ca/nihpd_info/info2/data_access.html13.26 ± 2.8067 (42%)Evans and Brain Development Cooperative Group (
      • Evans A.C.
      Brain Development Cooperative Group
      The NIH MRI study of normal brain development.
      )
      PINGPING was tasked in creating a large repository of behavioral, imaging, and genetics measures from typically developing children.https://chd.ucsd.edu/research/ping-study.html13.49 ± 2.92206 (52%)Jernigan et al. (
      • Jernigan T.L.
      • Brown T.T.
      • Hagler Jr., D.J.
      • Akshoomoff N.
      • Bartsch H.
      • Newman E.
      • et al.
      The pediatric imaging, neurocognition, and genetics (PING) data repository.
      )
      FORBOWFORBOW is a longitudinal study enriched for sons and daughters of parents with mental illness. Included behavioral and psychopathology data collected 2013–2020 and MRIs collected from 2016 to 2020.http://www.forbow.org13.57 ± 2.8271 (47%)Uher et al. (
      • Uher R.
      • Cumby J.
      • MacKenzie L.E.
      • Morash-Conway J.
      • Glover J.M.
      • Aylott A.
      • et al.
      A familial risk enriched cohort as a platform for testing early interventions to prevent severe mental illness.
      )
      ABIDE, Autism Brain Imaging Data Exchange; CMI, Child Mind Institute: Healthy Brain Network; CoRR, Consortium for Reliability and Reproducibility; FORBOW, Families Overcoming Risks and Building Opportunities for Well-being; MRI, magnetic resonance imaging; NIH, The NIH MRI Study of Normal Brain Development; PING, Pediatric Imaging, Neurocognition, and Genetics.

       FORBOW Assessments

       Polyenviromic Risk Score

      The adversity score was calculated as a mean of 10 binary indicators of socioeconomic adversity and victimization: 1) biological mother’s education, 2) biological father’s education, 3) home-ownership status, 4) annual household income, 5) emotional abuse, 6) physical abuse, 7) sexual abuse, 8) neglect, 9) exposure to violence at home, and 10) bullying. Our previous work goes into greater detail on these indicators (
      • Zwicker A.
      • MacKenzie L.E.
      • Drobinin V.
      • Bagher A.M.
      • Howes Vallis E.
      • Propper L.
      • et al.
      Neurodevelopmental and genetic determinants of exposure to adversity among youth at risk for mental illness.
      ). In instances where binarizing for visualization was necessary, polyenviromic risk score (PolyE) was considered high if there was any childhood maltreatment.

       Youth Experience Tracker Instrument

      The Youth Experience Tracker Instrument (YETI) is a 26-item self-report measure of 6 psychopathological antecedents that precede and predict mental illness: affective lability, anxiety, depressive symptoms, basic symptoms, psychotic-like experiences, and sleep (
      • Patterson V.C.
      • Pencer A.
      • Pavlova B.
      • Awadia A.
      • MacKenzie L.E.
      • Zwicker A.
      • et al.
      Youth Experience Tracker Instrument: A self-report measure of developmental antecedents to severe mental illness.
      ). The questionnaire was designed to facilitate early identification of risk for SMI and has been validated in the FORBOW cohort. A score ≥ 8 maximized the product of sensitivity and specificity when screening for early antecedents. The measure is available at https://www.youthhealthmeasures.com/.

       Major Depressive Disorder

      Participating youth were interviewed using the Kiddie Schedule for Affective Disorders and Schizophrenia, Present and Lifetime Version (
      • Kaufman J.
      • Birmaher B.
      • Brent D.
      • Rao U.
      • Flynn C.
      • Moreci P.
      • et al.
      Schedule for Affective Disorders and Schizophrenia for School-Age Children-Present and Lifetime Version (K-SADS-PL): Initial reliability and validity data.
      ), by assessors blinded to parent psychopathology. Diagnoses were confirmed in consensus meetings with a psychiatrist. See the Supplement for additional assessment details.

       Columbia Impairment Scale

      The Columbia Impairment Scale (CIS) is a 13-item scale that provides a global measure of impairment (
      • Bird H.R.
      • Shaffer D.
      • Fisher P.
      • Gould M.S.
      The Columbia Impairment Scale (CIS): Pilot findings on a measure of global impairment for children and adolescents.
      ). The questionnaire taps into several functional domains, including relationships with family at home, relations with peers, academic functioning, and involvement in general hobbies/interests. A score ≥ 15 indicates clinically significant functional impairment (
      • Attell B.K.
      • Cappelli C.
      • Manteuffel B.
      • Li H.
      Measuring functional impairment in children and adolescents: Psychometric properties of the Columbia Impairment Scale (CIS).
      ). We took the average of the child and parent reporting on the CIS for the analysis.

       MRI Acquisition

      Images were acquired with a 3T General Electric Discovery MR750 scanner (GE Healthcare) equipped with a 32-channel radiofrequency head coil (MR Instruments, Inc.). Scanning took place at the Biomedical Translational Imaging Centre, Halifax, Nova Scotia. We collected a three-dimensional T1-weighted brain volume imaging sequence with whole-brain coverage, 1-mm3 isotropic resolution, matrix = 224 × 224, field of view = 224 mm, 168 sagittal slices at 1-mm thickness, repetition time = 5.9 ms, echo time = 2.2 ms, inversion time = 450 ms, flip angle = 12°. In addition, we collected a T2-weighted Cube fluid attenuated inversion recovery sequence using a T2 prep contrast option with identical coverage, resolution, and acquisition orientation to the T1-weighted sequence; echo time = 98 ms, repetition time = 5100 ms, inversion time = 1427 ms, echo train length = 250 echoes, flip angle = 90°.

       MRI Processing and Model Features

      Data across all cohorts were processed with FreeSurfer (version 6.0.0) software; RRID:SCR_001847 (
      • Fischl B.
      ). In-depth reporting on the processing in the FORBOW sample as well as assessment of MRI reliability is available in our previous work [(
      • Drobinin V.
      • Van Gestel H.
      • Helmick C.A.
      • Schmidt M.H.
      • Bowen C.V.
      • Uher R.
      Reliability of multimodal MRI brain measures in youth at risk for mental illness.
      ); available on the GitHub repository].
      Automated quality assurance was completed with the Qoala-T tool (
      • Klapwijk E.T.
      • van de Kamp F.
      • van der Meulen M.
      • Peters S.
      • Wierenga L.M.
      Qoala-T: A supervised-learning tool for quality control of FreeSurfer segmented MRI data.
      ). Qoala-T is an ML tool designed to automatically classify the quality of FreeSurfer output. Please see the Supplement for more details regarding the quality control. The brain age prediction model was trained only on data that were recommended for inclusion by Qoala-T.
      For cortical features, we compiled 34 cortical structures per hemisphere based on the FreeSurfer default Desikan–Killiany atlas (
      • Desikan R.S.
      • Ségonne F.
      • Fischl B.
      • Quinn B.T.
      • Dickerson B.C.
      • Blacker D.
      • et al.
      An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest.
      ). We included cortical gray matter volume and cortical surface area measurements for each structure. We excluded cortical thickness measurements for several reasons: 1) cortical thickness measurements are the least reliable and most sensitive to MRI artifacts (
      • Drobinin V.
      • Van Gestel H.
      • Helmick C.A.
      • Schmidt M.H.
      • Bowen C.V.
      • Uher R.
      Reliability of multimodal MRI brain measures in youth at risk for mental illness.
      ,
      • Iscan Z.
      • Jin T.B.
      • Kendrick A.
      • Szeglin B.
      • Lu H.
      • Trivedi M.
      • et al.
      Test-retest reliability of FreeSurfer measurements within and between sites: Effects of visual approval process.
      ); 2) cortical thickness measurements are more scanner-specific than other measures (
      • Fortin J.P.
      • Cullen N.
      • Sheline Y.I.
      • Taylor W.D.
      • Aselcioglu I.
      • Cook P.A.
      • et al.
      Harmonization of cortical thickness measurements across scanners and sites.
      ), and there is no agreed upon way to standardize them within a cross-validation framework; and 3) we wanted to maintain an adequate ratio of features/predictors (p) to sample size (n). Overall, we included 136 cortical features.
      We also included 53 bilateral global (e.g., intracranial volume) and subcortical volumetric measures (e.g., amygdala volume) from the FreeSurfer output. The volume of the fifth ventricle was removed owing to near 0 variance. Overall, 189 features were used for the age prediction model (Table S3 for the full feature list).

       Brain Age Prediction

      First, we split the available data into training, validation, and test sets (Figure 1C). Eighty percent of the typically developing control subjects were used for model training. We implemented 10-fold cross-validation, repeated 10 times, with the folds stratified by the scan age. Twenty percent of the held-out control subjects were used for model validation and estimation of model bias (
      • Smith S.M.
      • Vidaurre D.
      • Alfaro-Almagro F.
      • Nichols T.E.
      • Miller K.L.
      Estimation of brain age delta from brain imaging.
      ); see the Supplement. We tested hypotheses in a separate at-risk cohort (FORBOW), fully independent from training and validation. The test set included 338 scans from 150 individuals; see Table S2 for the scan timing breakdown.
      ML was performed within the tidymodels (version 0.1.1) framework (
      • Kuhn M.
      • Wickham H.
      Tidymodels: A collection of packages for modeling and machine learning using tidyverse principles.
      ). We implemented the XGBoost ML algorithm (version 1.0.0.2) (
      • Chen T.
      • Guestrin C.
      XGBoost: A scalable tree boosting system.
      ) owing to its top performance in many ML challenges as well as successful use in the largest brain age study to date (
      • Kaufmann T.
      • van der Meer D.
      • Doan N.T.
      • Schwarz E.
      • Lund M.J.
      • Agartz I.
      • et al.
      Common brain disorders are associated with heritable patterns of apparent aging of the brain.
      ). The regression models predicted scan age using cortical and subcortical brain features. The primary objective was to minimize the mean absolute error (MAE) metric, expressed in years. See Table S4 for additional model parameters. We used the finalized XGBoost model to predict scan age in the validation and test sets. The final model is available on GitHub. We computed the brain age gap by subtracting the true scan age (chronological age) from the predicted age (Figure 1A). We bias corrected the brain age estimation using prior methods (
      • Smith S.M.
      • Vidaurre D.
      • Alfaro-Almagro F.
      • Nichols T.E.
      • Miller K.L.
      Estimation of brain age delta from brain imaging.
      ). In order to report on the specific brain regions most relevant to predicting age, we created variable importance plots with the vip R package (version 0.2.2) and visualized those regions with the ggseg R package (version 1.5.4) (
      • Mowinckel A.M.
      • Vidal-Piñeiro D.
      Visualization of brain statistics sith R Packages ggseg and ggseg3d.
      ).

       Statistical Analysis

      All statistical analyses were performed in R Studio (R version 3.6.3; RStudio version 1.3.959) (
      RStudio Team
      RStudio: Integrated development environment for R.
      ). Associations with clinical variables were analyzed with mixed-effects linear models implemented in the lme4 package (version 1.1.23) (
      • Bates D.
      • Maechler M.
      • Bolker B.
      • Walker S.
      Fitting linear mixed-effects models using lme4.
      ). We ran separate models with the PolyE, YETI, MDD, and CIS as the primary independent measures and the brain age gap as the dependent measure. As recommended (
      • Le T.T.
      • Kuplicki R.T.
      • McKinney B.A.
      • Yeh H.W.
      • Thompson W.K.
      • Paulus M.P.
      Tulsa 1000 Investigators
      A nonlinear simulation framework supports adjusting for age when analyzing BrainAGE.
      ), we covaried for the effects of age, age2, and sex in the main analyses. For sensitivity analysis, we additionally covaried family history of SMI, socioeconomic status, any prior cannabis use, and IQ. Socioeconomic status was not used as a covariate in the PolyE sensitivity analysis as it is one of the components of the adversity measure. To assess the relative impact of adversity indicators on individual development, we modeled and provided a breakdown of the subcomponents in the Supplement. We modeled multiple observations from each participant by including the individual identifier as a random effect. We also accounted for the nonindependence of data from related individuals by including the family identifier as a higher-order random effect. We reported effect sizes using standardized regression estimates (β) and their 95% confidence intervals (CIs).

      Results

       Brain Age Model Performance

      We built a brain age model using MRI scans of typically developing adolescents from 6 cohorts (n = 1299; age range 9–19 years old). The best model, selected for parsimony and accuracy, had an MAE of 1.53 years in cross-validation. See Table S5 for the top 10 models and their parameters. The finalized model from training performed with an MAE of 1.55 years on the held-out validation set (bias corrected MAE = 1.98). See Figure 2 for model performance across datasets. Our target of interest was the independent FORBOW cohort, where the finalized model performed with an MAE of 1.49 years (bias corrected MAE = 1.86).
      Figure thumbnail gr2
      Figure 2Brain age prediction in validation set and independent testing data. Brain age prediction scatterplot showing predicted brain age by actual chronological age. (A) Predicted age compared with scan age in validation (20% holdout) set. (B) Brain age prediction in an independent sample of at-risk adolescents (Families Overcoming Risks and Building Opportunities for Well-being [FORBOW]). Line of best fit in magenta with confidence interval in blue. Warmer colors indicate a positive brain age gap (older-appearing brain); cooler colors denote a negative brain age gap (younger-appearing brain).

       Reliability of Predicted Age

      While the reliability of individual brain imaging measurements has been established, the short-term reliability of brain age estimation is unknown. In 50 individuals re-scanned within weeks of their first scan, the intraclass correlation coefficient (1,1) for predicted brain age was 0.94 years (95% CI, 0.90 to 0.96). The reliability analysis shows that the data and the model are of sufficient quality to make reliable and consistent brain age predictions.

       Neuroanatomical Contribution to Age Prediction

      The ML model relied on a diverse set of features to make accurate age predictions. The top predictors included the total brain segmentation volume, the precuneus and other parietal regions, the bilateral ventral diencephalon, several prefrontal regions, and subcortical areas such as the hippocampus and the amygdala. Figure 3 displays the variable importance of the top cortical and subcortical volumes to brain age prediction.
      Figure thumbnail gr3
      Figure 3Top neuroanatomical structures involved in accurate age prediction. (A) Variable importance of top 10 cortical volume features. Left: stacked bar plot with right hemisphere, followed by left hemisphere importance. Right: variable importance of all cortical regions visualized on two-dimensional brain. (B) Variable importance of top 10 subcortical volume features. Left: stacked bar plot with right hemisphere followed by left hemisphere where applicable. Right: variable importance of all subcortical regions visualized on two-dimensional brain. bankssts, banks of the superior temporal sulcus; CC, corpus callosum; DC, diencephalon.

       Association With Exposures and Outcomes

       Adversity

      First, we examined how an aggregate measure of adverse environmental exposures (PolyE) relates to brain development. After controlling for age, age2, and sex, we found that PolyE was significantly associated with a positive brain age gap (β = 0.18; p = .02; 95% CI, 0.04 to 0.31). In other words, adversity was associated with older-appearing brains (Figure 4A). This effect remained after additionally controlling for the effects of family history of SMI, any lifetime cannabis use, and IQ (β = 0.17; p = .02; 95% CI, 0.03 to 0.31). See Figure S1 and Table S6 for the associations between the individual subcomponents of the adversity score and the brain age gap.
      Figure thumbnail gr4
      Figure 4Density plots of the main results. Median brain age gap differences (to avoid the influence of outliers) denoted by vertical lines on the plot and numerically in the top right corners (in months). (A) Maltreatment’s association with the brain age gap. (B) Developmental antecedents’ association with the brain age gap. This effect was not statistically significant. (C) Major depressive disorder (MDD) association with the brain age gap. (D) Relationship between functional impairment and the brain age gap.

       Antecedents

      Next, we tested the association between the YETI and the brain age gap. We found that the dimensional measure of 6 psychopathology antecedents was not significantly associated with deviation from chronological age (β = 0.10; p = .09; 95% CI, −0.01 to 0.21). Individuals high on the symptom scale were shifted to the right of the brain age gap distribution, toward an older-appearing brain; however, there was substantial overlap (Figure 4B).

       Major Depressive Disorder

      In Figure 4C, we showed that MDD was associated with a positive brain age gap (β = 0.61; p = .01; 95% CI, 0.23 to 0.99). The effect of an older-appearing brain in MDD held when further controlling for family history of SMI, socioeconomic status, any lifetime cannabis use, and IQ (β = 0.47; p = .02; 95% CI, 0.08 to 0.86). We wanted to explore the depression phenotype in the context of other factors that may be a risk for depression. See Figure S2 and Table S7 for the results from multivariate regressions modeling MDD along with the risk factors (adversity, antecedents) and outcomes (functional impairment).

       Functional Impairment (CIS)

      Finally, we examined the association between functional impairment and the brain age gap (Figure 4D). The main analysis showed that increasing functional impairment relates to a higher brain age gap (β = 0.16; p = .01; 95% CI, 0.05 to 0.27). The effect held in the sensitivity analysis (β = 0.13; p = .02; 95% CI, 0.02 to 0.24). See Figure S3 for a forest plot of associations across all the tests.

      Discussion

      In this work, we were able to predict age using neuroanatomical data accurately and reliably in a large sample of typically developing adolescents. The prediction accuracy generalized to an independent cohort of adolescents enriched for risk of mental illness (FORBOW). Within FORBOW, we found that multiple factors were associated with discrepancies between the predicted and chronological age. The spectrum of adverse experiences and outcomes, such as environmental adversity, depression onset in adolescence, and functional impairment, were all associated with a positive brain age gap. However, the unique effects of each marker while accounting for the presence of others remains to be tested in larger samples. Deviation from chronological age might be a general indicator of unwellness rather than a marker of a specific exposure or outcome.
      Our accuracy in predicting chronological age falls in line with prior developmental work with MAEs from 1 to 2 years [see (
      • Franke K.
      • Gaser C.
      Ten years of BrainAGE as a neuroimaging biomarker of brain aging: What insights have we gained?.
      ) for comprehensive review of the last decade of brain age studies]. We were able to achieve a 1.5-year MAE while maintaining scale, generalizability, and reliability. To our knowledge, we have aggregated the largest developmental sample in the study of brain age and leveraged it to show consistent performance among training, validation, and independent testing.
      The few published reports on developmental brain age suggest that an increased brain age gap is linked with psychopathology, including the risk of psychosis (
      • Chung Y.
      • Addington J.
      • Bearden C.E.
      • Cadenhead K.
      • Cornblatt B.
      • Mathalon D.H.
      • et al.
      Use of machine learning to determine deviance in neuroanatomical maturity associated with future psychosis in youths at clinically high risk.
      ) and depression (
      • de Nooij L.
      • Harris M.A.
      • Hawkins E.L.
      • Clarke T.K.
      • Shen X.
      • Chan S.W.Y.
      • et al.
      Longitudinal trajectories of brain age in young individuals at familial risk of mood disorder from the Scottish Bipolar Family Study.
      ). The present study not just confirms the association between the brain age gap and depression but extends this to associations with known risk factors and functional impairment. Multiple types of adverse exposures in childhood and adolescence have been established as strong risk factors for depression and other type of illness (
      • Uher R.
      • Zwicker A.
      Etiology in psychiatry: Embracing the reality of poly-gene-environmental causation of mental illness.
      ). In line with our hypothesis, we found that cumulative exposure to adversity was associated with advanced brain age. This novel approach to capturing aggregate adversity can be interpreted in the context of existing neuroimaging literature on the underlying components of the dimensional measure. Community disadvantage and lower socioeconomic status have previously been associated with reduced cortical tissue volume, both globally and regionally (
      • Gianaros P.J.
      • Kuan DC-H
      • Marsland A.L.
      • Sheu L.K.
      • Hackman D.A.
      • Miller K.G.
      • Manuck S.B.
      Community socioeconomic disadvantage in midlife relates to cortical morphology via neuroendocrine and cardiometabolic pathways.
      ,
      • McDermott C.L.
      • Seidlitz J.
      • Nadig A.
      • Liu S.
      • Clasen L.S.
      • Blumenthal J.D.
      • et al.
      Longitudinally mapping childhood socioeconomic status associations with cortical and subcortical morphology.
      ). Our measure also assessed childhood maltreatment, including physical, sexual, and emotional abuse and neglect. Maltreatment has been shown to have lasting effects on the stress response system and neurobiological development (
      • Bremne J.D.
      • Vermetten E.
      Stress and development: Behavioral and biological consequences.
      ,
      • Teicher M.H.
      • Andersen S.L.
      • Polcari A.
      • Anderson C.M.
      • Navalta C.P.
      • Kim D.M.
      The neurobiological consequences of early stress and childhood maltreatment.
      ).
      The most prominent neuroanatomical associations with maltreatment include gray matter reductions in frontoparietal and limbic structures such as the precuneus, prefrontal cortex, and hippocampus, enlargements in the ventricles, and reductions in the size of the corpus callosum (
      • Hart H.
      • Rubia K.
      Neuroimaging of child abuse: A critical review.
      ,
      • Teicher M.H.
      • Dumont N.L.
      • Ito Y.
      • Vaituzis C.
      • Giedd J.N.
      • Andersen S.L.
      Childhood neglect is associated with reduced corpus callosum area.
      ). Considering that typical development from late childhood to early adulthood involves widespread decreases in cortical volume (
      • Tamnes C.K.
      • Herting M.M.
      • Goddings A.L.
      • Meuwese R.
      • Blakemore S.J.
      • Dahl R.E.
      • et al.
      Development of the cerebral cortex across adolescence: A multisample study of inter-related longitudinal changes in cortical volume, surface area, and thickness.
      ,
      • Mills K.L.
      • Goddings A.L.
      • Herting M.M.
      • Meuwese R.
      • Blakemore S.J.
      • Crone E.A.
      • et al.
      Structural brain development between childhood and adulthood: Convergence across four longitudinal samples.
      ), the ML model is likely sensitive to the additional decreases associated with adversity, resulting in a prediction of advanced maturation or a wider positive brain age gap. Correspondingly, disproportionate increases in measures such as ventricular volumes, which typically increase with chronological age, are also associated with increased brain age. On average, the age prediction model was equally accurate on the training data from control individuals and the data from individuals at familial risk for mental illness. Yet, the brain age gap was increased in adolescents who experienced adversity. Our results suggest that in the interplay of biology and circumstance, deviation from chronological age may more strongly reflect what happens throughout life rather than the genetic contributions present from the beginning.
      We also hypothesized that developmental antecedents for mental illness would be associated with an increased brain age gap. While higher levels of antecedents shifted the distribution toward an increased brain age gap, the effect was not statistically significant. This was unexpected because we previously found that the basic symptoms and psychotic-like experiences captured by the YETI were associated with reduced cortical folding in this cohort (
      • Drobinin V.
      • Van Gestel H.
      • Zwicker A.
      • MacKenzie L.
      • Cumby J.
      • Patterson V.C.
      • et al.
      Psychotic symptoms are associated with lower cortical folding in youth at risk for mental illness.
      ). It is possible that early preprodromal symptoms are associated with subtle cortical alterations that are masked amid the developmental changes occurring in adolescence. Our previous work found reductions in the orbitofrontal and occipital areas, none of which feature prominently in the list of structures that contribute most to accurate age prediction. Our current findings compare to those from Chung et al. (
      • Chung Y.
      • Addington J.
      • Bearden C.E.
      • Cadenhead K.
      • Cornblatt B.
      • Mathalon D.H.
      • et al.
      Use of machine learning to determine deviance in neuroanatomical maturity associated with future psychosis in youths at clinically high risk.
      ), where prodrome symptoms were associated with a wider brain age gap but the trained models were not robust enough to predict conversion to psychosis.
      In our final analyses, we examined the brain age gap in the context of depression and then concluded the investigation by demonstrating the functional relevance of the brain age gap beyond diagnostic group differences. In the present study, MDD was associated with a higher positive brain age gap, confirming our hypothesis and resembling the effect recently found in adults with MDD (
      • Han L.K.M.
      • Dinga R.
      • Hahn T.
      • Ching C.R.K.
      • Eyler L.T.
      • Aftanas L.
      • et al.
      Brain aging in major depressive disorder: Results from the ENIGMA major depressive disorder working group.
      ). Finally, functional impairment is a necessary criterion to meet threshold for many mental health diagnoses and is an important outcome measure in its own right (
      • Attell B.K.
      • Cappelli C.
      • Manteuffel B.
      • Li H.
      Measuring functional impairment in children and adolescents: Psychometric properties of the Columbia Impairment Scale (CIS).
      ). Our results showed that functional impairment, as captured by a widely used youth impairment scale, is associated with higher brain age. One of the largest neuropsychiatric studies to date (
      • Kaufmann T.
      • van der Meer D.
      • Doan N.T.
      • Schwarz E.
      • Lund M.J.
      • Agartz I.
      • et al.
      Common brain disorders are associated with heritable patterns of apparent aging of the brain.
      ) has demonstrated that an increased brain age gap was associated with worse outcomes on several disorder specific functional measures. Our study expands on this finding by demonstrating a more generalized effect of functional impairment on the brain age gap during adolescence.

       Limitations and Future Directions

      There were several limitations to this study. Brain age prediction error can be further reduced in several ways. For example, some scan sites only provided chronological age as whole integers, imposing a built-in cap on prediction accuracy. Furthermore, state-of-the-art deep learning methods, specifically convolutional neural networks, have shown greater accuracy than more shallow ML techniques in adult samples (
      • Cole J.H.
      • Poudel R.P.K.
      • Tsagkrasoulis D.
      • Caan M.W.A.
      • Steves C.
      • Spector T.D.
      • Montana G.
      Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker.
      ). An additional benefit of convolutional neural networks would include fewer processing requirements for MRI data with traditional software. Furthermore, we focused on a broad range of cortical and subcortical measures. However, the feature set can be expanded to include multimodal data for improved accuracy and, perhaps more importantly, mechanistic inference (
      • Engemann D.A.
      • Kozynets O.
      • Sabbagh D.
      • Lemaître G.
      • Varoquaux G.
      • Liem F.
      • Gramfort A.
      Combining magnetoencephalography with magnetic resonance imaging enhances learning of surrogate-biomarkers.
      ).
      The brain age gap addresses two major challenges and opportunities in neuroimaging: high dimensionality of brain data and individual-level prediction. Regions across the brain are analyzed in aggregate through a multivariate framework to make accurate individual-level predictions. This process is then summarized by an intuitive single number, the brain age gap. However, this reduction in complexity is a double-edged sword when it comes to identifying the mechanisms responsible for the brain age gap. Our efforts at interpretable ML showed which structures contributed most to brain age prediction. By incorporating diffusion-weighted imaging, intracortical myelination, and data from other modalities, future studies may be able to capture different aspects of pathophysiology contributing to brain age gaps. A great example of such work was done by Brown et al. (
      • Brown T.T.
      • Kuperman J.M.
      • Chung Y.
      • Erhart M.
      • McCabe C.
      • Hagler Jr., D.J.
      • et al.
      Neuroanatomical assessment of biological maturity.
      ). The group examined age-varying contributions of different imaging measures to the prediction of age in healthy individuals. For example, diffusion measures from white matter fiber tracts were found to be most relevant between the ages of 12–15 years. Improvements on such study designs, done at a population neuroscience level, might offer mechanistic insights into the pathophysiology of brain age deviation in the context of neuropsychiatric disorders.
      Given the high covariance between adversity, depression, and impairment, a much larger sample would be required to conclusively identify the unique effects of each marker. A new generation of large-scale studies (
      • Casey B.J.
      • Cannonier T.
      • Conley M.I.
      • Cohen A.O.
      • Barch D.M.
      • Heitzeg M.M.
      • et al.
      The Adolescent Brain Cognitive Development (ABCD) study: Imaging acquisition across 21 sites.
      ,
      • Alexander L.M.
      • Escalera J.
      • Ai L.
      • Andreotti C.
      • Febre K.
      • Mangone A.
      • et al.
      An open resource for transdiagnostic research in pediatric mental health and learning disorders.
      ) investigating adolescent brain development across health and disease might offer enough power to examine individual markers while accounting for their correlation. Furthermore, longitudinal studies will be able to characterize the distinct developmental trajectories of at-risk individuals. Future work can run such analyses and target subsamples in further detail with adequate power to jointly examine the effects of lifestyle factors and medical conditions that are also known to influence brain health (
      • Smith S.M.
      • Vidaurre D.
      • Alfaro-Almagro F.
      • Nichols T.E.
      • Miller K.L.
      Estimation of brain age delta from brain imaging.
      ).

       Conclusions

      We have shown that several factors, including adversity, depression onset in adolescence, and functional impairment, were associated with a higher brain age gap. Future work in larger samples will allow us to study the independent contributions of these factors to brain age. We have shared our brain age algorithm with the wider scientific community. Future studies may characterize how an individual’s deviation from typical neuroanatomical maturity changes throughout life.

      Acknowledgments and Disclosures

      This study was supported by the Independent Investigator Award, Brain & Behavior Research Foundation (Grant No. 24684 [to RU]); the Canada Research Chairs Program (Grant No. 231397 [to RU]); the Canadian Institutes of Health Research (Grant Nos. 124976 , 142738 , 148394 , and 173592 [to RU]); Nova Scotia Health ; the Dalhousie Medical Research Foundation ; and a doctoral graduate award from the Canadian Institutes of Health Research (Grant No. 157975 [to VD]).
      The Biomedical Translational Imaging Centre imaging facility has received funding support from Brain Canada.
      VD, MHS, CVB, and RU designed the study. VD, HVG, CAH, and RU acquired the data, which VD and RU analyzed. VD wrote the article, which all authors reviewed. All authors approved the final version to be published and can certify that no other individuals not listed as authors have made substantial contributions to the paper.
      We thank the participating families and acknowledge the contributions of the Families Overcoming Risks and Building Opportunities for Well-being research team (see http://www.forbow.org). We also thank Anna Nazarova and Anna Minarik for their help in the lab.
      The analysis that supports the findings of this study is openly available on GitHub: https://github.com/GitDro/DevelopmentalBrainAge.
      The authors report no biomedical financial interests or potential conflicts of interest.

      Supplementary Material

      References

        • Kessler R.C.
        • Berglund P.
        • Demler O.
        • Jin R.
        • Merikangas K.R.
        • Walters E.E.
        Lifetime prevalence and age-of-onset distributions of DSM-IV disorders in the National Comorbidity Survey Replication.
        Arch Gen Psychiatry. 2005; 62: 593-602
        • Caspi A.
        • Houts R.M.
        • Ambler A.
        • Danese A.
        • Elliott M.L.
        • Hariri A.
        • et al.
        Longitudinal assessment of mental health disorders and comorbidities across 4 decades among participants in the Dunedin Birth Cohort Study.
        JAMA Netw Open. 2020; 3e203221
        • Tamnes C.K.
        • Herting M.M.
        • Goddings A.L.
        • Meuwese R.
        • Blakemore S.J.
        • Dahl R.E.
        • et al.
        Development of the cerebral cortex across adolescence: A multisample study of inter-related longitudinal changes in cortical volume, surface area, and thickness.
        J Neurosci. 2017; 37: 3402-3412
        • Walhovd K.B.
        • Fjell A.M.
        • Giedd J.
        • Dale A.M.
        • Brown T.T.
        Through thick and thin: A need to reconcile contradictory results on trajectories in human cortical development.
        Cereb Cortex. 2017; 27: 1472-1481
        • Mills K.L.
        • Goddings A.L.
        • Herting M.M.
        • Meuwese R.
        • Blakemore S.J.
        • Crone E.A.
        • et al.
        Structural brain development between childhood and adulthood: Convergence across four longitudinal samples.
        Neuroimage. 2016; 141: 273-281
        • Huttenlocher P.R.
        • Dabholkar A.S.
        Regional differences in synaptogenesis in human cerebral cortex.
        J Comp Neurol. 1997; 387: 167-178
        • Paus T.
        • Keshavan M.
        • Giedd J.N.
        Why do many psychiatric disorders emerge during adolescence?.
        Nat Rev Neurosci. 2008; 9: 947-957
        • Whitaker K.J.
        • Vértes P.E.
        • Romero-Garcia R.
        • Váša F.
        • Moutoussis M.
        • Prabhu G.
        • et al.
        Adolescence is associated with genomically patterned consolidation of the hubs of the human brain connectome.
        Proc Natl Acad Sci U S A. 2016; 113: 9105-9110
        • Casey B.J.
        • Cannonier T.
        • Conley M.I.
        • Cohen A.O.
        • Barch D.M.
        • Heitzeg M.M.
        • et al.
        The Adolescent Brain Cognitive Development (ABCD) study: Imaging acquisition across 21 sites.
        Dev Cogn Neurosci. 2018; 32: 43-54
        • Franke K.
        • Luders E.
        • May A.
        • Wilke M.
        • Gaser C.
        Brain maturation: Predicting individual BrainAGE in children and adolescents using structural MRI.
        Neuroimage. 2012; 63: 1305-1312
        • Brown T.T.
        • Kuperman J.M.
        • Chung Y.
        • Erhart M.
        • McCabe C.
        • Hagler Jr., D.J.
        • et al.
        Neuroanatomical assessment of biological maturity.
        Curr Biol. 2012; 22: 1693-1698
        • Chung Y.
        • Addington J.
        • Bearden C.E.
        • Cadenhead K.
        • Cornblatt B.
        • Mathalon D.H.
        • et al.
        Use of machine learning to determine deviance in neuroanatomical maturity associated with future psychosis in youths at clinically high risk.
        JAMA Psychiatry. 2018; 75: 960-968
        • Cole J.H.
        • Franke K.
        Predicting age using neuroimaging: Innovative brain ageing biomarkers.
        Trends Neurosci. 2017; 40: 681-690
        • Franke K.
        • Gaser C.
        Ten years of BrainAGE as a neuroimaging biomarker of brain aging: What insights have we gained?.
        Front Neurol. 2019; 10: 789
        • Cole J.H.
        • Ritchie S.J.
        • Bastin M.E.
        • Valdés Hernández M.C.
        • Muñoz Maniega S.
        • Royle N.
        • et al.
        Brain age predicts mortality.
        Mol Psychiatry. 2018; 23: 1385-1392
        • Han L.K.M.
        • Dinga R.
        • Hahn T.
        • Ching C.R.K.
        • Eyler L.T.
        • Aftanas L.
        • et al.
        Brain aging in major depressive disorder: Results from the ENIGMA major depressive disorder working group.
        Mol Psychiatry. 2021; 26: 5124-5139
        • Schnack H.G.
        • van Haren N.E.M.
        • Nieuwenhuis M.
        • Hulshoff Pol H.E.
        • Cahn W.
        • Kahn R.S.
        Accelerated brain aging in schizophrenia: A longitudinal pattern recognition study.
        Am J Psychiatry. 2016; 173: 607-616
        • Kaufmann T.
        • van der Meer D.
        • Doan N.T.
        • Schwarz E.
        • Lund M.J.
        • Agartz I.
        • et al.
        Common brain disorders are associated with heritable patterns of apparent aging of the brain.
        Nat Neurosci. 2019; 22: 1617-1623
        • Lewis J.D.
        • Evans A.C.
        • Tohka J.
        • Brain Development Cooperative Group, Pediatric Imaging, Neurocognition, and Genetics Study
        T1 white/gray contrast as a predictor of chronological age, and an index of cognitive performance.
        Neuroimage. 2018; 173: 341-350
        • de Nooij L.
        • Harris M.A.
        • Hawkins E.L.
        • Clarke T.K.
        • Shen X.
        • Chan S.W.Y.
        • et al.
        Longitudinal trajectories of brain age in young individuals at familial risk of mood disorder from the Scottish Bipolar Family Study.
        Wellcome Open Res. 2020; 4: 206
        • Polanczyk G.
        • Moffitt T.E.
        • Arseneault L.
        • Cannon M.
        • Ambler A.
        • Keefe R.S.E.
        • et al.
        Etiological and clinical features of childhood psychotic symptoms: Results from a birth cohort.
        Arch Gen Psychiatry. 2010; 67: 328-338
        • Wechsler D.
        Wechsler Abbreviated Scale of Intelligence, Second Edition (WASI-II). NCS Pearson, San Antonio, TX2011
        • Zwicker A.
        • MacKenzie L.E.
        • Drobinin V.
        • Bagher A.M.
        • Howes Vallis E.
        • Propper L.
        • et al.
        Neurodevelopmental and genetic determinants of exposure to adversity among youth at risk for mental illness.
        J Child Psychol Psychiatry. 2020; 61: 536-544
        • Patterson V.C.
        • Pencer A.
        • Pavlova B.
        • Awadia A.
        • MacKenzie L.E.
        • Zwicker A.
        • et al.
        Youth Experience Tracker Instrument: A self-report measure of developmental antecedents to severe mental illness.
        Early Interv Psychiatry. 2021; 15: 676-685
        • Kaufman J.
        • Birmaher B.
        • Brent D.
        • Rao U.
        • Flynn C.
        • Moreci P.
        • et al.
        Schedule for Affective Disorders and Schizophrenia for School-Age Children-Present and Lifetime Version (K-SADS-PL): Initial reliability and validity data.
        J Am Acad Child Adolesc Psychiatry. 1997; 36: 980-988
        • Bird H.R.
        • Shaffer D.
        • Fisher P.
        • Gould M.S.
        The Columbia Impairment Scale (CIS): Pilot findings on a measure of global impairment for children and adolescents.
        Int J Methods Psychiatr Res. 1993; 3: 167-176
        • Attell B.K.
        • Cappelli C.
        • Manteuffel B.
        • Li H.
        Measuring functional impairment in children and adolescents: Psychometric properties of the Columbia Impairment Scale (CIS).
        Eval Health Prof. 2020; 43: 3-15
        • Fischl B.
        FreeSurfer. Neuroimage. 2012; 62: 774-781
        • Drobinin V.
        • Van Gestel H.
        • Helmick C.A.
        • Schmidt M.H.
        • Bowen C.V.
        • Uher R.
        Reliability of multimodal MRI brain measures in youth at risk for mental illness.
        Brain Behav. 2020; 10e01609
        • Klapwijk E.T.
        • van de Kamp F.
        • van der Meulen M.
        • Peters S.
        • Wierenga L.M.
        Qoala-T: A supervised-learning tool for quality control of FreeSurfer segmented MRI data.
        Neuroimage. 2019; 189: 116-129
        • Desikan R.S.
        • Ségonne F.
        • Fischl B.
        • Quinn B.T.
        • Dickerson B.C.
        • Blacker D.
        • et al.
        An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest.
        Neuroimage. 2006; 31: 968-980
        • Iscan Z.
        • Jin T.B.
        • Kendrick A.
        • Szeglin B.
        • Lu H.
        • Trivedi M.
        • et al.
        Test-retest reliability of FreeSurfer measurements within and between sites: Effects of visual approval process.
        Hum Brain Mapp. 2015; 36: 3472-3485
        • Fortin J.P.
        • Cullen N.
        • Sheline Y.I.
        • Taylor W.D.
        • Aselcioglu I.
        • Cook P.A.
        • et al.
        Harmonization of cortical thickness measurements across scanners and sites.
        Neuroimage. 2018; 167: 104-120
        • Smith S.M.
        • Vidaurre D.
        • Alfaro-Almagro F.
        • Nichols T.E.
        • Miller K.L.
        Estimation of brain age delta from brain imaging.
        Neuroimage. 2019; 200: 528-539
        • Kuhn M.
        • Wickham H.
        Tidymodels: A collection of packages for modeling and machine learning using tidyverse principles.
        (Available at:)
        https://tidymodels.tidymodels.org/authors.html
        Date: 2020
        Date accessed: February 28, 2020
        • Chen T.
        • Guestrin C.
        XGBoost: A scalable tree boosting system.
        arXiv. 2016; https://doi.org/10.1145/2939672.2939785
        • Mowinckel A.M.
        • Vidal-Piñeiro D.
        Visualization of brain statistics sith R Packages ggseg and ggseg3d.
        Adv Meth Pract Psychol Sci. 2020; 3: 466-483
        • RStudio Team
        RStudio: Integrated development environment for R.
        RStudio, PBC, Boston2020
        • Bates D.
        • Maechler M.
        • Bolker B.
        • Walker S.
        Fitting linear mixed-effects models using lme4.
        J Stat Softw. 2015; 67: 1-48
        • Le T.T.
        • Kuplicki R.T.
        • McKinney B.A.
        • Yeh H.W.
        • Thompson W.K.
        • Paulus M.P.
        • Tulsa 1000 Investigators
        A nonlinear simulation framework supports adjusting for age when analyzing BrainAGE.
        Front Aging Neurosci. 2018; 10: 317
        • Uher R.
        • Zwicker A.
        Etiology in psychiatry: Embracing the reality of poly-gene-environmental causation of mental illness.
        World Psychiatry. 2017; 16: 121-129
        • Gianaros P.J.
        • Kuan DC-H
        • Marsland A.L.
        • Sheu L.K.
        • Hackman D.A.
        • Miller K.G.
        • Manuck S.B.
        Community socioeconomic disadvantage in midlife relates to cortical morphology via neuroendocrine and cardiometabolic pathways.
        Cereb Cortex. 2017; 27: 460-473
        • McDermott C.L.
        • Seidlitz J.
        • Nadig A.
        • Liu S.
        • Clasen L.S.
        • Blumenthal J.D.
        • et al.
        Longitudinally mapping childhood socioeconomic status associations with cortical and subcortical morphology.
        J Neurosci. 2019; 39: 1365-1373
        • Bremne J.D.
        • Vermetten E.
        Stress and development: Behavioral and biological consequences.
        Dev Psychopathol. 2001; 13: 473-489
        • Teicher M.H.
        • Andersen S.L.
        • Polcari A.
        • Anderson C.M.
        • Navalta C.P.
        • Kim D.M.
        The neurobiological consequences of early stress and childhood maltreatment.
        Neurosci Biobehav Rev. 2003; 27: 33-44
        • Hart H.
        • Rubia K.
        Neuroimaging of child abuse: A critical review.
        Front Hum Neurosci. 2012; 6: 52
        • Teicher M.H.
        • Dumont N.L.
        • Ito Y.
        • Vaituzis C.
        • Giedd J.N.
        • Andersen S.L.
        Childhood neglect is associated with reduced corpus callosum area.
        Biol Psychiatry. 2004; 56: 80-85
        • Drobinin V.
        • Van Gestel H.
        • Zwicker A.
        • MacKenzie L.
        • Cumby J.
        • Patterson V.C.
        • et al.
        Psychotic symptoms are associated with lower cortical folding in youth at risk for mental illness.
        J Psychiatry Neurosci. 2020; 45: 125-133
        • Cole J.H.
        • Poudel R.P.K.
        • Tsagkrasoulis D.
        • Caan M.W.A.
        • Steves C.
        • Spector T.D.
        • Montana G.
        Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker.
        Neuroimage. 2017; 163: 115-124
        • Engemann D.A.
        • Kozynets O.
        • Sabbagh D.
        • Lemaître G.
        • Varoquaux G.
        • Liem F.
        • Gramfort A.
        Combining magnetoencephalography with magnetic resonance imaging enhances learning of surrogate-biomarkers.
        Elife. 2020; 9e54055
        • Alexander L.M.
        • Escalera J.
        • Ai L.
        • Andreotti C.
        • Febre K.
        • Mangone A.
        • et al.
        An open resource for transdiagnostic research in pediatric mental health and learning disorders.
        Sci Data. 2017; 4: 170181
        • Craddock C.
        • Benhajali Y.
        • Chu C.
        • Chouinard F.
        • Evans A.
        • Jakab A.
        • et al.
        The neuro bureau preprocessing initiative: Open sharing of preprocessed neuroimaging data and derivatives.
        in: Presented at the 2013 INCF Neuroinformatics Congress, August 27–29, Stockholm, Sweden. 2013
        • Di Martino A.
        • O’Connor D.
        • Chen B.
        • Alaerts K.
        • Anderson J.S.
        • Assaf M.
        • et al.
        Enhancing studies of the connectome in autism using the autism brain imaging data exchange II.
        Sci Data. 2017; 4: 170010
        • Zuo X.N.
        • Anderson J.S.
        • Bellec P.
        • Birn R.M.
        • Biswal B.B.
        • Blautzik J.
        • et al.
        An open science resource for establishing reliability and reproducibility in functional connectomics.
        Sci Data. 2014; 1: 140049
        • Evans A.C.
        • Brain Development Cooperative Group
        The NIH MRI study of normal brain development.
        Neuroimage. 2006; 30: 184-202
        • Jernigan T.L.
        • Brown T.T.
        • Hagler Jr., D.J.
        • Akshoomoff N.
        • Bartsch H.
        • Newman E.
        • et al.
        The pediatric imaging, neurocognition, and genetics (PING) data repository.
        Neuroimage. 2016; 124: 1149-1154
        • Uher R.
        • Cumby J.
        • MacKenzie L.E.
        • Morash-Conway J.
        • Glover J.M.
        • Aylott A.
        • et al.
        A familial risk enriched cohort as a platform for testing early interventions to prevent severe mental illness.
        BMC Psychiatry. 2014; 14: 344