Brain Age Gap Research Articles

Development of Efficient Brain Age Estimation Method Based on Regional Brain Volume From Structural Magnetic Resonance Imaging.

We aimed to create an efficient and valid predicting model which can estimate individuals' brain age by quantifying their regional brain volumes. A total of 2,560 structural brain magnetic resonance imaging (MRI) scans, along with demographic and clinical data, were obtained. Pretrained deep-learning models were employed to automatically segment the MRI data, which enabled fast calculation of regional brain volumes. Brain age gaps for each subject were estimated using volumetric values from predefined 12 regions of interest (ROIs): bilateral frontal, parietal, occipital, and temporal lobes, as well as bilateral hippocampus and lateral ventricles. A larger weight was given to the ROIs having a larger mean volumetric difference between the cognitively unimpaired (CU) and cognitively impaired group including mild cognitive impairment (MCI), and dementia groups. The brain age was predicted by adding or subtracting the brain age gap to the chronological age according to the presence or absence of the atrophy region. The study showed significant differences in brain age gaps among CU, MCI, and dementia groups. Furthermore, the brain age gaps exhibited significant correlations with education level and measures of cognitive function, including the clinical dementia rating sum-of-boxes and the Korean version of the Mini-Mental State Examination. The brain age that we developed enabled fast and efficient brain age calculations, and it also reflected individual's cognitive function and cognitive reserve. Thus, our study suggested that the brain age might be an important marker of brain health that can be used effectively in real clinical settings.

The causal effect of HbA1c on white matter brain aging by two-sample Mendelian randomization analysis.

Poor glycemic control with elevated levels of hemoglobin A1c (HbA1c) is associated with increased risk of cognitive impairment, with potentially varying effects between sexes. However, the causal impact of poor glycemic control on white matter brain aging in men and women is uncertain. We used two nonoverlapping data sets from UK Biobank cohort: gene-outcome group (with neuroimaging data, (N = 15,193; males/females: 7,101/8,092)) and gene-exposure group (without neuroimaging data, (N = 279,011; males/females: 122,638/156,373)). HbA1c was considered the exposure and adjusted "brain age gap" (BAG) was calculated on fractional anisotropy (FA) obtained from brain imaging as the outcome, thereby representing the difference between predicted and chronological age. The causal effects of HbA1c on adjusted BAG were studied using the generalized inverse variance weighted (gen-IVW) and other sensitivity analysis methods, including Mendelian randomization (MR)-weighted median, MR-pleiotropy residual sum and outlier, MR-using mixture models, and leave-one-out analysis. We found that for every 6.75 mmol/mol increase in HbA1c, there was an increase of 0.49 (95% CI = 0.24, 0.74; p-value = 1.30 × 10-4) years in adjusted BAG. Subgroup analyses by sex and age revealed significant causal effects of HbA1c on adjusted BAG, specifically among men aged 60-73 (p-value = 2.37 × 10-8). Poor glycemic control has a significant causal effect on brain aging, and is most pronounced among older men aged 60-73 years, which provides insights between glycemic control and the susceptibility to age-related neurodegenerative diseases.

Analysis and visualization of the effect of multiple sclerosis on biological brain age.

The rate of neurodegeneration in multiple sclerosis (MS) is an important biomarker for disease progression but can be challenging to quantify. The brain age gap, which quantifies the difference between a patient's chronological and their estimated biological brain age, might be a valuable biomarker of neurodegeneration in patients with MS. Thus, the aim of this study was to investigate the value of an image-based prediction of the brain age gap using a deep learning model and compare brain age gap values between healthy individuals and patients with MS. A multi-center dataset consisting of 5,294 T1-weighted magnetic resonance images of the brain from healthy individuals aged between 19 and 89 years was used to train a convolutional neural network (CNN) for biological brain age prediction. The trained model was then used to calculate the brain age gap in 195 patients with relapsing remitting MS (20-60 years). Additionally, saliency maps were generated for healthy subjects and patients with MS to identify brain regions that were deemed important for the brain age prediction task by the CNN. Overall, the application of the CNN revealed accelerated brain aging with a larger brain age gap for patients with MS with a mean of 6.98 ± 7.18 years in comparison to healthy test set subjects (0.23 ± 4.64 years). The brain age gap for MS patients was weakly to moderately correlated with age at disease onset (ρ = -0.299, p < 0.0001), EDSS score (ρ = 0.206, p = 0.004), disease duration (ρ = 0.162, p = 0.024), lesion volume (ρ = 0.630, p < 0.0001), and brain parenchymal fraction (ρ = -0.718, p < 0.0001). The saliency maps indicated significant differences in the lateral ventricle (p < 0.0001), insula (p < 0.0001), third ventricle (p < 0.0001), and fourth ventricle (p = 0.0001) in the right hemisphere. In the left hemisphere, the inferior lateral ventricle (p < 0.0001) and the third ventricle (p < 0.0001) showed significant differences. Furthermore, the Dice similarity coefficient showed the highest overlap of salient regions between the MS patients and the oldest healthy subjects, indicating that neurodegeneration is accelerated in this patient cohort. In conclusion, the results of this study show that the brain age gap is a valuable surrogate biomarker to measure disease progression in patients with multiple sclerosis.

Discovery of High-Risk Clinical Factors That Accelerate Brain Aging in Adults: A Population-Based Machine Learning Study.

Introduction: Brain age prediction using neuroimaging data and machine learning algorithms holds significant promise for gaining insights into the development of neurodegenerative diseases. The estimation of brain age may be influenced not only by the imaging modality but also by multidomain clinical factors. However, the degree to which various clinical factors in individuals are associated with brain structure, as well as the comprehensive relationship between these factors and brain aging, is not yet clear. Methods: In this study, multimodal brain magnetic resonance imaging data and longitudinal clinical information were collected from 964 participants in a population-based cohort with 16 years of follow-up in northern China. We developed a machine learning-based algorithm to predict multimodal brain age and compared the estimated brain age gap (BAG) differences among the 5 groups characterized by varying exposures to these high-risk clinical factors. We then estimated modality-specific brain age in the hypertension group based on hypertension-related regional imaging metrics. Results: The results revealed a significantly larger BAG estimated from multimodal neuroimaging in subjects with 4 or 5 risk factors compared to other groups, suggesting an acceleration of brain aging under cumulative exposure to multiple risk factors. The estimated T1-based BAG exhibited a significantly higher level in the hypertensive subjects compared to the normotensive individuals. Conclusion: Our study provides valuable insights into a range of health factors across lifestyle, metabolism, and social context that are reflective of brain aging and also contributes to the advancement of interventions and public health initiatives targeted at the general population aimed at promoting brain health.

Brain age gap and decline in specific cognitive domains after stroke

Brain age gap and decline in specific cognitive domains after stroke

Brain structure ages-A new biomarker for multi-disease classification.

Age is an important variable to describe the expected brain's anatomy status across the normal aging trajectory. The deviation from that normative aging trajectory may provide some insights into neurological diseases. In neuroimaging, predicted brain age is widely used to analyze different diseases. However, using only the brain age gap information (i.e., the difference between the chronological age and the estimated age) can be not enough informative for disease classification problems. In this paper, we propose to extend the notion of global brain age by estimating brain structure ages using structural magnetic resonance imaging. To this end, an ensemble of deep learning models is first used to estimate a 3D aging map (i.e., voxel-wise age estimation). Then, a 3D segmentation mask is used to obtain the final brain structure ages. This biomarker can be used in several situations. First, it enables to accurately estimate the brain age for the purpose of anomaly detection at the population level. In this situation, our approach outperforms several state-of-the-art methods. Second, brain structure ages can be used to compute the deviation from the normal aging process of each brain structure. This feature can be used in a multi-disease classification task for an accurate differential diagnosis at the subject level. Finally, the brain structure age deviations of individuals can be visualized, providing some insights about brain abnormality and helping clinicians in real medical contexts.

UNDERSTANDING THE INTERPLAY OF BRAIN HEALTH, COGNITION, AND AUTONOMIC FUNCTION

Abstract Research in clinical populations focused on various age-related diseases report multi-system difficulties in autonomic regulation, motor performance, cognition, and brain health. My research investigated the relationship between brain health, chronological age, and cognition. To assess these domains, I cross analyzed Compass 31, MoCA, and Brain Age Technology. The study population included 158 participants, both healthy and unhealthy. The collected data evaluated the relationship between brain age disparity, chronological age, and autonomic function. Correlation analysis, regression modeling, and subgroup comparisons were employed to explore potential associations, age-related patterns, and autonomic function variations. The findings from this research study contributes to a deeper understanding of the complex interplay between brain health, chronological age, and autonomic function. Age, White Matter Hyperintensities, Brain Age Gap, and Brain Age Variance demonstrate high significance when correlated with the MoCA total score. MoCA and all Compass 31 domains were found to be predictive of total white matter hyperintensity volume. This finding highlights a strong relationship between all three domains and suggests that when participants score high on both assessments, they should follow up with neuroimaging to discover potential brain damage. Future studies should identify risk factors for cognitive impairment and brain health that are also symptoms for autonomic dysregulation.

Advanced structural brain aging in preclinical autosomal dominant Alzheimer disease

Background“Brain-predicted age” estimates biological age from complex, nonlinear features in neuroimaging scans. The brain age gap (BAG) between predicted and chronological age is elevated in sporadic Alzheimer disease (AD), but is underexplored in autosomal dominant AD (ADAD), in which AD progression is highly predictable with minimal confounding age-related co-pathology.MethodsWe modeled BAG in 257 deeply-phenotyped ADAD mutation-carriers and 179 non-carriers from the Dominantly Inherited Alzheimer Network using minimally-processed structural MRI scans. We then tested whether BAG differed as a function of mutation and cognitive status, or estimated years until symptom onset, and whether it was associated with established markers of amyloid (PiB PET, CSF amyloid-β-42/40), phosphorylated tau (CSF and plasma pTau-181), neurodegeneration (CSF and plasma neurofilament-light-chain [NfL]), and cognition (global neuropsychological composite and CDR-sum of boxes). We compared BAG to other MRI measures, and examined heterogeneity in BAG as a function of ADAD mutation variants, APOE ε4 carrier status, sex, and education.ResultsAdvanced brain aging was observed in mutation-carriers approximately 7 years before expected symptom onset, in line with other established structural indicators of atrophy. BAG was moderately associated with amyloid PET and strongly associated with pTau-181, NfL, and cognition in mutation-carriers. Mutation variants, sex, and years of education contributed to variability in BAG.ConclusionsWe extend prior work using BAG from sporadic AD to ADAD, noting consistent results. BAG associates well with markers of pTau, neurodegeneration, and cognition, but to a lesser extent, amyloid, in ADAD. BAG may capture similar signal to established MRI measures. However, BAG offers unique benefits in simplicity of data processing and interpretation. Thus, results in this unique ADAD cohort with few age-related confounds suggest that brain aging attributable to AD neuropathology can be accurately quantified from minimally-processed MRI.

Combining Clinical With Cognitive or Magnetic Resonance Imaging Data for Predicting Transition to Psychosis in Ultra High-Risk Patients: Data From the PACE 400 Cohort

BackgroundMultimodal modeling that combines biological and clinical data shows promise in predicting transition to psychosis in individuals who are at ultra-high risk. Individuals who transition to psychosis are known to have deficits at baseline in cognitive function and reductions in gray matter volume in multiple brain regions identified by magnetic resonance imaging. MethodsIn this study, we used Cox proportional hazards regression models to assess the additive predictive value of each modality—cognition, cortical structure information, and the neuroanatomical measure of brain age gap—to a previously developed clinical model using functioning and duration of symptoms prior to service entry as predictors in the Personal Assessment and Crisis Evaluation (PACE) 400 cohort. The PACE 400 study is a well-characterized cohort of Australian youths who were identified as ultra-high risk of transitioning to psychosis using the Comprehensive Assessment of At Risk Mental States (CAARMS) and followed for up to 18 years; it contains clinical data (from N = 416 participants), cognitive data (n = 213), and magnetic resonance imaging cortical parameters extracted using FreeSurfer (n = 231). ResultsThe results showed that neuroimaging, brain age gap, and cognition added marginal predictive information to the previously developed clinical model (fraction of new information: neuroimaging 0%–12%, brain age gap 7%, cognition 0%–16%). ConclusionsIn summary, adding a second modality to a clinical risk model predicting the onset of a psychotic disorder in the PACE 400 cohort showed little improvement in the fit of the model for long-term prediction of transition to psychosis.

Brain and Neural Reserve Mediate Associations Between Lifestyle and Cognition: The Maastricht Study

AbstractBackgroundLife‐course exposure to risk and protective factors impacts brain macro‐ and micro‐structure, which in turn affects cognition. Brain Age Gap (BAG) directly measures brain reserve by comparing an individual’s neuroimaging‐based predicted age with their calendar age. Higher BAG implies accelerated brain aging and lower brain reserve. In this study, we comprehensively modeled mutual associations between brain risk and protective factors, reserve, and cognition in a large, middle‐aged population using structural equation modelling (SEM).MethodsCognitive test scores, lifestyle, and 3T MRI data for n = 4881 participants (mean age(±SD) = 59.2(±8.6), 50.1% male) were available from The Maastricht Study, a population‐based cohort study with extensive phenotyping. Whole brain volumes (gray matter (GM), cerebrospinal fluid (CSF), white matter hyperintensity (WMH)), cerebral microbleeds (CMB), and structural white matter connectivity were calculated. Lifestyle factors were combined into the Lifestyle for BRAin health (LIBRA) weighted sum score, with higher score indicating greater dementia risk (Figure 1). Cognition was calculated by averaging z‐scores across three cognitive domains (executive function and attention, memory, information processing speed). BAG was calculated by comparing calendar age to predictions from a neuroimaging‐based multivariable regression model. Paths between LIBRA, BAG and cognitive function were tested using linear regression and SEM, adjusting for confounders. LIBRA was split into tertiles for SEM analysis.ResultsCSF, GM, WMH and CMB best predicted BAG (R2 = 0.455, RMSE = 6.44). In regression analysis higher LIBRA scores (greater dementia risk) were associated with higher BAG (standardized regression coefficient ß = 0.127, p&lt;0.001), lower connectivity (ß = ‐0.071, p = 0.002) and worse cognition (ßlinear = ‐0.044, p = 0.017, ßquadratic = ‐0.047, p = 0.018). Higher BAG was associated with lower connectivity (ß = ‐0.418, p&lt;0.001) and worse cognition (ß = ‐0.165, p&lt;0.001). Lower connectivity was associated with worse cognition (ß = 0.086, p&lt;0.001). In mediation analysis (Figure 2), 21% of the total differences between the highest and lowest LIBRA tertile on cognition was mediated by BAG (ßindirect = ‐0.019, p&lt;0.001; ßtotal = ‐0.092, p&lt;0.001), and an additional 4.1% was mediated via connectivity (ßindirect = ‐0.003, p&lt;0.001; ßtotal = ‐0.073, p&lt;0.001).ConclusionAssociations between health‐ and lifestyle‐based risk/protective factors (LIBRA) and cognition is partially explained by maintenance of brain reserve (BAG) and neural reserve (connectivity). Lifestyle interventions promoting brain and neural reserve may help maintain cognitive function into older age.

Bridging the Brain‐Age Gap: Quantifying regional contributions using Shapley‐Owen values

AbstractBackgroundThe concept of brain age gap (BAG) is increasingly being used to express the deviation of brain from the normative trajectory. However, each brain region is subject to independent aging transformations due to differences in neurobiological processes. So, reducing high‐dimensional imaging features down to a single number for simultaneously evaluating brain health, capacity, and residual lifespan is an error‐prone task. Furthermore, brain age is observed to be correlated with chronological age. Therefore, there is need for a systematic empirical evaluation of BAG to understand contributions of different regions when considering BAG as a potential aging biomarker for age‐related neuroanatomical abnormalities. Although methods such as saliency maps have been proposed, there is need for a model‐agnostic technique that quantifies consistent feature contributions across various predictive models.MethodWe used morphological features estimated by Freesurfer from T1w (OASIS3 dataset) to train predictive models for BAG. The bias‐correction was performed using two strategies (i.e., scale‐down and scale up) on each of linear regression and XGBoost models as shown in Figure 1. We present feature importance for top‐10 features (based on median feature importance scores) across 100 bootstrap runs (Figures 2 and 3 respectively), along with correlations with chronological age. We use Shapley‐Owen feature attribution technique as a way of assigning importance to features.ResultAs shown in Figures 2 and 3, we found sub‐cortical, anterior cingulate, and ventricle volumes among the most relevant features. We also observe that SHAP determines an almost identical set of most relevant features for predicting corrected BAG irrespective of the predictive model (linear regression or XGboost) or the bias‐correction approach. Furthermore, we found the results to be consistent with prior literature e.g., subcortical brain volumes esp. gray matter. We also empirically observe that bias‐correction mitigates dependence on chronological age.ConclusionWe present a systematic empirical evaluation to identify the most relevant morphological features for predicting corrected BAG using SHAP. A consistent overlap of most relevant features irrespective of predictive model and the bias‐correction approach provides evidence for the robustness of using Shapley‐Owen values in explaining the contribution of morphological features for predicting corrected BAG.

Brain age gap, dementia risk factors and cognition in middle age

AbstractBackgroundBrain Age Gap (BAG) represents the difference between an individual’s predicted age, derived from machine learning models trained on neuroimaging data, and their chronological age. BAG has been associated with dementia and cognition in old age. Less is known relating BAG to dementia risk‐factors or cognitive performance in middle‐age.MethodCognitively healthy, middle‐aged (40‐59 years) subjects from PREVENT‐Dementia had an array of neuropsychological, neuroimaging and genetic assessments. Brain Ages were predicted from T1‐weighted 3T MRI scans. Cognition was assessed using COGNITO. Multiple linear robust regression models tested hypotheses that: (i) BAG is positively associated with dementia risk‐factors; (ii) increased BAG is associated with worse cognition; (iii) longitudinal BAG change is positively associated with longitudinal cognitive deterioration. A range of machine learning algorithms with nested cross‐validation was used to assess whether BAG and cognition could predict each other.Result552 middle‐aged participants (median age 52.8 years) had all baseline assessments; 68 had amyloid PET data and 138 had longitudinal data. Median BAG was ‐2.0 years with a range from ‐21.2 to 18.4 years (Figure 1). BAG in middle‐age was associated with hypertension (p = 0.007) and alcohol intake (p = 0.008) but not APOE4 carrier status (p = 0.14) or amyloid centiloids (p = 0.53). BAG was not associated with cognitive performance either cross‐sectionally (p = 0.74) or longitudinally (p = 0.30), and there was no added predictive value between BAG and cognition. More education was associated with better cognition (p = 4.7×10−11) but not with BAG (p = 0.32).ConclusionEven in midlife, substantial inter‐individual heterogeneity exists in the extent to which brains have aged. BAG in middle‐age is associated with modifiable dementia risk‐factors, suggesting that lifestyle risk‐factor modification needs to start at, or before, midlife to optimise brain health. BAG in middle‐age was not associated with risk‐factors for Alzheimer’s disease (APOE4, amyloid deposition) or cognitive performance, despite there being a plausible and expected association between more education and better cognitive performance. These results are important for understanding brain‐age in middle‐aged populations who might be the target of future dementia‐preventing therapies.

Evaluating brain age as a marker of autosomal dominant Alzheimer disease progression

AbstractBackgroundEstimates of “brain‐predicted age” quantify apparent brain age compared to normative trajectories of neuroimaging features. Brain‐predicted age is elevated in sporadic Alzheimer disease (AD), but is underexplored in autosomal dominant AD (ADAD). We used a previously‐trained model (DeepBrainNet [DBN], Bashyam et al., 2020), which requires minimal MRI pre‐processing, to predict brain age in the Dominantly Inherited Alzheimer Network (DIAN) and evaluated brain age as a marker of ADAD progression.MethodWe used DBN to predict brain age from minimally‐processed, whole‐brain T1 structural MRI scans in 265 ADAD mutation‐carriers (MCs) and 183 non‐carrier controls (NCs). We then tested whether the brain age gap (BAG; difference between predicted and true age) differed as a function of mutation and cognitive status, or estimated years until symptom onset (EYO), and whether it was associated with established markers of amyloid (PiB PET, CSF amyloid‐ß‐42/40), phosphorylated tau (CSF and plasma pTau‐181), neurodegeneration (CSF and plasma neurofilament light [NFL]), and cognition (global neuropsychological composite and CDR‐sum of boxes). Finally, we compared BAG to other MRI measures, and examined heterogeneity in BAG as a function of mutation variants (APP vs. PSEN1 before or after codon 200), APOE E4 carrier status, sex, and education.ResultDBN accurately predicted age in DIAN (Figure 1A). BAG was elevated in symptomatic and asymptomatic MCs, compared to NCs, beginning around ‐10 EYO (Figure 1B,C). BAG, hippocampal volume, and a cortical thickness summary followed similar trajectories across EYO (Figure 1D). BAG was positively associated with PiB PET, CSF and plasma pTau, and CSF and plasma NFL, and was associated with worse cognitive scores, especially in symptomatic MCs (Figure 2). BAG was most elevated in MCs with a PSEN1 mutation before codon 200, but did not differ as a function of APOE, sex, or education (Figure 3).ConclusionWe extend prior work using BAG from sporadic AD to ADAD, noting consistent results. BAG tracks well with markers of pTau, neurodegeneration, and cognition, but to a lesser extent, amyloid, in ADAD. BAG may capture similar signal to established MRI measures. However, DBN‐based BAG offers unique benefits in simplicity of data processing and interpretation.

Men show increased brain aging with respect to women among Cognitively Normal Individuals

AbstractBackgroundThere is an increasing interest in using machine learning and artificial intelligence to estimate chronological age using neuroimaging data. The gap between chronological age and estimated brain age (brain age gap, BAG) is used as a measure of accelerated/resilient brain aging. Previously, BAG has been associated with cognitive status. However, whether the BAG varies across sex and cognitive status have been less explored. The present study examines these associations and validates a voxel‐based machine learning approach based on the elastic net regression (ENR) for BAG calculation.MethodUsing data from the Atherosclerosis Risk in Communities Study (ARIC) study, the Wake Forest School of Medicine Alzheimer’s Disease Research Center (WFSM‐ADRC) clinical cohort and Alzheimer’s Disease Neuroimaging Initiative (ADNI), we examined associations of BAG across cognitive status and sex. We used structural MRI scans from 1853 ARIC participants (ages 67‐90, 60% females), 508 from the WFSM‐ADRC (55‐95 yo., 66% females) and 584 ADNI cognitively normal (CN) participants (55‐90 yo., 57% females). All images were aligned into a common template and the derived gray matter (GM) probability maps from ADNI MRIs were used as input to train the machine learning algorithm. Once the model was fitted the ARIC and WFSM‐ADRC GM probability maps were provided as input to the algorithm to estimate the BAG values. Finally, an age bias correction was applied. Linear regression methods were used to investigate differences between groups. Age, race, education, sex, and cognitive status were included in the model.ResultWe found in both ARIC and WFSM‐ADRC participants that differences in BAG values between CN‐MCI and MCI‐Dementia participants were highly significant. In addition, when we examined differences in BAG values across sex per cognitive status, we found again in both cohorts that differences were only significant for CN individuals. See Table 1 for details.ConclusionOur analyses show that our approach to estimate chronological age using high‐dimensional ENR, produces BAG values which are strongly associated with cognitive status. The increased severity of cognitive impairment is related to accelerated brain aging. Differences in BAG between men and women were significant for CN individuals only.

Novel Framework for Brain Age Prediction using Graph Neural Networks

AbstractBackgroundAging is among the largest risk factors for neurodegeneration which can be accelerated by age‐related pathologies. Hence, individuals may age at different rates reflected by a gap in biological estimates of age and actual chronological age. Graph neural networks (GNN) are deep learning models that leverage spatial information inherent in the dataset for inference. Here, we develop an MRI cortical thickness (CT) based brain age prediction framework using GNNs and illustrate that it provides a feasible mechanism to identify contributing regions leading to elevated brain age gap in Alzheimer’s disease (AD).MethodWe used ANTs to calculate CT in 100 parcels from 3T MRI of 170 healthy controls (HC; age = 64.26±8.27y, 101 females), 53 mild cognitive impairment (MCI; age = 68.56±8.58y, 22 females), and 62 AD (age = 67.25±8.83y, 30 females) individuals. A GNN model based on the anatomical covariance matrix from HC cohort was trained to predict chronological age from associated CT for HC cohort. GNN output was evaluated as an unweighted mean of entities associated with the brain regions in the final layer. Hence, individual contributions to the GNN output by each brain region could be quantified. Final brain age prediction was obtained after removing age‐bias from GNN outputs using linear regression model. For all subjects, we evaluated residuals at regional level (regional age‐gap) by comparing the contribution of each parcel with corresponding GNN output. The residual between predicted brain age and chronological age (age‐gap) was also evaluated. See Figure 1 for an overview.ResultANCOVA (with correction for age and gender) with post‐hoc analyses revealed that regional age‐gap was greater for AD relative to HC in inferior parietal, temporal pole, inferior temporal, medial temporal, and superior frontal regions (Bonferroni corrected p‐value&lt;0.05). Also, regional age‐gap was greater for MCI relative to HC for inferior parietal and temporal pole regions (Figure 2). Subsequently, age‐gap was elevated in AD (mean = 5.64y) and MCI (mean = 2.66y) relative to HC (mean = 0y) reflecting a linear increase in age‐gap with disease stage (Figure 3).ConclusionOur novel framework identified regional CT associations with age‐gap in AD and MCI, suggesting that this GNN approach may be used to further our understanding between aging and neurodegeneration.

BrainAGE methods: influence of field strength, voxel size, race, and ethnicity

AbstractBackgroundThe brain‐age algorithm utilizes a regression model of the typical aging trajectory, trained on structural MRIs and chronological ages of a large population of healthy individuals spanning a wide age range (Cole et al. 2017, Neuroimage). MRIs from new populations are then compared to this regression for estimating brain age, a biomarker of brain health. Few studies have investigated stability of the brain‐age model across field strength and the influence of voxel size and race is understudied.MethodWe analyzed stability of the brain‐age model within and across field strength in the ADNI cohort (n = 75: 25 CN/25 MCI/25 AD) using intra‐class correlation coefficients (ICC) and multiple R2 values. Impact of voxel size (0.8mm, 1mm, and ADNI2 sequence 1.1×1.1×1.2mm) was compared in a sample from the Indiana ADRC (n = 48: 19 CN/16 SCD/10 MCI/3 AD). We then calculated brain age gap (BAG; estimated– chronological age) and compared results across self‐reported racial and ethnic groups matched on diagnosis, sex, age, education, and handedness using independent t‐tests. BAG results of African Americans (AAs) from the IADRC (n = 71: 30 CN/19 SCD/15 MCI/7 AD) and ADNI (n = 147: 41 CN/20 EMCI/27 LMCI/15 AD/44 SMC), and Hispanics (n = 76: 24 CN/16 EMCI/11 LMCI/11 AD/14 SMC) and Asians (n = 47: 12 CN/7 EMCI/4 LMCI/9 AD/15 SMC) from ADNI only, were compared to matched non‐Hispanic Whites (NHWs).ResultThe brain‐age method was stable across repeated scans within field strength, but less stable across field strengths (Fig.1). 3T scans consistently estimated individuals to be ∼4.43 years younger than the 1.5T scans. The method was relatively stable within and across voxel sizes (Fig.2). There was a significant difference in BAG between races (NHWs and AAs, and NHWs and Asians), but not between ethnicities (NHWs and Hispanics) (Fig.3).ConclusionDue to the model’s variability across field strength, we propose a linear offset equation for data harmonization (Fig.1): ((3T estimate/0.92)+9.55). We are also investigating ComBat harmonization to eliminate effects of field strength. While other studies show structural differences across race, it will be important to determine whether the self‐reported racial differences in BAG are due to inherent model bias or true biological differences.

BrainAGE methods: influence of field strength, voxel size, race, and ethnicity

AbstractBackgroundThe brain‐age algorithm utilizes a regression model of the typical aging trajectory, trained on structural MRIs and chronological ages of a large population of healthy individuals spanning a wide age range (Cole et al. 2017, Neuroimage). MRIs from new populations are then compared to this regression for estimating brain age, a biomarker of brain health. Few studies have investigated stability of the brain‐age model across field strength and the influence of voxel size and race is understudied.MethodWe analyzed stability of the brain‐age model within and across field strength in the ADNI cohort (n = 75: 25 CN/25 MCI/25 AD) using intra‐class correlation coefficients (ICC) and multiple R2 values. Impact of voxel size (0.8mm, 1mm, and ADNI2 sequence 1.1×1.1×1.2mm) was compared in a sample from the Indiana ADRC (n = 48: 19 CN/16 SCD/10 MCI/3 AD). We then calculated brain age gap (BAG; estimated– chronological age) and compared results across self‐reported racial and ethnic groups matched on diagnosis, sex, age, education, and handedness using independent t‐tests. BAG results of African Americans (AAs) from the IADRC (n = 71: 30 CN/19 SCD/15 MCI/7 AD) and ADNI (n = 147: 41 CN/20 EMCI/27 LMCI/15 AD/44 SMC), and Hispanics (n = 76: 24 CN/16 EMCI/11 LMCI/11 AD/14 SMC) and Asians (n = 47: 12 CN/7 EMCI/4 LMCI/9 AD/15 SMC) from ADNI only, were compared to matched non‐Hispanic Whites (NHWs).ResultThe brain‐age method was stable across repeated scans within field strength, but less stable across field strengths (Fig.1). 3T scans consistently estimated individuals to be ∼4.43 years younger than the 1.5T scans. The method was relatively stable within and across voxel sizes (Fig.2). There was a significant difference in BAG between races (NHWs and AAs, and NHWs and Asians), but not between ethnicities (NHWs and Hispanics) (Fig.3).ConclusionDue to the model’s variability across field strength, we propose a linear offset equation for data harmonization (Fig.1): ((3T estimate/0.92)+9.55). We are also investigating ComBat harmonization to eliminate effects of field strength. While other studies show structural differences across race, it will be important to determine whether the self‐reported racial differences in BAG are due to inherent model bias or true biological differences.

MRI or 18F-FDG PET for Brain Age Gap Estimation: Links to Cognition, Pathology, and Alzheimer Disease Progression.

Deviations of brain age from chronologic age, known as the brain age gap (BAG), have been linked to neurodegenerative diseases such as Alzheimer disease (AD). Here, we compare the associations of MRI-derived (atrophy) or 18F-FDG PET-derived (brain metabolism) BAG with cognitive performance, neuropathologic burden, and disease progression in cognitively normal individuals (CNs) and individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI). Methods: Machine learning pipelines were trained to estimate brain age from 185 matched T1-weighted MRI or 18F-FDG PET scans of CN from the Alzheimer's Disease Neuroimaging Initiative and validated in external test sets from the Open Access of Imaging and German Center for Neurodegenerative Diseases-Longitudinal Cognitive Impairment and Dementia studies. BAG was correlated with measures of cognitive performance and AD neuropathology in CNs, SCD subjects, and MCI subjects. Finally, BAG was compared between cognitively stable and declining individuals and subsequently used to predict disease progression. Results: MRI (mean absolute error, 2.49 y) and 18F-FDG PET (mean absolute error, 2.60 y) both estimated chronologic age well. At the SCD stage, MRI-based BAG correlated significantly with beta-amyloid1-42 (Aβ1-42) in cerebrospinal fluid, whereas 18F-FDG PET BAG correlated with memory performance. At the MCI stage, both BAGs were associated with memory and executive function performance and cerebrospinal fluid Aβ1-42, but only MRI-derived BAG correlated with phosphorylated-tau181/Aβ1-42 Lastly, MRI-estimated BAG predicted MCI-to-AD progression better than 18F-FDG PET-estimated BAG (areas under the curve, 0.73 and 0.60, respectively). Conclusion: Age was reliably estimated from MRI or 18F-FDG PET. MRI BAG reflected cognitive and pathologic markers of AD in SCD and MCI, whereas 18F-FDG PET BAG was sensitive mainly to early cognitive impairment, possibly constituting an independent biomarker of brain age-related changes.

Brain Age Estimation on a Dementia Cohort Using FLAIR MRI Biomarkers.

The prodromal stage of Alzheimer's disease presents an imperative intervention window. This work focuses on using brain age prediction models and biomarkers from FLAIR MR imaging to identify subjects who progress to Alzheimer's disease (converting mild cognitive impairment) or those who remain stable (stable mild cognitive impairment). A machine learning model was trained to predict the age of normal control subjects on the basis of volume, intensity, and texture features from 3239 FLAIR MRI volumes. The brain age gap estimation (BrainAGE) was computed as the difference between the predicted and true age, and it was used as a biomarker for both cross-sectional and longitudinal analyses. Differences in biomarker means, slopes, and intercepts were investigated using ANOVA and Tukey post hoc test. Correlation analysis was performed between brain age gap estimation and established Alzheimer's disease indicators. The brain age prediction model showed accurate results (mean absolute error = 2.46 years) when testing on held out normal control data. The computed BrainAGE metric showed significant differences between the stable mild cognitive impairment and converting mild cognitive impairment groups in cross-sectional and longitudinal analyses, most notably showing significant differences up to 4 years before conversion to Alzheimer's disease. A significant correlation was found between BrainAGE and previously established Alzheimer's disease conversion biomarkers. The BrainAGE metric can allow clinicians to consider a single explainable value that summarizes all the biomarkers because it considers many dimensions of disease and can determine whether the subject has normal aging patterns or if he or she is trending into a high-risk category using a single value.

BrainAGE as a measure of maturation during early adolescence

Abstract The Brain-Age Gap Estimation (BrainAGE) is an important new tool that purports to evaluate brain maturity when used in adolescent populations. However, it is unclear whether BrainAGE tracks with other maturational metrics in adolescence. In the current study, we related BrainAGE to metrics of pubertal and cognitive development using both a previously validated model and a novel model trained specifically on an early adolescent population. The previously validated model was used to predict BrainAGE in two age bands, 9-11 and 10-13 years old, while the novel model was used with 9-11 year olds only. Across both models and age bands, an older BrainAGE was related to more advanced pubertal development. The relationship between BrainAGE and cognition was less clear, with conflicting relationships across the two models. Additionally, longitudinal analysis revealed moderate to high stability in BrainAGE across early adolescence. The results of the current study provide initial evidence that BrainAGE tracks with some metrics of maturation, including pubertal development. However, the conflicting results between BrainAGE and cognition lead us to question the utility of these models for non-biological processes.