Bias-adjustment in neuroimaging-based brain age frameworks: A robust scheme

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

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

Multimodal imaging analyses in neuromyelitis optica spectrum disorder with or without visual disturbance

BACKGROUND AND PURPOSE

Neuromyelitis optica spectrum disorder is a demyelinating and inflammatory affliction that often leads to visual disturbance. Various imaging techniques, including free-water imaging, have been used to determine neuroinflammation and degeneration. Therefore, this study aimed at determining multimodal imaging differences between patients with neuromyelitis optica spectrum disorder, especially those with visual disturbance, and healthy controls.

MATERIALS AND METHODS

Eighty-five neuromyelitis optica spectrum disorder patients and 89 age- and sex-matched healthy controls underwent 3-T magnetic resonance imaging (MRI). We analyzed adjusted brain-predicted age difference, voxel-based morphometry, and free-water-corrected diffusion tensor imaging (DTI) by tract-based spatial statistics in each patient group (MRI-positive/negative neuromyelitis optica spectrum disorder patients with or without a history of visual disturbance) compared with the healthy control group.

RESULTS

MRI-positive neuromyelitis optica spectrum disorder patients exhibited reduced volumes of the bilateral thalamus. Tract-based spatial statistics showed diffuse white matter abnormalities in all DTI metrics in MRI-positive neuromyelitis optica spectrum disorder patients with a history of visual disturbance. In MRI-negative neuromyelitis optica spectrum disorder patients with a history of visual disturbance, voxel-based morphometry showed volume reduction of bilateral thalami and optic radiations, and tract-based spatial statistics revealed significantly lower free-water-corrected fractional anisotropy and higher mean diffusivity in the posterior dominant distributions, including the optic nerve radiation.

CONCLUSION

Free-water-corrected DTI and voxel-based morphometry analyses may reflect symptoms of visual disturbance in neuromyelitis optica spectrum disorder.

Brain age has limited utility as a biomarker for capturing fluid cognition in older individuals

One well-known biomarker candidate that supposedly helps capture fluid cognition is Brain Age, or a predicted value based on machine-learning models built to predict chronological age from brain MRI. To formally evaluate the utility of Brain Age for capturing fluid cognition, we built 26 age-prediction models for Brain Age based on different combinations of MRI modalities, using the Human Connectome Project in Aging (n=504, 36-100 years old). First, based on commonality analyses, we found a large overlap between Brain Age and chronological age: Brain Age could uniquely add only around 1.6% in explaining variation in fluid cognition over and above chronological age. Second, the age-prediction models that performed better at predicting chronological age did NOT necessarily create better Brain Age for capturing fluid cognition over and above chronological age. Instead, better-performing age-prediction models created Brain Age that overlapped larger with chronological age, up to around 29% out of 32%, in explaining fluid cognition. Third, Brain Age missed around 11% of the total variation in fluid cognition that could have been explained by the brain variation. That is, directly predicting fluid cognition from brain MRI data (instead of relying on Brain Age and chronological age) could lead to around a 1/3-time improvement of the total variation explained. Accordingly, we demonstrated the limited utility of Brain Age as a biomarker for fluid cognition and made some suggestions to ensure the utility of Brain Age in explaining fluid cognition and other phenotypes of interest.

Neuroanatomical Signature of the Transition from Normal Cognition to MCI in Parkinson's Disease

The progression of Parkinson's disease (PD) is often accompanied by cognitive decline. We had previously developed a brain age estimation program utilizing structural MRI data of 949 healthy individuals from publicly available sources. Structural MRI data of 244 PD patients who were cognitively normal at baseline was acquired from the Parkinson Progression Markers Initiative (PPMI). 192 of these showed stable normal cognitive function from baseline out to 5 years (PD-SNC), and the remaining 52 had unstable normal cognition and developed mild cognitive impairment within 5 years (PD-UNC). 105 healthy controls were also included in the analysis as a reference. First, we examined if there were any baseline differences in regional brain structure between PD-UNC and PD-SNC cohorts utilizing the three most widely used atrophy estimation pipelines, i.e., voxel-based morphometry (VBM), deformation-based morphometry and cortical thickness analyses. We then investigated if accelerated brain age estimation with our multivariate regressive machine learning algorithm was different across these groups (HC, PD-SNC, and PD-UNC). As per the VBM analysis, PD-UNC patients demonstrated a noticeable increase in GM volume in the posterior and anterior lobes of the cerebellum, sub-lobar, extra-nuclear, thalamus, and pulvinar regions when compared to PD-SNC at baseline. PD-UNC patients were observed to have significantly older brain age compared to both PD-SNC patients (p=0.009) and healthy controls (p<0.009). The increase in GM volume in the PD-UNC group could potentially indicate an inflammatory or neuronal hypertrophy response, which could serve as a biomarker for future cognitive decline among this population.

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

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

Older Tissue Age Derived From Abdominal Computed Tomography Biomarkers of Muscle, Fat, and Bone Is Associated With Chronic Conditions and Higher Mortality

OBJECTIVE

To determine whether body composition derived from medical imaging may be useful for assessing biologic age at the tissue level because people of the same chronologic age may vary with respect to their biologic age.

METHODS

We identified an age- and sex-stratified cohort of 4900 persons with an abdominal computed tomography scan from January 1, 2010, to December 31, 2020, who were 20 to 89 years old and representative of the general population in Southeast Minnesota and West Central Wisconsin. We constructed a model for estimating tissue age that included 6 body composition biomarkers calculated from abdominal computed tomography using a previously validated deep learning model.

RESULTS

Older tissue age associated with intermediate subcutaneous fat area, higher visceral fat area, lower muscle area, lower muscle density, higher bone area, and lower bone density. A tissue age older than chronologic age was associated with chronic conditions that result in reduced physical fitness (including chronic obstructive pulmonary disease, arthritis, cardiovascular disease, and behavioral disorders). Furthermore, a tissue age older than chronologic age was associated with an increased risk of death (hazard ratio, 1.56; 95% CI, 1.33 to 1.84) that was independent of demographic characteristics, county of residency, education, body mass index, and baseline chronic conditions.

CONCLUSION

Imaging-based body composition measures may be useful in understanding the biologic processes underlying accelerated aging.

Brain Age Gap in Early Illness Schizophrenia and the Clinical High-Risk Syndrome: Associations With Experiential Negative Symptoms and Conversion to Psychosis

BACKGROUND AND HYPOTHESIS

Brain development/aging is not uniform across individuals,spawning efforts to characterize brain age from a biological perspective to model the effects of disease and maladaptive life processes on the brain. The brain age gap represents the discrepancy between estimated brain biological age and chronological age (in this case, based on structural magnetic resonance imaging, MRI). Structural MRI studies report an increased brain age gap (biological age > chronological age) in schizophrenia, with a greater brain age gap related to greater negative symptom severity. Less is known regarding the nature of this gap early in schizophrenia (ESZ), if this gap represents a psychosis conversion biomarker in clinical high-risk (CHR-P) individuals, and how altered brain development and/or agingmap onto specific symptom facets.

STUDY DESIGN

Using structural MRI, we compared the brain age gap among CHR-P (n = 51), ESZ (n = 78), and unaffected comparison participants (UCP; n = 90), and examined associations with CHR-P psychosis conversion (CHR-P converters n = 10; CHR-P non-converters; n = 23) and positive and negative symptoms.

STUDY RESULTS

ESZ showed a greater brain age gap relative to UCP and CHR-P (Ps < .010). CHR-P individuals who converted to psychosis showed a greater brain age gap (P = .043) relative to CHR-P non-converters. A larger brain age gap in ESZ was associated with increased experiential (P = .008), but not expressive negative symptom severity.

CONCLUSIONS

Consistent with schizophrenia pathophysiological models positing abnormal brain maturation, results suggest abnormal brain development is present early in psychosis. An increased brain age gap may be especially relevant to motivational and functional deficits in schizophrenia.

Association between allostatic load and accelerated white matter brain aging: findings from the UK Biobank

White matter (WM) brain age, a neuroimaging-derived biomarker indicating WM microstructural changes, helps predict dementia and neurodegenerative disorder risks. The cumulative effect of chronic stress on WM brain aging remains unknown. In this study, we assessed cumulative stress using a multi-system composite allostatic load (AL) index based on inflammatory, anthropometric, respiratory, lipidemia, and glucose metabolism measures, and investigated its association with WM brain age gap (BAG), computed from diffusion tensor imaging data using a machine learning model, among 22 951 European ancestries aged 40 to 69 (51.40% women) from UK Biobank. Linear regression, Mendelian randomization, along with inverse probability weighting and doubly robust methods, were used to evaluate the impact of AL on WM BAG adjusting for age, sex, socioeconomic, and lifestyle behaviors. We found increasing one AL score unit significantly increased WM BAG by 0.29 years in association analysis and by 0.33 years in Mendelian analysis. The age- and sex-stratified analysis showed consistent results among participants 45-54 and 55-64 years old, with no significant sex difference. This study demonstrated that higher chronic stress was significantly associated with accelerated brain aging, highlighting the importance of stress management in reducing dementia and neurodegenerative disease risks.

A growth chart of brain function from infancy to adolescence based on EEG

BACKGROUND

In children, objective, quantitative tools that determine functional neurodevelopment are scarce and rarely scalable for clinical use. Direct recordings of cortical activity using routinely acquired electroencephalography (EEG) offer reliable measures of brain function.

METHODS

We developed and validated a measure of functional brain age (FBA) using a residual neural network-based interpretation of the paediatric EEG. In this cross-sectional study, we included 1056 children with typical development ranging in age from 1 month to 18 years. We analysed a 10- to 15-min segment of 18-channel EEG recorded during light sleep (N1 and N2 states).

FINDINGS

The FBA had a weighted mean absolute error (wMAE) of 0.85 years (95% CI: 0.69-1.02; n = 1056). A two-channel version of the FBA had a wMAE of 1.51 years (95% CI: 1.30-1.73; n = 1056) and was validated on an independent set of EEG recordings (wMAE = 2.27 years, 95% CI: 1.90-2.65; n = 723). Group-level maturational delays were also detected in a small cohort of children with Trisomy 21 (Cohen's d = 0.36, p = 0.028).

INTERPRETATION

A FBA, based on EEG, is an accurate, practical and scalable automated tool to track brain function maturation throughout childhood with accuracy comparable to widely used physical growth charts.

FUNDING

This research was supported by the National Health and Medical Research Council, Australia, Helsinki University Diagnostic Center Research Funds, Finnish Academy, Finnish Paediatric Foundation, and Sigrid Juselius Foundation.

Left ventricular hypertrophy as a risk factor for accelerated brain aging: Results from the Study of Health in Pomerania

Previous studies provided evidence for the importance of cardiac structure abnormalities, in particular greater left ventricular (LV) mass, for brain aging, but longitudinal studies are lacking to date. We included 926 individuals (median age 48 years; 53% women) from the TREND cohort of the Study of Health in Pomerania (SHIP) without reduced ejection fraction or a history of myocardial infarction. LV mass index (LVMI) was determined by echocardiography at baseline. Brain morphometric measurements were derived from magnetic resonance images at baseline and 7-year follow-up. Direct effects of baseline LVMI on brain morphometry at follow-up were estimated using linear regression models with adjustment for baseline brain morphometry. At baseline, median LVMI was 40 g/m2.7 and 241 individuals (26%) met the criterion of LV hypertrophy. After correction for multiple testing, baseline LVMI was directly associated with reduced global cortical thickness and increased cortical brain age at follow-up independent from hypertension and blood pressure. Exposure-outcome relations were nonlinear and significantly stronger in the upper half of the exposure distribution. Specifically, an increase in baseline LVMI from the 50% quantile to the 95% quantile was associated additional 2.7 years (95% confidence interval = [1.5 years, 3.8 years]) of cortical brain age at follow-up. Additional regional analyses yielded bilateral effects on multiple frontal cortical regions. Our findings highlight the role of cardiac structure in brain aging. LVMI constitutes an easily measurable marker that might help to identify persons at risk for cognitive impairment and dementia.

Deep learning-based BMI inference from structural brain MRI reflects brain alterations following lifestyle intervention

Obesity is associated with negative effects on the brain. We exploit Artificial Intelligence (AI) tools to explore whether differences in clinical measurements following lifestyle interventions in overweight population could be reflected in brain morphology. In the DIRECT-PLUS clinical trial, participants with criterion for metabolic syndrome underwent an 18-month lifestyle intervention. Structural brain MRIs were acquired before and after the intervention. We utilized an ensemble learning framework to predict Body-Mass Index (BMI) scores, which correspond to adiposity-related clinical measurements from brain MRIs. We revealed that patient-specific reduction in BMI predictions was associated with actual weight loss and was significantly higher in active diet groups compared to a control group. Moreover, explainable AI (XAI) maps highlighted brain regions contributing to BMI predictions that were distinct from regions associated with age prediction. Our DIRECT-PLUS analysis results imply that predicted BMI and its reduction are unique neural biomarkers for obesity-related brain modifications and weight loss.

Differences in brain aging between sexes in Parkinson's disease

Parkinson's disease (PD) is linked to faster brain aging. Male sex is associated with higher prevalence, severe symptoms, and a faster progression rate in PD. There remains a significant gap in understanding the function of sex in the process of brain aging in PD. The structural T1-weighted MRI-driven brain-predicted age difference (i.e., Brain-PAD: the actual age subtracted from the brain-predicted age) was computed in a group of 373 people with PD (mean age ± SD: 61.37 ± 9.81, age range: 33-85, 34% female) from the Parkinson's Progression Marker Initiative database using a robust brain-age estimation framework that was trained on 949 healthy subjects. Linear regression models were used to investigate the association between Brain-PAD and clinical variables in PD, stratified by sex. Males with Parkinson's disease (PD-M) exhibited a significantly higher mean Brain-PAD than their female counterparts (PD-F) (t(256) = 2.50, p = 0.012). In the propensity score-matched PD-M group (PD-M*), Brain-PAD was found to be associated with a decline in general cognition, a worse degree of sleep behavior disorder, reduced visuospatial acuity, and caudate atrophy. Conversely, no significant links were observed between these factors and Brain-PAD in the PD-F group. Having 'older' looking brains in PD-M than PD-F supports the idea that sex plays a vital function in PD, such that the PD mechanism may be different in males and females. This study has the potential to broaden our understanding of dissimilarities in brain aging between sexes in the context of PD.

Brain Age Prediction Based on Quantitative Susceptibility Mapping Using the Segmentation Transformer

The process of brain aging is intricate, encompassing significant structural and functional changes, including myelination and iron deposition in the brain. Brain age could act as a quantitative marker to evaluate the degree of the individual's brain evolution. Quantitative susceptibility mapping (QSM) is sensitive to variations in magnetically responsive substances such as iron and myelin, making it a favorable tool for estimating brain age. In this study, we introduce an innovative 3D convolutional network named Segmentation-Transformer-Age-Network (STAN) to predict brain age based on QSM data. STAN employs a two-stage network architecture. The first-stage network learns to extract informative features from the QSM data through segmentation training, while the second-stage network predicts brain age by integrating the global and local features. We collected QSM images from 712 healthy participants, with 548 for training and 164 for testing. The results demonstrate that the proposed method achieved a high accuracy brain age prediction with a mean absolute error (MAE) of 4.124 years and a coefficient of determination (R2) of 0.933. Furthermore, the gaps between the predicted brain age and the chronological age of Parkinson's disease patients were significantly higher than those of healthy subjects (P<0.01). We thus believe that using QSM-based predicted brain age offers a more reliable and accurate phenotype, with the potentiality to serve as a biomarker to explore the process of advanced brain aging.

A review on brain age prediction models

Brain age in neuroimaging has emerged over the last decade and reflects the estimated age based on the brain MRI scan from a person. As a person ages, their brain structure will change, and these changes will be exclusive to males and females and will differ for each. White matter and grey matter density have a deeper relationship with brain aging. Hence, if the white matter and grey matter concentrations vary, the rate at which the brain ages will also vary. Neurodegenerative illnesses can be detected using the biomarker known as brain age. The development of deep learning has made it possible to analyze structural neuroimaging data in new ways, notably by predicting brain ages. We introduce the techniques and possible therapeutic uses of brain age prediction in this cutting-edge review. Creating a machine learning regression model to analyze age-related changes in brain structure among healthy individuals is a typical procedure in studies focused on brain aging. Subsequently, this model is employed to forecast the aging of brains in new individuals. The concept of the "brain-age gap" refers to the difference between an individual's predicted brain age and their actual chronological age. This score may serve as a gauge of the general state of the brain's health while also reflecting neuroanatomical disorders. It may help differential diagnosis, prognosis, and therapy decisions as well as early identification of brain-based illnesses. The following is a summary of the many forecasting techniques utilized over the past 11 years to estimate brain age. The study's conundrums and potential outcomes of the brain age predicted by current models will both be covered.

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.

Deep learning-based age estimation from chest CT scans

PURPOSE

Medical imaging can be used to estimate a patient's biological age, which may provide complementary information to clinicians compared to chronological age. In this study, we aimed to develop a method to estimate a patient's age based on their chest CT scan. Additionally, we investigated whether chest CT estimated age is a more accurate predictor of lung cancer risk compared to chronological age.

METHODS

To develop our age prediction model, we utilized composite CT images and Inception-ResNet-v2. The model was trained, validated, and tested on 13,824 chest CT scans from the National Lung Screening Trial, with 91% for training, 5% for validation, and 4% for testing. Additionally, we independently tested the model on 1849 CT scans collected locally. To assess chest CT estimated age as a risk factor for lung cancer, we computed the relative lung cancer risk between two groups. Group 1 consisted of individuals assigned a CT age older than their chronological age, while Group 2 comprised those assigned a CT age younger than their chronological age.

RESULTS

Our analysis revealed a mean absolute error of 1.84 years and a Pearson's correlation coefficient of 0.97 for our local data when comparing chronological age with the estimated CT age. The model showed the most activation in the area associated with the lungs during age estimation. The relative risk for lung cancer was 1.82 (95% confidence interval, 1.65-2.02) for individuals assigned a CT age older than their chronological age compared to those assigned a CT age younger than their chronological age.

CONCLUSION

Findings suggest that chest CT age captures some aspects of biological aging and may be a more accurate predictor of lung cancer risk than chronological age. Future studies with larger and more diverse patients are required for the generalization of the interpretations.

Successful cognitive aging is associated with thicker anterior cingulate cortex and lower tau deposition compared to typical aging

INTRODUCTION

There is no consensus on either the definition of successful cognitive aging (SA) or the underlying neural mechanisms.

METHODS

We examined the agreement between new and existing definitions using: (1) a novel measure, the cognitive age gap (SA-CAG, cognitive-predicted age minus chronological age), (2) composite scores for episodic memory (SA-EM), (3) non-memory cognition (SA-NM), and (4) the California Verbal Learning Test (SA-CVLT).

RESULTS

Fair to moderate strength of agreement was found between the four definitions. Most SA groups showed greater cortical thickness compared to typical aging (TA), especially in the anterior cingulate and midcingulate cortices and medial temporal lobes. Greater hippocampal volume was found in all SA groups except SA-NM. Lower entorhinal 18 F-Flortaucipir (FTP) uptake was found in all SA groups.

DISCUSSION

These findings suggest that a feature of SA, regardless of its exact definition, is resistance to tau pathology and preserved cortical integrity, especially in the anterior cingulate and midcingulate cortices.

HIGHLIGHTS

Different approaches have been used to define successful cognitive aging (SA). Regardless of definition, different SA groups have similar brain features. SA individuals have greater anterior cingulate thickness and hippocampal volume. Lower entorhinal tau deposition, but not amyloid beta is related to SA. A combination of cortical integrity and resistance to tau may be features of SA.

Ordinal Classification with Distance Regularization for Robust Brain Age Prediction

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

Brain age prediction using combined deep convolutional neural network and multi-layer perceptron algorithms

The clinical applications of brain age prediction have expanded, particularly in anticipating the onset and prognosis of various neurodegenerative diseases. In the current study, we proposed a deep learning algorithm that leverages brain structural imaging data and enhances prediction accuracy by integrating biological sex information. Our model for brain age prediction, built on deep neural networks, employed a dataset of 3004 healthy subjects aged 18 and above. The T1-weighted images were minimally preprocessed and analyzed using the convolutional neural network (CNN) algorithm. The categorical sex information was then incorporated using the multi-layer perceptron (MLP) algorithm. We trained and validated both a CNN-only algorithm (utilizing only brain structural imaging data), and a combined CNN-MLP algorithm (using both structural brain imaging data and sex information) for age prediction. By integrating sex information with T1-weighted imaging data, our proposed CNN-MLP algorithm outperformed not only the CNN-only algorithm but also established algorithms, such as brainageR, in prediction accuracy. Notably, this hybrid CNN-MLP algorithm effectively distinguished between mild cognitive impairment and Alzheimer's disease groups by identifying variances in brain age gaps between them, highlighting the algorithm's potential for clinical application. Overall, these results underscore the enhanced precision of the CNN-MLP algorithm in brain age prediction, achieved through the integration of sex information.

Image-Based Biological Heart Age Estimation Reveals Differential Aging Patterns Across Cardiac Chambers

BACKGROUND

Biological heart age estimation can provide insights into cardiac aging. However, existing studies do not consider differential aging across cardiac regions.

PURPOSE

To estimate biological age of the left ventricle (LV), right ventricle (RV), myocardium, left atrium, and right atrium using magnetic resonance imaging radiomics phenotypes and to investigate determinants of aging by cardiac region.

STUDY TYPE

Cross-sectional.

POPULATION

A total of 18,117 healthy UK Biobank participants including 8338 men (mean age = 64.2 ± 7.5) and 9779 women (mean age = 63.0 ± 7.4).

FIELD STRENGTH/SEQUENCE

A 1.5 T/balanced steady-state free precession.

ASSESSMENT

An automated algorithm was used to segment the five cardiac regions, from which radiomic features were extracted. Bayesian ridge regression was used to estimate biological age of each cardiac region with radiomics features as predictors and chronological age as the output. The "age gap" was the difference between biological and chronological age. Linear regression was used to calculate associations of age gap from each cardiac region with socioeconomic, lifestyle, body composition, blood pressure and arterial stiffness, blood biomarkers, mental well-being, multiorgan health, and sex hormone exposures (n = 49).

STATISTICAL TEST

Multiple testing correction with false discovery method (threshold = 5%).

RESULTS

The largest model error was with RV and the smallest with LV age (mean absolute error in men: 5.26 vs. 4.96 years). There were 172 statistically significant age gap associations. Greater visceral adiposity was the strongest correlate of larger age gaps, for example, myocardial age gap in women (Beta = 0.85, P = 1.69 × 10-26 ). Poor mental health associated with large age gaps, for example, "disinterested" episodes and myocardial age gap in men (Beta = 0.25, P = 0.001), as did a history of dental problems (eg LV in men Beta = 0.19, P = 0.02). Higher bone mineral density was the strongest associate of smaller age gaps, for example, myocardial age gap in men (Beta = -1.52, P = 7.44 × 10-6 ).

DATA CONCLUSION

This work demonstrates image-based heart age estimation as a novel method for understanding cardiac aging.

EVIDENCE LEVEL

1.

TECHNICAL EFFICACY

Stage 1.

Feasibility of brain age predictions from clinical T1-weighted MRIs

An individual's brain predicted age minus chronological age (brain-PAD) obtained from MRIs could become a biomarker of disease in research studies. However, brain age reports from clinical MRIs are scant despite the rich clinical information hospitals provide. Since clinical MRI protocols are meant for specific clinical purposes, performance of brain age predictions on clinical data need to be tested. We explored the feasibility of using DeepBrainNet, a deep network previously trained on research-oriented MRIs, to predict the brain ages of 840 patients who visited 15 facilities of a health system in Florida. Anticipating a strong prediction bias in our clinical sample, we characterized it to propose a covariate model in group-level regressions of brain-PAD (recommended to avoid Type I, II errors), and tested its generalizability, a requirement for meaningful brain age predictions in new single clinical cases. The best bias-related covariate model was scanner-independent and linear in age, while the best method to estimate bias-free brain ages was the inverse of a scanner-independent and quadratic in brain age function. We demonstrated the feasibility to detect sex-related differences in brain-PAD using group-level regression accounting for the selected covariate model. These differences were preserved after bias correction. The Mean-Average Error (MAE) of the predictions in independent data was ∼8 years, 2-3 years greater than reports for research-oriented MRIs using DeepBrainNet, whereas an R2 (assuming no bias) was 0.33 and 0.76 for the uncorrected and corrected brain ages, respectively. DeepBrainNet on clinical populations seems feasible, but more accurate algorithms or transfer-learning retraining is needed.

Biological age and brain age in midlife: relationship to multimorbidity and mental health

Biological age and brain age estimated using biological and neuroimaging measures have recently emerged as surrogate aging biomarkers shown to be predictive of diverse health outcomes. As aging underlies the development of many chronic conditions, surrogate aging biomarkers capture health at the whole person level, having the potential to improve our understanding of multimorbidity. Our study investigates whether elevated biological age and brain age are associated with an increased risk of multimorbidity using a large dataset from the Midlife in the United States Refresher study. Ensemble learning is utilized to combine multiple machine learning models to estimate biological age using a comprehensive set of biological markers. Brain age is obtained using Gaussian processes regression and neuroimaging data. Our study is the first to examine the relationship between accelerated brain age and multimorbidity. Furthermore, it is the first attempt to explore how biological age and brain age are related to multimorbidity in mental health. Our findings hold the potential to advance the understanding of disease accumulation and their relationship with aging.

Associations between polygenic risk scores and accelerated brain ageing in smokers

BACKGROUND

Smoking contributes to a variety of neurodegenerative diseases and neurobiological abnormalities, suggesting that smoking is associated with accelerated brain aging. However, the neurobiological mechanisms affected by smoking, and whether they are genetically influenced, remain to be investigated.

METHODS

Using structural magnetic resonance imaging data from the UK Biobank (n = 33 293), a brain age predictor was trained on non-smoking healthy groups and tested on smokers to obtain the BrainAge Gap (BAG). The cumulative effect of multiple common genetic variants associated with smoking was then calculated to acquire a polygenic risk score (PRS). The relationship between PRS, BAG, total gray matter volume (tGMV), and smoking parameters was explored and further genes included in the PRS were annotated to identify potential molecular mechanisms affected by smoking.

RESULTS

The BrainAge in smokers was predicted with very high accuracy (r = 0.725, MAE = 4.16). Smokers had a greater BAG (Cohen's d = 0.074, p < 0.0001) and higher PRS (Cohen's d = 0.63, p < 0.0001) than non-smokers. A higher PRS was associated with increased amount of smoking, mediated by BAG and tGMV. Several neurotransmitters and ion channel pathways were enriched in the group of smoking-related genes involved in addiction, brain synaptic plasticity, and some neurological disorders.

CONCLUSION

By using a simplified single indicator of the entire brain (BAG) in combination with the PRS, this study highlights the greater BAG in smokers and its linkage with genes and smoking behavior, providing insight into the neurobiological underpinnings and potential features of smoking-related aging.

Toward MR protocol-agnostic, unbiased brain age predicted from clinical-grade MRIs

The difference between the estimated brain age and the chronological age ('brain-PAD') could become a clinical biomarker. However, most brain age models were developed for research-grade high-resolution T1-weighted MRIs, limiting their applicability to clinical-grade MRIs from various protocols. We adopted a dual-transfer learning strategy to develop a model agnostic to modality, resolution, or slice orientation. We retrained a convolutional neural network (CNN) using 6281 clinical MRIs from 1559 patients, among 7 modalities and 8 scanner models. The CNN was trained to estimate brain age from synthetic research-grade magnetization-prepared rapid gradient-echo MRIs (MPRAGEs) generated by a 'super-resolution' method. The model failed with T2-weighted Gradient-Echo MRIs. The mean absolute error (MAE) was 5.86-8.59 years across the other modalities, still higher than for research-grade MRIs, but comparable between actual and synthetic MPRAGEs for some modalities. We modeled the "regression bias" in brain age, for its correction is crucial for providing unbiased summary statistics of brain age or for personalized brain age-based biomarkers. The bias model was generalizable as its correction eliminated any correlation between brain-PAD and chronological age in new samples. Brain-PAD was reliable across modalities. We demonstrate the feasibility of brain age predictions from arbitrary clinical-grade MRIs, thereby contributing to personalized medicine.

Developmental prediction modeling based on diffusion tensor imaging uncovering age-dependent heterogeneity in early childhood autistic brain

OBJECTIVE

There has been increasing evidence for atypical white matter (WM) microstructure in autistic people, but findings have been divergent. The development of autistic people in early childhood is clouded by the concurrently rapid brain growth, which might lead to the inconsistent findings of atypical WM microstructure in autism. Here, we aimed to reveal the developmental nature of autistic children and delineate atypical WM microstructure throughout early childhood while taking developmental considerations into account.

METHOD

In this study, diffusion tensor imaging was acquired from two independent cohorts, containing 91 autistic children and 100 typically developing children (TDC), aged 4-7 years. Developmental prediction modeling using support vector regression based on TDC participants was conducted to estimate the WM atypical development index of autistic children. Then, subgroups of autistic children were identified by using the k-means clustering method and were compared to each other on the basis of demographic information, WM atypical development index, and autistic trait by using two-sample t-test. Relationship of the WM atypical development index with age was estimated by using partial correlation. Furthermore, we performed threshold-free cluster enhancement-based two-sample t-test for the group comparison in WM microstructures of each subgroup of autistic children with the rematched subsets of TDC.

RESULTS

We clustered autistic children into two subgroups according to WM atypical development index. The two subgroups exhibited distinct developmental stages and age-dependent diversity. WM atypical development index was found negatively associated with age. Moreover, an inverse pattern of atypical WM microstructures and different clinical manifestations in the two stages, with subgroup 1 showing overgrowth with low level of autistic traits and subgroup 2 exhibiting delayed maturation with high level of autistic traits, were revealed.

CONCLUSION

This study illustrated age-dependent heterogeneity in early childhood autistic children and delineated developmental stage-specific difference that ranged from an overgrowth pattern to a delayed pattern. Trial registration This study has been registered at ClinicalTrials.gov (Identifier: NCT02807766) on June 21, 2016 ( https://clinicaltrials.gov/ct2/show/NCT02807766 ).

Explainable Brain Age Prediction using coVariance Neural Networks

In computational neuroscience, there has been an increased interest in developing machine learning algorithms that leverage brain imaging data to provide estimates of "brain age" for an individual. Importantly, the discordance between brain age and chronological age (referred to as "brain age gap") can capture accelerated aging due to adverse health conditions and therefore, can reflect increased vulnerability towards neurological disease or cognitive impairments. However, widespread adoption of brain age for clinical decision support has been hindered due to lack of transparency and methodological justifications in most existing brain age prediction algorithms. In this paper, we leverage coVariance neural networks (VNN) to propose an explanation-driven and anatomically interpretable framework for brain age prediction using cortical thickness features. Specifically, our brain age prediction framework extends beyond the coarse metric of brain age gap in Alzheimer's disease (AD) and we make two important observations: (i) VNNs can assign anatomical interpretability to elevated brain age gap in AD by identifying contributing brain regions, (ii) the interpretability offered by VNNs is contingent on their ability to exploit specific eigenvectors of the anatomical covariance matrix. Together, these observations facilitate an explainable and anatomically interpretable perspective to the task of brain age prediction.

Predicting cognitive decline in a low-dimensional representation of brain morphology

Identifying early signs of neurodegeneration due to Alzheimer's disease (AD) is a necessary first step towards preventing cognitive decline. Individual cortical thickness measures, available after processing anatomical magnetic resonance imaging (MRI), are sensitive markers of neurodegeneration. However, normal aging cortical decline and high inter-individual variability complicate the comparison and statistical determination of the impact of AD-related neurodegeneration on trajectories. In this paper, we computed trajectories in a 2D representation of a 62-dimensional manifold of individual cortical thickness measures. To compute this representation, we used a novel, nonlinear dimension reduction algorithm called Uniform Manifold Approximation and Projection (UMAP). We trained two embeddings, one on cortical thickness measurements of 6237 cognitively healthy participants aged 18-100 years old and the other on 233 mild cognitively impaired (MCI) and AD participants from the longitudinal database, the Alzheimer's Disease Neuroimaging Initiative database (ADNI). Each participant had multiple visits ([Formula: see text]), one year apart. The first embedding's principal axis was shown to be positively associated ([Formula: see text]) with participants' age. Data from ADNI is projected into these 2D spaces. After clustering the data, average trajectories between clusters were shown to be significantly different between MCI and AD subjects. Moreover, some clusters and trajectories between clusters were more prone to host AD subjects. This study was able to differentiate AD and MCI subjects based on their trajectory in a 2D space with an AUC of 0.80 with 10-fold cross-validation.

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

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

Significant Acceleration of Regional Brain Aging and Atrophy After Mild Traumatic Brain Injury

Brain regions' rates of age-related volumetric change after traumatic brain injury (TBI) are unknown. Here, we quantify these rates cross-sectionally in 113 persons with recent mild TBI (mTBI), whom we compare against 3 418 healthy controls (HCs). Regional gray matter (GM) volumes were extracted from magnetic resonance images. Linear regression yielded regional brain ages and the annualized average rates of regional GM volume loss. These results were compared across groups after accounting for sex and intracranial volume. In HCs, the steepest rates of volume loss were recorded in the nucleus accumbens, amygdala, and lateral orbital sulcus. In mTBI, approximately 80% of GM structures had significantly steeper rates of annual volume loss than in HCs. The largest group differences involved the short gyri of the insula and both the long gyrus and central sulcus of the insula. No significant sex differences were found in the mTBI group, regional brain ages being the oldest in prefrontal and temporal structures. Thus, mTBI involves significantly steeper regional GM loss rates than in HCs, reflecting older-than-expected regional brain ages.

Regional Neuroanatomic Effects on Brain Age Inferred Using Magnetic Resonance Imaging and Ridge Regression

The biological age of the brain differs from its chronological age (CA) and can be used as biomarker of neural/cognitive disease processes and as predictor of mortality. Brain age (BA) is often estimated from magnetic resonance images (MRIs) using machine learning (ML) that rarely indicates how regional brain features contribute to BA. Leveraging an aggregate training sample of 3 418 healthy controls (HCs), we describe a ridge regression model that quantifies each region's contribution to BA. After model testing on an independent sample of 651 HCs, we compute the coefficient of partial determination R¯p2 for each regional brain volume to quantify its contribution to BA. Model performance is also evaluated using the correlation r between chronological and biological ages, the mean absolute error (MAE ) and mean squared error (MSE) of BA estimates. On training data, r=0.92, MSE=70.94 years, MAE=6.57 years, and R¯2=0.81; on test data, r=0.90, MSE=81.96 years, MAE=7.00 years, and R¯2=0.79. The regions whose volumes contribute most to BA are the nucleus accumbens (R¯p2=7.27%), inferior temporal gyrus (R¯p2=4.03%), thalamus (R¯p2=3.61%), brainstem (R¯p2=3.29%), posterior lateral sulcus (R¯p2=3.22%), caudate nucleus (R¯p2=3.05%), orbital gyrus (R¯p2=2.96%), and precentral gyrus (R¯p2=2.80%). Our ridge regression, although outperformed by the most sophisticated ML approaches, identifies the importance and relative contribution of each brain structure to overall BA. Aside from its interpretability and quasi-mechanistic insights, our model can be used to validate future ML approaches for BA estimation.

A Skewed Loss Function for Correcting Predictive Bias in Brain Age Prediction

In neuroimaging, the difference between predicted brain age and chronological age, known as brain age delta, has shown its potential as a biomarker related to various pathological phenotypes. There is a frequently observed bias when estimating brain age delta using regression models. This bias manifests as an overestimation of brain age for young participants and an underestimation of brain age for older participants. Therefore, the brain age delta is negatively correlated with chronological age, which can be problematic when evaluating relationships between brain age delta and other age-associated variables. This paper proposes a novel bias correction method for regression models by introducing a skewed loss function to replace the normal symmetric loss function. The regression model then behaves differently depending on whether it makes overestimations or underestimations. Our approach works with any type of MR image and no specific preprocessing is required, as long as the image is sensitive to age-related changes. The proposed approach has been validated using three classic deep learning models, namely ResNet, VGG, and GoogleNet on publicly available neuroimaging aging datasets. It shows flexibility across different model architectures and different choices of hyperparameters. The corrected brain age delta from our approach then has no linear relationship with chronological age and achieves higher predictive accuracy than a commonly-used two-stage approach.

Physiological Age by Artificial Intelligence-Enhanced Electrocardiograms as a Novel Risk Factor of Mortality in Kidney Transplant Candidates

BACKGROUND

Mortality risk assessment before kidney transplantation (KT) is imperfect. An emerging risk factor for death in nontransplant populations is physiological age as determined by the application of artificial intelligence to the electrocardiogram (ECG). The aim of this study was to examine the relationship between ECG age and KT waitlist mortality.

METHODS

We applied a previously developed convolutional neural network to the ECGs of KT candidates evaluated 2014 to 2019 to determine ECG age. We used a Cox proportional hazard model to examine whether ECG age was associated with waitlist mortality.

RESULTS

Of the 2183 patients evaluated, 59.1% were male, 81.4% were white, and 11.4% died during follow-up. Mean ECG age was 59.0 ± 12.0 y and mean chronological age at ECG was 53.3 ± 13.6 y. After adjusting for chronological age, comorbidities, and other characteristics associated with mortality, each increase in ECG age of >10 y than the average ECG age for patients of a similar chronological age was associated with an increase in mortality risk (hazard ratio 3.59 per 10-y increase; 95% confidence interval, 2.06-5.72; P  < 0.0001).

CONCLUSIONS

ECG age is a risk factor for KT waitlist mortality. Determining ECG age through artificial intelligence may help guide risk-benefit assessment when evaluating candidates for KT.

Cocaine Destroys Gray Matter Brain Cells and Accelerates Brain Aging

Introduction: Cocaine use disorder (CUD) is a substance use disorder characterized by a strong desire to obtain, consume, and misuse cocaine. Little is known about how cocaine affects the structure of the brain. In this study, we first investigated the anatomical brain changes in individuals with CUD compared to their matched healthy controls, and then explored whether these anatomical brain abnormalities contribute to considerably accelerated brain aging among this population. Methods: At the first stage, we used anatomical magnetic resonance imaging (MRI) data, voxel-based morphometry (VBM), and deformation-based morphometry techniques to uncover the morphological and macroscopic anatomical brain changes in 74 CUD patients compared to 62 age- and sex-matched healthy controls (HCs) obtained from the SUDMEX CONN dataset, the Mexican MRI dataset of patients with CUD. Then, we computed brain-predicted age difference (i.e., brain-PAD: the brain-predicted age minus the actual age) in CUD and HC groups using a robust brain age estimation framework. Using a multiple regression analysis, we also investigated the regional gray matter (GM) and white matter (WM) changes associated with the brain-PAD. Results: Using a whole-brain VBM analysis, we observed widespread gray matter atrophy in CUD patients located in the temporal lobe, frontal lobe, insula, middle frontal gyrus, superior frontal gyrus, rectal gyrus, and limbic lobe regions compared to the HCs. In contrast, we did not observe any swelling in the GM, changes in the WM, or local brain tissue atrophy or expansion between the CUD and HC groups. Furthermore, we found a significantly higher brain-PAD in CUD patients compared to matched HCs (mean difference = 2.62 years, Cohen's d = 0.54; t-test = 3.16, p = 0.002). The regression analysis showed significant negative changes in GM volume associated with brain-PAD in the CUD group, particularly in the limbic lobe, subcallosal gyrus, cingulate gyrus, and anterior cingulate regions. Discussion: The results of our investigation reveal that chronic cocaine use is linked to significant changes in gray matter, which hasten the process of structural brain aging in individuals who use the drug. These findings offer valuable insights into the impact of cocaine on the composition of the brain.

Brain-age prediction: A systematic comparison of machine learning workflows

The difference between age predicted using anatomical brain scans and chronological age, i.e., the brain-age delta, provides a proxy for atypical aging. Various data representations and machine learning (ML) algorithms have been used for brain-age estimation. However, how these choices compare on performance criteria important for real-world applications, such as; (1) within-dataset accuracy, (2) cross-dataset generalization, (3) test-retest reliability, and (4) longitudinal consistency, remains uncharacterized. We evaluated 128 workflows consisting of 16 feature representations derived from gray matter (GM) images and eight ML algorithms with diverse inductive biases. Using four large neuroimaging databases covering the adult lifespan (total N = 2953, 18-88 years), we followed a systematic model selection procedure by sequentially applying stringent criteria. The 128 workflows showed a within-dataset mean absolute error (MAE) between 4.73-8.38 years, from which 32 broadly sampled workflows showed a cross-dataset MAE between 5.23-8.98 years. The test-retest reliability and longitudinal consistency of the top 10 workflows were comparable. The choice of feature representation and the ML algorithm both affected the performance. Specifically, voxel-wise feature spaces (smoothed and resampled), with and without principal components analysis, with non-linear and kernel-based ML algorithms performed well. Strikingly, the correlation of brain-age delta with behavioral measures disagreed between within-dataset and cross-dataset predictions. Application of the best-performing workflow on the ADNI sample showed a significantly higher brain-age delta in Alzheimer's and mild cognitive impairment patients compared to healthy controls. However, in the presence of age bias, the delta estimates in the patients varied depending on the sample used for bias correction. Taken together, brain-age shows promise, but further evaluation and improvements are needed for its real-world application.

Evaluating the causal effect of tobacco smoking on white matter brain aging: a two-sample Mendelian randomization analysis in UK Biobank

BACKGROUND AND AIMS

Tobacco smoking is a risk factor for impaired brain function, but its causal effect on white matter brain aging remains unclear. This study aimed to measure the causal effect of tobacco smoking on white matter brain aging.

DESIGN

Mendelian randomization (MR) analysis using two non-overlapping data sets (with and without neuroimaging data) from UK Biobank (UKB). The group exposed to smoking and control group consisted of current smokers and never smokers, respectively. Our main method was generalized weighted linear regression with other methods also included as sensitivity analysis.

SETTING

United Kingdom.

PARTICIPANTS

The study cohort included 23 624 subjects [10 665 males and 12 959 females with a mean age of 54.18 years, 95% confidence interval (CI) = 54.08, 54.28].

MEASUREMENTS

Genetic variants were selected as instrumental variables under the MR analysis assumptions: (1) associated with the exposure; (2) influenced outcome only via exposure; and (3) not associated with confounders. The exposure smoking status (current versus never smokers) was measured by questionnaires at the initial visit (2006-10). The other exposure, cigarettes per day (CPD), measured the average number of cigarettes smoked per day for current tobacco users over the life-time. The outcome was the 'brain age gap' (BAG), the difference between predicted brain age and chronological age, computed by training machine learning model on a non-overlapping set of never smokers.

FINDINGS

The estimated BAG had a mean of 0.10 (95% CI = 0.06, 0.14) years. The MR analysis showed evidence of positive causal effect of smoking behaviors on BAG: the effect of smoking is 0.21 (in years, 95% CI = 6.5 × 10-3 , 0.41; P-value = 0.04), and the effect of CPD is 0.16 year/cigarette (UKB: 95% CI = 0.06, 0.26; P-value = 1.3 × 10-3 ; GSCAN: 95% CI = 0.02, 0.31; P-value = 0.03). The sensitivity analyses showed consistent results.

CONCLUSIONS

There appears to be a significant causal effect of smoking on the brain age gap, which suggests that smoking prevention can be an effective intervention for accelerated brain aging and the age-related decline in cognitive function.

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

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

Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment

The gap between chronological age (CA) and biological brain age, as estimated from magnetic resonance images (MRIs), reflects how individual patterns of neuroanatomic aging deviate from their typical trajectories. MRI-derived brain age (BA) estimates are often obtained using deep learning models that may perform relatively poorly on new data or that lack neuroanatomic interpretability. This study introduces a convolutional neural network (CNN) to estimate BA after training on the MRIs of 4,681 cognitively normal (CN) participants and testing on 1,170 CN participants from an independent sample. BA estimation errors are notably lower than those of previous studies. At both individual and cohort levels, the CNN provides detailed anatomic maps of brain aging patterns that reveal sex dimorphisms and neurocognitive trajectories in adults with mild cognitive impairment (MCI, N = 351) and Alzheimer's disease (AD, N = 359). In individuals with MCI (54% of whom were diagnosed with dementia within 10.9 y from MRI acquisition), BA is significantly better than CA in capturing dementia symptom severity, functional disability, and executive function. Profiles of sex dimorphism and lateralization in brain aging also map onto patterns of neuroanatomic change that reflect cognitive decline. Significant associations between BA and neurocognitive measures suggest that the proposed framework can map, systematically, the relationship between aging-related neuroanatomy changes in CN individuals and in participants with MCI or AD. Early identification of such neuroanatomy changes can help to screen individuals according to their AD risk.

Gray matter volume drives the brain age gap in schizophrenia: a SHAP study

Neuroimaging-based brain age is a biomarker that is generated by machine learning (ML) predictions. The brain age gap (BAG) is typically defined as the difference between the predicted brain age and chronological age. Studies have consistently reported a positive BAG in individuals with schizophrenia (SCZ). However, there is little understanding of which specific factors drive the ML-based brain age predictions, leading to limited biological interpretations of the BAG. We gathered data from three publicly available databases - COBRE, MCIC, and UCLA - and an additional dataset (TOPSY) of early-stage schizophrenia (82.5% untreated first-episode sample) and calculated brain age with pre-trained gradient-boosted trees. Then, we applied SHapley Additive Explanations (SHAP) to identify which brain features influence brain age predictions. We investigated the interaction between the SHAP score for each feature and group as a function of the BAG. These analyses identified total gray matter volume (group × SHAP interaction term β = 1.71 [0.53; 3.23]; p_corr < 0.03) as the feature that influences the BAG observed in SCZ among the brain features that are most predictive of brain age. Other brain features also presented differences in SHAP values between SCZ and HC, but they were not significantly associated with the BAG. We compared the findings with a non-psychotic depression dataset (CAN-BIND), where the interaction was not significant. This study has important implications for the understanding of brain age prediction models and the BAG in SCZ and, potentially, in other psychiatric disorders.

Advanced brain age correlates with greater rumination and less mindfulness in schizophrenia

BACKGROUND

Individual variation in brain aging trajectories is linked with several physical and mental health outcomes. Greater stress levels, worry, and rumination correspond with advanced brain age, while other individual characteristics, like mindfulness, may be protective of brain health. Multiple lines of evidence point to advanced brain aging in schizophrenia (i.e., neural age estimate > chronological age). Whether psychological dimensions such as mindfulness, rumination, and perceived stress contribute to brain aging in schizophrenia is unknown.

METHODS

We estimated brain age from high-resolution anatomical scans in 54 healthy controls (HC) and 52 individuals with schizophrenia (SZ) and computed the brain predicted age difference (BrainAGE-diff), i.e., the delta between estimated brain age and chronological age. Emotional well-being summary scores were empirically derived to reflect individual differences in trait mindfulness, rumination, and perceived stress. Core analyses evaluated relationships between BrainAGE-diff and emotional well-being, testing for slopes differences across groups.

RESULTS

HC showed higher emotional well-being (greater mindfulness and less rumination/stress), relative to SZ. We observed a significant group difference in the relationship between BrainAge-diff and emotional well-being, explained by BrainAGE-diff negatively correlating with emotional well-being scores in SZ, and not in HC. That is, SZ with younger appearing brains (predicted age < chronological age) had emotional summary scores that were more like HC, a relationship that endured after accounting for several demographic and clinical variables.

CONCLUSIONS

These data reveal clinically relevant aspects of brain age heterogeneity among SZ and point to case-control differences in the relationship between advanced brain aging and emotional well-being.

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

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

Forensic age estimation from human blood using age-related microRNAs and circular RNAs markers

Aging is a complicated process characterized by progressive and extensive changes in physiological homeostasis at the organismal, tissue, and cellular levels. In modern society, age estimation is essential in a large variety of legal rights and duties. Accumulating evidence suggests roles for microRNAs (miRNAs) and circular RNAs (circRNAs) in regulating numerous processes during aging. Here, we performed circRNA sequencing in two age groups and analyzed microarray data of 171 healthy subjects (17-104 years old) downloaded from Gene Expression Omnibus (GEO) and ArrayExpress databases with integrated bioinformatics methods. A total of 1,403 circular RNAs were differentially expressed between young and old groups, and 141 circular RNAs were expressed exclusively in elderly samples while 10 circular RNAs were expressed only in young subjects. Based on their expression pattern in these two groups, the circular RNAs were categorized into three classes: age-related expression between young and old, age-limited expression-young only, and age-limited expression-old only. Top five expressed circular RNAs among three classes and a total of 18 differentially expressed microRNAs screened from online databases were selected to validate using RT-qPCR tests. An independent set of 200 blood samples (20-80 years old) was used to develop age prediction models based on 15 age-related noncoding RNAs (11 microRNAs and 4 circular RNAs). Different machine learning algorithms for age prediction were applied, including regression tree, bagging, support vector regression (SVR), random forest regression (RFR), and XGBoost. Among them, random forest regression model performed best in both training set (mean absolute error = 3.68 years, r = 0.96) and testing set (MAE = 6.840 years, r = 0.77). Models using one single type of predictors, circular RNAs-only or microRNAs-only, result in bigger errors. Smaller prediction errors were shown in males than females when constructing models according to different-sex separately. Putative microRNA targets (430 genes) were enriched in the cellular senescence pathway and cell homeostasis and cell differentiation regulation, indirectly indicating that the microRNAs screened in our study were correlated with development and aging. This study demonstrates that the noncoding RNA aging clock has potential in predicting chronological age and will be an available biological marker in routine forensic investigation to predict the age of biological samples.

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

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

Investigating the temporal pattern of neuroimaging-based brain age estimation as a biomarker for Alzheimer's Disease related neurodegeneration

Neuroimaging-based brain-age estimation via machine learning has emerged as an important new approach for studying brain aging. The difference between one's estimated brain age and chronological age, the brain age gap (BAG), has been proposed as an Alzheimer's Disease (AD) biomarker. However, most past studies on the BAG have been cross-sectional. Quantifying longitudinal changes in an individual's BAG temporal pattern would likely improve prediction of AD progression and clinical outcome based on neurophysiological changes. To fill this gap, our study conducted predictive modeling using a large neuroimaging dataset with up to 8 years of follow-up to examine the temporal patterns of the BAG's trajectory and how it varies by subject-level characteristics (sex, APOEɛ4 carriership) and disease status. Specifically, we explored the pattern and rate of change in BAG over time in individuals who remain stable with normal cognition or mild cognitive impairment (MCI), as well as individuals who progress to clinical AD. Combining multimodal imaging data in a support vector regression model to estimate brain age yielded improved performance over single modality. Multilevel modeling results showed the BAG followed a linear increasing trajectory with a significantly faster rate in individuals with MCI who progressed to AD compared to cognitively normal or MCI individuals who did not progress. The dynamic changes in the BAG during AD progression were further moderated by sex and APOEɛ4 carriership. Our findings demonstrate the BAG as a potential biomarker for understanding individual specific temporal patterns related to AD progression.

Brain age estimation reveals older adults' accelerated senescence after traumatic brain injury

Adults aged 60 and over are most vulnerable to mild traumatic brain injury (mTBI). Nevertheless, the extent to which chronological age (CA) at injury affects TBI-related brain aging is unknown. This study applies Gaussian process regression to T1-weighted magnetic resonance images (MRIs) acquired within [Formula: see text]7 days and again [Formula: see text]6 months after a single mTBI sustained by 133 participants aged 20-83 (CA [Formula: see text] = 42.6 ± 17 years; 51 females). Brain BAs are estimated, modeled, and compared as a function of sex and CA at injury using a statistical model selection procedure. On average, the brains of older adults age by 15.3 ± 6.9 years after mTBI, whereas those of younger adults age only by 1.8 ± 5.6 years, a significant difference (Welch's t32 =  - 9.17, p ≃ 9.47 × 10-11). For an adult aged [Formula: see text]30 to [Formula: see text]60, the expected amount of TBI-related brain aging is [Formula: see text]3 years greater than in an individual younger by a decade. For an individual over [Formula: see text]60, the respective amount is [Formula: see text]7 years. Despite no significant sex differences in brain aging (Welch's t108 = 0.78, p > 0.78), the statistical test is underpowered. BAs estimated at acute baseline versus chronic follow-up do not differ significantly (t264 = 0.41, p > 0.66, power = 80%), suggesting negligible TBI-related brain aging during the chronic stage of TBI despite accelerated aging during the acute stage. Our results indicate that a single mTBI sustained after age [Formula: see text]60 involves approximately [Formula: see text]10 years of premature and lasting brain aging, which is MRI detectable as early as [Formula: see text]7 days post-injury.

Modeling multivariate age-related imaging variables with dependencies

Neuroimaging techniques have been increasingly used to understand the neural biology of aging brains. The neuroimaging variables from distinct brain locations and modalities can exhibit age-related patterns that reflect localized neural decline. However, it is a challenge to identify the impacts of risk factors (eg, mental disorders) on multivariate imaging variables while simultaneously accounting for the dependence structure and nonlinear age trajectories using existing tools. We propose a mixed-effects model to address this challenge by building random effects based on the latent brain aging status. We develop computationally efficient algorithms to estimate the parameters of new random effects. The simulations show that our approach provides accurate parameter estimates, improves the inference efficiency, and reduces the root mean square error compared to existing methods. We further apply this method to the UK Biobank data to investigate the effects of tobacco smoking on the white matter integrity of the entire brain during aging and identify the adverse effects on white matter integrity with multiple fiber tracts.

The age of violence: Mapping brain age in psychosis and psychopathy

Young chronological age is one of the strongest predictors for antisocial behaviour in the general population and for violent offending in individuals with psychotic disorders. An individual's age can be predicted with high accuracy using neuroimaging and machine-learning. The deviation between predicted and chronological age, i.e., brain age gap (BAG) has been suggested to reflect brain health, likely relating partly to neurodevelopmental and aging-related processes and specific disease mechanisms. Higher BAG has been demonstrated in patients with psychotic disorders. However, little is known about the brain-age in violent offenders with psychosis and the possible associations with psychopathy traits. We estimated brain-age in 782 male individuals using T1-weighted MRI scans. Three machine learning models (random forest, extreme gradient boosting with and without hyper parameter tuning) were first trained and tested on healthy controls (HC, n = 586). The obtained BAGs were compared between HC and age matched violent offenders with psychosis (PSY-V, n = 38), violent offenders without psychosis (NPV, n = 20) and non-violent psychosis patients (PSY-NV, n = 138). We ran additional comparisons between BAG of PSY-V and PSY-NV and associations with Positive and Negative Syndrome Scale (PANSS) total score as a measure of psychosis symptoms. Psychopathy traits in the violence groups were assessed with Psychopathy Checklist-revised (PCL-R) and investigated for associations with BAG. We found significantly higher BAG in PSY-V compared with HC (4.9 years, Cohen'sd = 0.87) and in PSY-NV compared with HC (2.7 years, d = 0.41). Total PCL-R scores were negatively associated with BAG in the violence groups (d = 1.17, p < 0.05). Additionally, there was a positive association between psychosis symptoms and BAG in the psychosis groups (d = 1.12, p < 0.05). While the significant BAG differences related to psychosis and not violence suggest larger BAG for psychosis, the negative associations between BAG and psychopathy suggest a complex interplay with psychopathy traits. This proof-of-concept application of brain age prediction in severe mental disorders with a history of violence and psychopathy traits should be tested and replicated in larger samples.

Deep Relation Learning for Regression and Its Application to Brain Age Estimation

Most deep learning models for temporal regression directly output the estimation based on single input images, ignoring the relationships between different images. In this paper, we propose deep relation learning for regression, aiming to learn different relations between a pair of input images. Four non-linear relations are considered: "cumulative relation," "relative relation," "maximal relation" and "minimal relation." These four relations are learned simultaneously from one deep neural network which has two parts: feature extraction and relation regression. We use an efficient convolutional neural network to extract deep features from the pair of input images and apply a Transformer for relation learning. The proposed method is evaluated on a merged dataset with 6,049 subjects with ages of 0-97 years using 5-fold cross-validation for the task of brain age estimation. The experimental results have shown that the proposed method achieved a mean absolute error (MAE) of 2.38 years, which is lower than the MAEs of 8 other state-of-the-art algorithms with statistical significance (p<0.05) in paired T-test (two-side).

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

Background

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

Methods

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

Findings

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

Conclusion

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

Estimation of biological heart age using cardiovascular magnetic resonance radiomics

We developed a novel interpretable biological heart age estimation model using cardiovascular magnetic resonance radiomics measures of ventricular shape and myocardial character. We included 29,996 UK Biobank participants without cardiovascular disease. Images were segmented using an automated analysis pipeline. We extracted 254 radiomics features from the left ventricle, right ventricle, and myocardium of each study. We then used Bayesian ridge regression with tenfold cross-validation to develop a heart age estimation model using the radiomics features as the model input and chronological age as the model output. We examined associations of radiomics features with heart age in men and women, observing sex-differential patterns. We subtracted actual age from model estimated heart age to calculate a "heart age delta", which we considered as a measure of heart aging. We performed a phenome-wide association study of 701 exposures with heart age delta. The strongest correlates of heart aging were measures of obesity, adverse serum lipid markers, hypertension, diabetes, heart rate, income, multimorbidity, musculoskeletal health, and respiratory health. This technique provides a new method for phenotypic assessment relating to cardiovascular aging; further studies are required to assess whether it provides incremental risk information over current approaches.