Ten Years of BrainAGE as a Neuroimaging Biomarker of Brain Aging: What Insights Have We Gained?

Brain Age Gap Associations with Body Composition and Metabolic Indices in an Asian Cohort: An MRI-Based Study

BACKGROUND

Global aging raises concerns about cognitive health, metabolic disorders, and sarcopenia. Prevention of reversible decline and diseases in middle-aged individuals is essential for promoting healthy aging. We hypothesize that changes in body composition, specifically muscle mass and visceral fat, and metabolic indices are associated with accelerated brain aging. To explore these relationships, we employed a brain age model to investigate the links between the brain age gap (BAG), body composition, and metabolic markers.

METHODS

Using T1-weighted anatomical brain MRIs, we developed a machine learning model to predict brain age from gray matter features, trained on 2,675 healthy individuals aged 18-92 years. This model was then applied to a separate cohort of 458 Taiwanese adults (57.8 years ± 11.6; 280 men) to assess associations between BAG, body composition quantified by MRI, and metabolic markers.

RESULTS

Our model demonstrated reliable generalizability for predicting individual age in the clinical dataset (MAE = 6.11 years, r = 0.900). Key findings included significant correlations between larger BAG and reduced total abdominal muscle area (r = -0.146, p = 0.018), lower BMI-adjusted skeletal muscle indices, (r = -0.134, p = 0.030), increased systemic inflammation, as indicated by high-sensitivity C-reactive protein levels (r = 0.121, p = 0.048), and elevated fasting glucose levels (r = 0.149, p = 0.020).

CONCLUSIONS

Our findings confirm that muscle mass and metabolic health decline are associated with accelerated brain aging. Interventions to improve muscle health and metabolic control may mitigate adverse effects of brain aging, supporting healthier aging trajectories.

Brain age prediction based on brain region volume modeling under broad network field of view

BACKGROUND AND OBJECTIVE

Brain region volume from Structural Magnetic Resonance Imaging (sMRI) can directly reflect abnormal states in brain aging. While promising for clinical brain health assessment, existing volume-based brain age prediction methods fail to explore both linear and nonlinear relationships, resulting in weak representation and suboptimal estimates.

METHODS

This paper proposes a brain age prediction method, RFBLSO, based on Random Forest (RF), Broad Learning System (BLS), and Leave-One-Out Cross Validation (LOO). Firstly, RF is used to eliminate redundant brain regions with low correlation to the target value. The objective function is constructed by integrating feature nodes, enhancement nodes, and optimal regularization parameters. Subsequently, the pseudo-inverse method is employed to solve for the output coefficients, which facilitates a more accurate representation of the linear and nonlinear relationships between volume features and brain age.

RESULTS

Across various datasets, RFBLSO demonstrates the capability to formulate brain age prediction models, achieving a Mean Absolute Error (MAE) of 4.60 years within the Healthy Group and 4.98 years within the Chinese2020 dataset. In the Clinical Group, RFBLSO achieves measurement and effective differentiation among Healthy Controls (HC), Mild Cognitive Impairment (MCI), and Alzheimer's disease (AD) (MAE for HC, MCI, and AD: 4.46 years, 8.77 years, 13.67 years; the effect size η2 of the analysis of variance for AD/MCI vs. HC is 0.23; the effect sizes of post-hoc tests are Cohen's d = 0.74 (AD vs. MCI), 1.50 (AD vs. HC), 0.77 (MCI vs. HC)). Compared to other linear or nonlinear brain age prediction methods, RFBLSO offers more accurate measurements and effectively distinguishes between Clinical Groups. This is because RFBLSO can simultaneously explore both linear and nonlinear relationships between brain region volume and brain age.

CONCLUSION

The proposed RFBLSO effectively represents both linear and nonlinear relationships between brain region volume and brain age, allowing for more accurate individual brain age estimation. This provides a feasible method for predicting the risk of neurodegenerative diseases.

Accelerometer-Measured Physical Activity and Neuroimaging-Driven Brain Age

Background: A neuroimaging-derived biomarker termed the brain age is considered to capture the degree and diversity in the aging process of the brain, serving as a robust indicator of overall brain health. The impact of different levels of physical activity (PA) intensities on brain age is still not fully understood. This study aimed to investigate the associations between accelerometer-measured PA and brain age. Methods: A total of 16,972 eligible participants with both valid T 1-weighted neuroimaging and accelerometer data from the UK Biobank was included. Brain age was estimated using an ensemble learning approach called Light Gradient-Boosting Machine (LightGBM). Over 1,400 image-derived phenotypes (IDPs) were initially chosen to undergo data-driven feature selection for brain age prediction. A measure of accelerated brain aging, the brain age gap (BAG) can be derived by subtracting the chronological age from the estimated brain age. A positive BAG indicates accelerated brain aging. PA was measured over a 7-day period using wrist-worn accelerometers, and time spent on light-intensity PA (LPA), moderate-intensity PA (MPA), vigorous-intensity PA (VPA), and moderate- to vigorous-intensity PA (MVPA) was extracted. The generalized additive model was applied to examine the nonlinear association between PA and BAG after adjusting for potential confounders. Results: The brain age estimated by LightGBM achieved an appreciable performance (r = 0.81, mean absolute error [MAE] = 3.65), which was further improved by age bias correction (r = 0.90, MAE = 3.03). We found that LPA (F = 2.47, P = 0.04), MPA (F = 6.49, P < 1 × 10-300), VPA (F = 4.92, P = 2.58 × 10-5), and MVPA (F = 6.45, P < 1 × 10-300) exhibited an approximate U-shaped relationship with BAG, demonstrating that both insufficient and excessive PA levels adversely impact brain aging. Furthermore, mediation analysis suggested that BAG partially mediated the associations between PA and cognitive functions as well as brain-related disorders. Conclusions: Our study revealed a U-shaped association between accelerometer-measured PA and BAG, highlighting that advanced brain health may be attainable through engaging in moderate amounts of objectively measured PA irrespectively of intensities.

Exploring the values underlying machine learning research in medical image analysis

Machine learning has emerged as a crucial tool for medical image analysis, largely due to recent developments in deep artificial neural networks addressing numerous, diverse clinical problems. As with any conceptual tool, the effective use of machine learning should be predicated on an understanding of its underlying motivations just as much as algorithms or theory - and to do so, we need to explore its philosophical foundations. One of these foundations is the understanding of how values, despite being non-empirical, nevertheless affect scientific research. This article has three goals: to introduce the reader to values in a way that is specific to medical image analysis; to characterise a particular set of technical decisions (what we call the end-to-end vs. separable learning spectrum) that are fundamental to machine learning for medical image analysis; and to create a simple and structured method to show how these values can be rigorously connected to these technical decisions. This better understanding of how the philosophy of science can clarify fundamental elements of how medical image analysis research is performed and can be improved.

Hyperfusion: A hypernetwork approach to multimodal integration of tabular and medical imaging data for predictive modeling

The integration of diverse clinical modalities such as medical imaging and the tabular data extracted from patients' Electronic Health Records (EHRs) is a crucial aspect of modern healthcare. Integrative analysis of multiple sources can provide a comprehensive understanding of the clinical condition of a patient, improving diagnosis and treatment decision. Deep Neural Networks (DNNs) consistently demonstrate outstanding performance in a wide range of multimodal tasks in the medical domain. However, the complex endeavor of effectively merging medical imaging with clinical, demographic and genetic information represented as numerical tabular data remains a highly active and ongoing research pursuit. We present a novel framework based on hypernetworks to fuse clinical imaging and tabular data by conditioning the image processing on the EHR's values and measurements. This approach aims to leverage the complementary information present in these modalities to enhance the accuracy of various medical applications. We demonstrate the strength and generality of our method on two different brain Magnetic Resonance Imaging (MRI) analysis tasks, namely, brain age prediction conditioned by subject's sex and multi-class Alzheimer's Disease (AD) classification conditioned by tabular data. We show that our framework outperforms both single-modality models and state-of-the-art MRI tabular data fusion methods. A link to our code can be found at https://github.com/daniel4725/HyperFusion.

Adherence to life's essential 8 is associated with delayed white matter aging

BACKGROUND

The American Heart Association introduced Life's Essential 8 (LE8) to promote cardiovascular health and longevity. However, its impact on brain ageing and interactions with genetic risk factors of dementia, such as APOE4, remains unclear. This study investigates the relationship between LE8 and white matter brain ageing and evaluates the moderating effects of the APOE4 allele.

METHODS

This cross-sectional study utilized data from the UK Biobank, including genetic, neuroimaging, and health-related data from touchscreen questionnaires, physical examinations, and biological samples. Participants were non-pregnant whites with LE8 variables, diffusion tensor imaging (DTI) data, and APOE4 genetic information available, excluding those with extreme white matter hyperintensities. Regional fractional anisotropy measures from DTI data were used to predict white matter brain age via random forest regression. The white matter brain age gap (BAG) was calculated by subtracting chronological age from predicted brain age.

FINDINGS

The analysis included 18,817 participants (9430 women and 9387 men; mean age 55.45 years [SD: 7.46]). Higher LE8 scores were associated with a lower white matter BAG, indicating delayed brain ageing. The effect was more pronounced in non-APOE4 carriers (124 days younger per 10-point increase, 95% CI: 102-146 days; p < 0.001) compared to APOE4 carriers (84 days younger per 10-point increase, 95% CI: 47-120 days; p < 0.001). Potential interaction between APOE4 and LE8 on brain ageing was observed for some age and sex groups but with only borderline significance, further investigation in larger and more targeted studies is needed to validate the finding.

INTERPRETATION

Adherence to LE8 is associated with delayed brain ageing, with genetic factors such as APOE4 potentially moderating this effect in specific age and sex groups. The overall benefit from a healthier lifestyle in individuals' brain ageing across genetic, sex, and age groups underscore the importance and broad applicability of behavioural lifestyle interventions in promoting brain health.

FUNDING

US National Institute of Health, University of Maryland, Montgomery County of Maryland.

Neuroimaging-derived biological brain age and its associations with glial reactivity and synaptic dysfunction cerebrospinal fluid biomarkers

Magnetic resonance Imaging (MRI)-derived brain-age prediction is a promising biomarker of biological brain aging. Accelerated brain aging has been found in Alzheimer's disease (AD) and other neurodegenerative diseases. However, no previous studies have investigated the relationship between specific pathophysiological pathways in AD and biological brain aging. Here, we studied whether glial reactivity and synaptic dysfunction are associated with biological brain aging in the earliest stages of the Alzheimer's continuum, and if these mechanisms are differently associated with AD-related cortical atrophy. We further evaluated their effects on cognitive decline. We included 380 cognitively unimpaired individuals from the ALFA+ study, for which we computed their brain-age deltas by subtracting chronological age from their brain age predicted by machine learning algorithms. We studied the cross-sectional linear associations between brain-age delta and cerebrospinal fluid (CSF) biomarkers of synaptic dysfunction (neurogranin, GAP43, synaptotagmin-1, SNAP25, and α-synuclein), glial reactivity (sTREM2, YKL-40, GFAP, and S100b) and inflammation (interleukin-6). We also studied the cross-sectional linear associations between AD signature and these CSF biomarkers, We further evaluated the mechanisms linking baseline brain-age delta and longitudinal cognitive decline by performing mediation analyses. To reproduce our findings on an independent cohort, we included 152 cognitively unimpaired and 310 mild cognitive impaired (MCI) individuals from the ADNI study. We found that higher CSF sTREM2 was associated with a younger brain-age after adjusting for AD pathology, both in ALFA+ cognitively unimpaired and in ADNI MCI individuals. Furthermore, we found that CSF sTREM2 fully mediated the link between older brain-age and cognitive decline in ALFA+. In summary, we showed that the protective microglial state reflected by higher CSF sTREM2 has a beneficial impact on biological brain aging that may partly explains the variability in cognitive decline in early AD stages, independently of AD pathology.

Electroencephalography estimates brain age in infants with high precision: Leveraging advanced machine learning in healthcare

Changes in the pace of neurodevelopment are key indicators of atypical maturation during early life. Unfortunately, reliable prognostic tools rely on assessments of cognitive and behavioral skills that develop towards the second year of life and after. Early assessment of brain maturation using electroencephalography (EEG) is crucial for clinical intervention and care planning. We developed a reliable methodology using conventional machine learning (ML) and novel deep learning (DL) networks to efficiently quantify the difference between chronological and biological age, so-called brain age gap (BAG) as a marker of accelerated/decelerated biological brain development. In this cross-sectional study, EEG from 219 typically-developing infants aged from three to 14-months was used. For DL networks, the input samples were increased to 2628 recordings. We further validated the BAG tool in a population at clinical risk with abnormal brain growth (macrocephaly) to capture deviation from normal aging. Our results indicate that DL networks outperform conventional ML models, capturing complex non-monotonic EEG characteristics and predicting the biological age with a mean absolute error of only one month (MAE = 1 month, 95 %CI:0.88-1.15, r = 0.82, 95 %CI:0.78-0.85). Additionally, the developing brain follows a trajectory characterized by increased non-linearity and complexity in which alpha rhythm plays an important role. BAG could detect group-level maturational delays between typically-developing and macrocephaly (pvalue=0.009). In macrocephaly, BAG negatively correlated with the general adaptive composite of the ABAS-II (pvalue=0.04) at 18-months and the information processing speed scale of the WPSSI-IV at age four (pvalue=0.006). The EEG-based BAG score offers a reliable non-invasive measure of brain maturation, with significant advantages and implications for developmental neuroscience and clinical practice.

Advanced Brain Age Prediction Using Multi-Head Self-Attention: A Comparative Analysis of Western and Middle Eastern MRI Datasets

Brain age estimation is a critical biomarker for early detection of neurodegenerative diseases, but existing models are primarily trained on Western datasets, limiting their applicability to diverse populations. Recent studies suggest that brain aging patterns vary across ethnic groups, highlighting the need for more inclusive and adaptable AI-driven neuroimaging models. We trained our model on 4,635 healthy individuals (40-80 years) from ADNI, OASIS-3, Cam-CAN, and IXI, using 80% of data (n=3700) for training and 20% (n=935) for testing. The model was further tested on a Middle Eastern dataset (107 subjects, Tehran, Iran). It integrates multi-head self-attention along with residual connections to enhance long-range spatial feature learning, improving upon previous CNN models. Performance was evaluated using mean absolute error (MAE). The model achieved state-of-the-art accuracy (MAE = 1.99 years) on the Western test set, while being much lighter than previous models (approximately 3 million parameters); however, it performed significantly worse on the ME dataset (best MAE = 4.35 years, final = 5.83 years). Bias correction did not improve performance, indicating population-specific brain aging differences. These findings emphasize the need for diverse training datasets and cross-population adaptation techniques.

Maintaining Brain Health: The Impact of Physical Activity and Fitness on the Aging Brain-A UK Biobank Study

The growing prevalence of physical and neurological disorders linked to aging poses significant challenges for society. Many of these disorders are closely linked to changes in brain structure and function, highlighting the importance of identifying protective factors that can preserve brain structure in later life and mitigate age-related decline. Physical activity (PA) is consistently linked to physical health and was found to mitigate age-related disorders. However, its effects on markers of brain aging remain inconclusive, partly due to reliance on underpowered studies and self-reported data. We investigated the effects of accelerometer-measured PA and physical fitness on BrainAGE, a machine-learning-derived marker of brain aging, in a large UK Biobank cohort. Using cortical and subcortical neuroimaging-derived features, a BrainAGE model was trained on 21,442 participants (mean absolute error: 3.75 years) and applied to predict BrainAGE for an independent sample of 10,874 participants. Accelerometer-measured moderate-intensity PA, but not self-reported PA, was associated with decelerated brain aging, indicated by a negative BrainAGE. Further, higher hand grip strength, along with lower body mass index (BMI), diastolic blood pressure (DBP), and resting heart rate, was linked to decelerated aging. These fitness measures impacted BrainAGE independently of PA. Additionally, fitness partially accounted for the relationship between PA and BrainAGE. Specifically, BMI, DBP, and resting heart rate showed a significant mediating effect, while grip strength did not. These findings highlight the interplay between PA and fitness in maintaining brain health and provide valuable insights for neuroscience and preventive health measures.

Brain Age as a New Measure of Disease Stratification in Huntington's Disease

BACKGROUND

Despite advancements in understanding Huntington's disease (HD) over the past two decades, absence of disease-modifying treatments remains a challenge. Accurately characterizing progression states is crucial for developing effective therapeutic interventions. Various factors contribute to this challenge, including the need for precise methods that can account for the complex nature of HD progression.

OBJECTIVE

This study aims to address this gap by leveraging the concept of the brain's biological age as a foundation for a data-driven clustering method to delineate various states of progression. Brain-predicted age, influenced by somatic expansion and its impact on brain volumes, offers a promising avenue for stratification by stratifying subgroups and determining the optimal timing for interventions.

METHODS

To achieve this, data from 953 participants across diverse cohorts, including PREDICT-HD, TRACK-HD, and IMAGE-HD, were meticulously analyzed. Brain-predicted age was computed using sophisticated algorithms, and participants were categorized into four groups based on CAG and age product score. Unsupervised k-means clustering with brain-predicted age difference (brain-PAD) was then employed to identify distinct progression states.

RESULTS

The analysis revealed significant disparities in brain-predicted age between HD participants and controls, with these differences becoming more pronounced as the disease progressed. Brain-PAD demonstrated a correlation with disease severity, effectively identifying five distinct progression states characterized by significant longitudinal disparities.

CONCLUSIONS

These findings highlight the potential of brain-PAD in capturing HD progression states, thereby enhancing prognostic methodologies and providing valuable insights for future clinical trial designs and interventions. © 2025 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Neuropsychiatric symptoms and neuroimaging-based brain age in mild cognitive impairment and early dementia: A multicenter study

AIM

Despite the clinical importance and significant social burden of neuropsychiatric symptoms (NPS) in dementia, the underlying neurobiological mechanism remains poorly understood. Recently, neuroimaging-derived brain-age estimation by machine-learning analysis has shown promise as an individual-level biomarker. We investigated the relationship between NPS and brain-age in amnestic mild cognitive impairment (MCI) and early dementia.

METHODS

In this cross-sectional study, clinical data, including neuropsychiatric inventory (NPI), and structural brain MRI of 499 individuals with clinical diagnoses of amnestic MCI (n = 185), early Alzheimer's disease (AD) (n = 258) or dementia with Lewy bodies (DLB) (n = 56) were analyzed. We established a brain-age prediction model using 694 healthy brain MRIs and a support vector regression model and applied it to the participants' data. Finally, the brain-predicted age difference (brain-PAD: predicted age minus chronological age) was calculated.

RESULTS

All groups showed significantly increased brain-PAD, and the median (IQR) brain-PAD was 4.3 (5.4) years in MCI, 6.3 (6.2) years in AD, and 5.0 (6.5) years in DLB. The NPI scores were subdivided into the following four categories: (i) Agitation and Irritability, (ii) Depression and Apathy, (iii) Delusions and Hallucinations, and (iv) Euphoria and Disinhibition. We found a significantly positive correlation between brain-PAD and the depression/apathy factor (Spearman's rs = 0.156, FDR-corrected P = 0.002), whereas no significance was shown for the other NPS factors.

CONCLUSION

Higher brain-age may be associated with depression and apathy symptoms presented in MCI to early dementia stages, and brain-age analysis may be useful as a novel biomarker for the assessment or monitoring of NPS.

Resting-state functional connectivity correlates of brain structural aging in schizophrenia

A large body of research has shown that schizophrenia patients demonstrate increased brain structural aging. Although this process may be coupled with aberrant changes in intrinsic functional architecture of the brain, they remain understudied. We hypothesized that there are brain regions whose whole-brain functional connectivity at rest is differently associated with brain structural aging in schizophrenia patients compared to healthy controls. Eighty-four male schizophrenia patients and eighty-six male healthy controls underwent structural MRI and resting-state fMRI. The brain-predicted age difference (b-PAD) was a measure of brain structural aging. Resting-state fMRI was applied to obtain global correlation (GCOR) maps comprising voxelwise values of the strength and sign of functional connectivity of a given voxel with the rest of the brain. Schizophrenia patients had higher b-PAD compared to controls (mean between-group difference + 2.9 years). Greater b-PAD in schizophrenia patients, compared to controls, was associated with lower whole-brain functional connectivity of a region in frontal orbital cortex, inferior frontal gyrus, Heschl's Gyrus, plana temporale and polare, insula, and opercular cortices of the right hemisphere (rFTI). According to post hoc seed-based correlation analysis, decrease of functional connectivity with the posterior cingulate gyrus, left superior temporal cortices, as well as right angular gyrus/superior lateral occipital cortex has mainly driven the results. Lower functional connectivity of the rFTI was related to worse verbal working memory and language production. Our findings demonstrate that well-established frontotemporal functional abnormalities in schizophrenia are related to increased brain structural aging.

Increased Brain Age Among Psychiatrically Healthy Adults Exposed to Childhood Trauma

BACKGROUND

Adults with childhood trauma exposure may exhibit brain changes typically associated with aging and neurodegeneration (e.g., reduced tissue volume or integrity) to a greater degree than their unexposed counterparts, suggesting accelerated brain aging. Machine learning methods that predict a person's age based on their magnetic resonance imaging (MRI) brain scan may be useful for investigating aberrant brain aging following childhood trauma exposure. Emerging evidence indicates altered brain aging in adolescents with childhood trauma exposure; however, this association has not been examined in healthy adults.

METHODS

We investigated the associations between childhood trauma exposure, including abuse and neglect, and brain-predicted age in psychiatrically healthy adults. "Brain age" predictions were generated from T1-weighted structural MRI scans using a pre-trained machine learning pipeline, namely brainageR. The differences between brain-predicted age and chronological age were calculated and associations with childhood trauma questionnaire scores were investigated using linear regression.

RESULTS

The final sample (n = 153; mean age 46 ± 16 years, 70% female) included 69 adults with childhood trauma exposure and 84 unexposed adults. Childhood sexual abuse was associated with an average increased brain age of 3.2 years, adjusting for chronological age and age-squared, sex, and scanner site; however, this finding did not survive correction for multiple comparisons.

CONCLUSIONS

To our knowledge, this study represents the first published investigation of brain age in adults with childhood trauma using a machine-learning-based prediction model. Our findings suggest a link between childhood trauma exposure, specifically sexual abuse, and accelerated brain aging in adulthood, but this association should be replicated in future work. Accentuated brain aging in adulthood may increase the risk of age-related cognitive and neurodegenerative decline and associated disorders later in life.

Enhancing Brain Age Prediction and Neurodegeneration Detection with Contrastive Learning on Regional Biomechanical Properties

The aging process affects brain structure and function, yet its biomechanical properties remain underexplored. Magnetic Resonance Elastography (MRE) provides a unique perspective by mapping brain tissue stiffness and damping ratio, observables that correlate with age and disease. Using a self-supervised contrastive regression framework, we demonstrate that MRE surpasses conventional structural magnetic resonance imaging (MRI) in sensitivity. Specifically, stiffness captures Alzheimer's disease (AD), while damping ratio detects subtle changes associated with mild cognitive impairment (MCI). Our regional analysis identifies deep brain structures, particularly the caudate and thalamus, as key biomarkers of aging. The greater age sensitivity of MRE translates to superior differentiation of AD and MCI from healthy individuals, pinpointing regions where significant biomechanical alterations occur, notably the thalamus in AD and hippocampus in MCI. Furthermore, our results reveal biomechanical alterations in cognitively healthy individuals whose aging profiles closely resemble patients with MCI and AD. These findings highlight MRE's potential as a biomarker for early neurodegenerative changes, aiding dementia risk detection and early intervention.

Brain Aging in Specific Phobia: An ENIGMA-Anxiety Mega-Analysis

Introduction

Specific phobia (SPH) is a prevalent anxiety disorder and may involve advanced biological aging. However, brain age research in psychiatry has primarily examined mood and psychotic disorders. This mega-analysis investigated brain aging in SPH participants within the ENIGMA-Anxiety Working Group.

Methods

3D brain structural MRI scans from 17 international samples (600 SPH individuals, of whom 504 formally diagnosed and 96 questionnaire-based cases; 1,134 controls; age range: 22-75 years) were processed with FreeSurfer. Brain age was estimated from 77 subcortical and cortical regions with a publicly available ENIGMA brain age model. The brain-predicted age difference (brain-PAD) was calculated as brain age minus chronological age. Linear mixed-effect models examined group differences in brain-PAD and moderation by age.

Results

No significant group difference in brain-PAD manifested (β diagnosis (SE)=0.37 years (0.43), p=0.39). A negative diagnosis-by-age interaction was identified, which was most pronounced in formally diagnosed SPH (β diagnosis-by-age=-0.08 (0.03), pFDR=0.02). This interaction remained significant when excluding participants with anxiety comorbidities, depressive comorbidities, and medication use. Post-hoc analyses revealed a group difference for formal SPH diagnosis in younger participants (22-35 years; β diagnosis=1.20 (0.60), p<0.05, mixed-effects d (95% confidence interval)=0.14 (0.00-0.28)), but not older participants (36-75 years; β diagnosis=0.07 (0.65), p=0.91).

Conclusions

Brain aging did not relate to SPH in the full sample. However, a diagnosis-by-age interaction was observed across analyses, and was strongest in formally diagnosed SPH. Post-hoc analyses showed a subtle advanced brain aging in young adults with formally diagnosed SPH. Taken together, these findings indicate the importance of clinical severity, impairment and persistence, and may suggest a slightly earlier end to maturational processes or subtle decline of brain structure in SPH.

Report of the Medical Image De-Identification (MIDI) Task Group -- Best Practices and Recommendations

This report addresses the technical aspects of de-identification of medical images of human subjects and biospecimens, such that re-identification risk of ethical, moral, and legal concern is sufficiently reduced to allow unrestricted public sharing for any purpose, regardless of the jurisdiction of the source and distribution sites. All medical images, regardless of the mode of acquisition, are considered, though the primary emphasis is on those with accompanying data elements, especially those encoded in formats in which the data elements are embedded, particularly Digital Imaging and Communications in Medicine (DICOM). These images include image-like objects such as Segmentations, Parametric Maps, and Radiotherapy (RT) Dose objects. The scope also includes related non-image objects, such as RT Structure Sets, Plans and Dose Volume Histograms, Structured Reports, and Presentation States. Only de-identification of publicly released data is considered, and alternative approaches to privacy preservation, such as federated learning for artificial intelligence (AI) model development, are out of scope, as are issues of privacy leakage from AI model sharing. Only technical issues of public sharing are addressed.

Genetically supported targets and drug repurposing for brain aging: A systematic study in the UK Biobank

Brain age gap (BAG), the deviation between estimated brain age and chronological age, is a promising marker of brain health. However, the genetic architecture and reliable targets for brain aging remains poorly understood. In this study, we estimate magnetic resonance imaging (MRI)-based brain age using deep learning models trained on the UK Biobank and validated with three external datasets. A genome-wide association study for BAG identified two unreported loci and seven previously reported loci. By integrating Mendelian Randomization (MR) and colocalization analysis on eQTL and pQTL data, we prioritized seven genetically supported druggable genes, including MAPT, TNFSF12, GZMB, SIRPB1, GNLY, NMB, and C1RL, as promising targets for brain aging. We rediscovered 13 potential drugs with evidence from clinical trials of aging and prioritized several drugs with strong genetic support. Our study provides insights into the genetic basis of brain aging, potentially facilitating drug development for brain aging to extend the health span.

Caregiving is associated with lower brain age in humans

Middle-aged adults who are parents have better average cognitive performance and lower average brain age compared with middle-aged adults without children, raising the possibility that caregiving slows brain aging. Here, we investigate this hypothesis in two additional groups of caregivers: grandmothers and caregivers for people living with dementia (PLWD). Demographic, questionnaire, and structural Magnetic Resonance Imaging (MRI) data were acquired from n = 50 grandmothers, n = 24 caregivers of PLWD, and n = 37 non-caregiver controls, and BrainAGE was estimated. BrainAGE estimation results suggest that after controlling for relevant covariates, grandmothers had a brain age that was 5.5 years younger than non-grandmother controls, and caregivers of PLWD had brains that were 4.7 years younger than non-caregiver controls. Women who became grandmothers at a later age had lower brain age than those who became grandmothers at an earlier age. Among caregivers of PLWD, stress and caregiving burden were associated with increased brain age, such that the beneficial effect of caregiving on brain age was reduced in caregivers reporting more burden. Our findings suggest that caring for dependents may slow brain aging.

Unravelling pathological ageing with brain age gap estimation in Alzheimer's disease, diabetes and schizophrenia

Brain age gap estimation (BrainAGE), the difference between predicted brain age and chronological age, might be a putative biomarker aiming to detect the transition from healthy to pathological brain ageing. The biomarker primarily models healthy ageing with machine learning models trained with structural magnetic resonance imaging (MRI) data. BrainAGE is expected to translate the deviations in neural ageing trajectory and has been shown to be increased in multiple pathologies, such as Alzheimer's disease (AD), schizophrenia and Type 2 diabetes (T2D). Thus, accelerated ageing seems to be a general feature of neuropathological processes. However, neurobiological constraints remain to be identified to provide specificity to this biomarker. Explainability might be the key to uncovering age predictions and understanding which brain regions lead to an elevated predicted age on a given pathology compared to healthy controls. This is highly relevant to understanding the similarities and differences in neurodegeneration in AD and T2D, which remains an outstanding biological question. Sensitivity maps explain models by computing the importance of each voxel on the final prediction, thereby contributing to the interpretability of deep learning approaches. This paper assesses whether sensitivity maps yield different results across three conditions related to pathological neural ageing: AD, schizophrenia and T2D. Five deep learning models were considered, each model trained with different MRI data types: minimally processed T1-weighted brain scans, and corresponding grey matter, white matter, cerebrospinal fluid tissue segmentation and deformation fields (after spatial normalization). Our results revealed an increased BrainAGE in all pathologies, with a different mean, which is the smallest in schizophrenia; this is in line with the observation that neural loss is secondary in this early-onset condition. Importantly, our findings suggest that the sensitivity, indexing regional weights, for all models varies with age. A set of regions were shown to yield statistical differences across conditions. These sensitivity results suggest that mechanisms of neurodegeneration are quite distinct in AD and T2D. For further validation, the sensitivity and the morphometric maps were compared. The findings outlined a high congruence between the sensitivity and morphometry maps for age and clinical group conditions. Our evidence outlines that the biological explanation of model predictions is vital in adding specificity to the BrainAGE and understanding the pathophysiology of chronic conditions affecting the brain.

Greater alcohol intake predicts accelerated brain aging in humans, which mediates the relationship between alcohol intake and behavioral inflexibility

BACKGROUND

Hazardous use of alcohol is associated with cognitive-behavioral impairments and accelerated aging. To date, however, accelerated brain aging has not been tested as a mediating factor between alcohol use and associated task-based behavioral deficits, such as behavioral inflexibility. Here, we evaluated hazardous alcohol use as a predictor of machine learning-derived brain aging and tested if this measure accounted for the relationship between hazardous alcohol use and a task-based measure of behavioral flexibility.

METHODS

In this secondary analysis, we applied brainageR, a machine learning algorithm, to anatomical T1-weighted magnetic resonance imaging (MRI) images to estimate brain age for a sample of healthy adults (ages 22-40) who self-reported alcohol use with the alcohol use disorder identification test (AUDIT) and performed the hidden association between images task (HABIT), a behavioral flexibility task. Behavioral inflexibility was quantified as the proportion of perseverative errors performed on the HABIT as a measure of habitual action selection. We then analyzed AUDIT score as a predictor of brain aging, and brain aging as a predictor of behavioral inflexibility. Lastly, we conducted a mediation analysis to evaluate brain aging as a mediator between alcohol use and behavioral inflexibility.

RESULTS

Controlling for chronological age and sex, a higher AUDIT score predicted significantly more accelerated brain aging, which was further associated with more perseverative errors on the HABIT. Moreover, brain aging significantly mediated the association between AUDIT scores and behavioral inflexibility.

CONCLUSIONS

Our findings demonstrate that alcohol use is a significant predictor of accelerated brain aging, even in young adulthood. In addition, our findings suggest that such brain changes may mechanistically link more hazardous alcohol use to impaired behavioral flexibility. Future studies should also explore factors, such as other lifestyle behaviors, that may mitigate alcohol- and age-related processes.

Estimating Chronological Age From the Electrical Activity of the Brain: How EEG-Age Can Be Used as a Marker of General Brain Functioning

With an aging global population, the number of older adults with age-related changes in the brain, including dementia, will continue to increase unless we can make progress in the early detection and treatment of such conditions. There is extensive literature on the effects of aging on the EEG, particularly a decline in the Peak Alpha Frequency (PAF), but here, in a reversal of convention, we used the EEG power-frequency spectrum to estimate chronological age. The motivation for this approach was that an individual's brain age might act as a proxy for their general brain functioning, whereby a discrepancy between chronological age and EEG age could prove clinically informative by implicating deleterious conditions. With a sample of sixty healthy adults, whose ages ranged from 20 to 78 years, and using multivariate methods to analyze the broad EEG spectrum (0.1-45 Hz), strong positive correlations between chronological age and EEG age emerged. Furthermore, EEG age was a more accurate estimate and accounted for more variance in chronological age than well-established PAF-based estimates of age, indicating that EEG age could be a more comprehensive measure of general brain functioning. We conclude that EEG age could become a biomarker for neural and cognitive integrity.

Brain Age Gap as a Predictor of Early Treatment Response and Functional Outcomes in First-Episode Schizophrenia: A Longitudinal Study: L'écart d'âge cérébral comme prédicteur de la réponse en début de traitement et des résultats fonctionnels dans un premier épisode de schizophrénie : une étude longitudinale

OBJECTIVES

Accelerated brain aging, i.e., the age-related structural changes in the brain appearing earlier than expected from one's chronological age, is a feature that is now well established in schizophrenia. Often interpreted as a feature of a progressive pathophysiological process that typifies schizophrenia, its prognostic relevance is still unclear. We investigate its role in response to antipsychotic treatment in first-episode schizophrenia.

METHODS

We recruited 49 drug-naive patients with schizophrenia who were then treated with risperidone at a standard dose range of 2-6 mg/day. We followed them up for 3 months to categorize their response status. We acquired T1-weighted anatomical images and used the XGboost method to evaluate individual brain age. The brain age gap (BAG) is the difference between the predicted brain age and chronological age.

RESULTS

Patients with FES had more pronounced BAG compared to healthy subjects, and this difference was primarily driven by those who did not respond adequately after 12 weeks of treatment. BAG did not worsen significantly over the 12-week period, indicating a lack of prominent brain-ageing effect induced by the early antipsychotic exposure per se. However, highly symptomatic patients had a more prominent increase in BAG, while patients with higher BAG when initiating treatment later showed lower gains in global functioning upon treatment, highlighting the prognostic value of BAG measures in FES.

CONCLUSIONS

Accelerated brain aging is a feature of first-episode schizophrenia that is more likely to be seen among those who will not respond adequately to first-line antipsychotic use. Given that early poor response indicates later treatment resistance, measuring BAG using structural MRI in the first 12 weeks of treatment initiation may provide useful prognostic information when considering second-line treatments in schizophrenia.

Metabolic Status Modulates Global and Local Brain Age Estimates in Overweight and Obese Adults

BACKGROUND

As people live longer, maintaining brain health becomes essential for extending health span and preserving independence. Brain degeneration and cognitive decline are major contributors to disability. In this study, we investigated how metabolic health influences the brain age gap estimate (brainAGE), which measures the difference between neuroimaging-predicted brain age and chronological age.

METHODS

K-means clustering was applied to fasting metabolic markers including insulin, glucose, leptin, cortisol, triglycerides, high-density lipoprotein cholesterol and low-density lipoprotein cholesterol, steady-state plasma glucose, and body mass index of 114 physically and cognitively healthy adults. The homeostatic model assessment for insulin resistance served as a reference. T1-weighted brain magnetic resonance imaging was used to calculate voxel-level and global brainAGE. Longitudinal data were available for 53 participants over a 3-year interval.

RESULTS

K-means clustering divided the sample into 2 groups, those with favorable (n = 58) and those with suboptimal (n = 56) metabolic health. The suboptimal group showed signs of insulin resistance and dyslipidemia (false discovery rate-corrected p < .05) and had older global brainAGE and local brainAGE, with deviations most prominent in cerebellar, ventromedial prefrontal, and medial temporal regions (familywise error-corrected p < .05). Longitudinal analysis revealed group differences but no significant time or interaction effects on brainAGE measures.

CONCLUSIONS

Suboptimal metabolic status is linked to accelerated brain aging, particularly in brain regions rich in insulin receptors. These findings highlight the importance of metabolic health in maintaining brain function and suggest that promoting metabolic well-being may help extend health span.

Transformer-based approaches for neuroimaging: an in-depth review of their role in classification and regression tasks

In the ever-evolving landscape of deep learning (DL), the transformer model emerges as a formidable neural network architecture, gaining significant traction in neuroimaging-based classification and regression tasks. This paper presents an extensive examination of transformer's application in neuroimaging, surveying recent literature to elucidate its current status and research advancement. Commencing with an exposition on the fundamental principles and structures of the transformer model and its variants, this review navigates through the methodologies and experimental findings pertaining to their utilization in neuroimage classification and regression tasks. We highlight the transformer model's prowess in neuroimaging, showcasing its exceptional performance in classification endeavors while also showcasing its burgeoning potential in regression tasks. Concluding with an assessment of prevailing challenges and future trajectories, this paper proffers insights into prospective research directions. By elucidating the current landscape and envisaging future trends, this review enhances comprehension of transformer's role in neuroimaging tasks, furnishing valuable guidance for further inquiry.

Judged by your neighbors: Brain structural normativity profiles for large and heterogeneous samples

The detection of norm deviations is fundamental to clinical decision making and impacts our ability to diagnose and treat diseases effectively. Current normative modeling approaches rely on generic comparisons and quantify deviations in relation to the population average. However, generic models interpolate subtle nuances and risk the loss of critical information, thereby compromising effective personalization of health care strategies. To acknowledge the substantial heterogeneity among patients and support the paradigm shift of precision medicine, we introduce Nearest Neighbor Normativity (N3), which is a strategy to refine normativity evaluations in diverse and heterogeneous clinical study populations. We address current methodological shortcomings by accommodating several equally normative population prototypes, comparing individuals from multiple perspectives and designing specifically tailored control groups. Applied to brain structure in 36,896 individuals, the N3 framework provides empirical evidence for its utility and significantly outperforms traditional methods in the detection of pathological alterations. Our results underscore N3's potential for individual assessments in medical practice, where norm deviations are not merely a benchmark, but an important metric supporting the realization of personalized patient care.

An Update on Neuroaging on Earth and in Spaceflight

Over 400 articles on the pathophysiology of brain aging, neuroaging, and neurodegeneration were reviewed, with a focus on epigenetic mechanisms and numerous non-coding RNAs. In particular, this review the accent is on microRNAs, the discovery of whose pivotal role in gene regulation was recognized by the 2024 Nobel Prize in Physiology or Medicine. Aging is not a gradual process that can be easily modeled and described. Instead, multiple temporal processes occur during aging, and they can lead to mosaic changes that are not uniform in pace. The rate of change depends on a combination of external and internal factors and can be boosted in accelerated aging. The rate can decrease in decelerated aging due to individual structural and functional reserves created by cognitive, physical training, or pharmacological interventions. Neuroaging can be caused by genetic changes, epigenetic modifications, oxidative stress, inflammation, lifestyle, and environmental factors, which are especially noticeable in space environments where adaptive changes can trigger aging-like processes. Numerous candidate molecular biomarkers specific to neuroaging need to be validated to develop diagnostics and countermeasures.

Cross-Sectional Comparison of Structural MRI Markers of Impairment in a Diverse Cohort of Older Adults

Neurodegeneration is presumed to be the pathological process measure most proximal to clinical symptom onset in Alzheimer Disease (AD). Structural MRI is routinely collected in research and clinical trial settings. Several quantitative MRI-based measures of atrophy have been proposed, but their low correspondence with each other has been previously documented. The purpose of this study was to identify which commonly used structural MRI measure (hippocampal volume, cortical thickness in AD signature regions, or brain age gap [BAG]) had the best correspondence with the Clinical Dementia Rating (CDR) in an ethno-racially diverse sample. 2870 individuals recruited by the Healthy and Aging Brain Study-Health Disparities completed both structural MRI and CDR evaluation. Of these, 1887 individuals were matched on ethno-racial identity (Mexican American [MA], non-Hispanic Black [NHB], and non-Hispanic White [NHW]) and CDR (27% CDR > 0). We estimated brain age using two pipelines (DeepBrainNet, BrainAgeR) and then calculated BAG as the difference between the estimated brain age and chronological age. We also quantified their hippocampal volumes using HippoDeep and cortical thicknesses (both an AD-specific signature and average whole brain) using FreeSurfer. We used ordinal regression to evaluate associations between neuroimaging measures and CDR and to test whether these associations differed between ethno-racial groups. Higher BAG (pDeepBrainNet = 0.0002; pBrainAgeR = 0.00117) and lower hippocampal volume (p = 0.0015) and cortical thickness (p < 0.0001) were associated with worse clinical status (higher CDR). AD signature cortical thickness had the strongest relationship with CDR (AICDeepBrainNet = 2623, AICwhole cortex = 2588, AICBrainAgeR = 2533, AICHippocampus = 2293, AICSignature Cortical Thickness = 1903). The relationship between CDR and atrophy measures differed between ethno-racial groups for both BAG estimates and hippocampal volume, but not for cortical thickness. We interpret the lack of an interaction between ethno-racial identity and AD signature cortical thickness on CDR as evidence that cortical thickness effectively captures sources of disease-related atrophy that may differ across racial and ethnic groups. Cortical thickness had the strongest association with CDR. These results suggest that cortical thickness may be a more sensitive and generalizable marker of neurodegeneration than hippocampal volume or BAG in ethno-racially diverse cohorts.

Structural Magnetic Resonance Imaging Brain Age Investigation in Athletes with Persistent Postconcussion Syndrome

Brain age prediction algorithms using structural magnetic resonance imaging (MRI) estimate the biological age of the brain by comparing it to a normal aging trajectory, allowing for the identification of deviations that may indicate slower or accelerated biological aging. Traumatic brain injury (TBI) and sports-related concussion (SRC) have been associated with greater brain age gap (BAG) compared to healthy controls. In this study, we aimed to investigate BAG in athletes suffering from persistent postconcussion syndrome (PCS+) compared to PCS- athletes, and used SHapley Additive exPlanations (SHAP), an explainable artificial intelligence framework, to provide further details on which specific features drive the brain age predictions. Brain age was derived from T1-weighted MRI images in a cohort of 50 athletes (24 with PCS+) from 22 to 73 years old from the general population. The results revealed that athletes with PCS+ had a brain age approximately 5 years older than the PCS- athletes, with no clinical variable associated with it. Exploratory analyses also showed a greater brain age in athletes who self-reported five or more SRCs. Regarding SHAP, the third ventricle was found to be the most informative feature in the PCS+ group, while the superior temporal sulcus posterior area was more informative in the PCS- group. This study demonstrated the potential of using brain age and explainable artificial intelligence frameworks to study athletes with PCS. Further research is needed to explore the underlying mechanisms driving brain aging in this population and to identify potential biomarkers for early detection and intervention.

Altered brain functional network connectivity and topology in type 2 diabetes mellitus

Introduction

Type 2 diabetes mellitus (T2DM) accelerates brain aging and disrupts brain functional network connectivity, though the specific mechanisms remain unclear. This study aimed to investigate T2DM-driven alterations in brain functional network connectivity and topology.

Methods

Eighty-five T2DM patients and 67 healthy controls (HCs) were included. All participants underwent clinical, neuropsychological, and laboratory tests, followed by MRI examinations, including resting-state functional magnetic resonance imaging (rs-fMRI) and three-dimensional high-resolution T1-weighted imaging (3D-T1WI) on a 3.0 T MRI scanner. Post-image preprocessing, brain functional networks were constructed using the Dosenbach atlas and analyzed with the DPABI-NET toolkit through graph theory.

Results

In T2DM patients, functional connectivity within and between the default mode network (DMN), frontal parietal network (FPN), subcortical network (SCN), ventral attention network (VAN), somatosensory network (SMN), and visual network (VN) was significantly reduced compared to HCs. Conversely, two functional connections within the VN and between the DMN and SMN were significantly increased. Global network topology analysis showed an increased shortest path length and decreased clustering coefficient, global efficiency, and local efficiency in the T2DM group. MoCA scores were negatively correlated with the shortest path length and positively correlated with global and local efficiency in the T2DM group. Node network topology analysis indicated reduced clustering coefficient, degree centrality, eigenvector centrality, and nodal efficiency in multiple nodes in the T2DM group. MoCA scores positively correlated with clustering coefficient and nodal efficiency in the bilateral precentral gyrus in the T2DM group.

Discussion

This study demonstrated significant abnormalities in connectivity and topology of large-scale brain functional networks in T2DM patients. These findings suggest that brain functional network connectivity and topology could serve as imaging biomarkers, providing insights into the underlying neuropathological processes associated with T2DM-related cognitive impairment.

Preserved brain youthfulness: longitudinal evidence of slower brain aging in superagers

BACKGROUND

Superagers, older adults with exceptional cognitive abilities, show preserved brain structure compared to typical older adults. We investigated whether superagers have biologically younger brains based on their structural integrity.

METHODS

A cohort of 153 older adults (aged 61-93) was recruited, with 63 classified as superagers based on superior episodic memory and 90 as typical older adults, of whom 64 were followed up after two years. A deep learning model for brain age prediction, trained on 899 diverse-aged adults (aged 31-100), was adapted to the older adult cohort via transfer learning. Brain age gap (BAG), a metric based on brain structural patterns, defined as the difference between predicted and chronological age, and its annual rate of change were calculated to assess brain aging status and speed, respectively, and compared among subgroups.

RESULTS

Lower BAGs correlated with more favorable cognitive status in memory and general cognitive function. Superagers exhibited a lower BAG than typical older adults at both baseline and follow-up. Individuals who maintained or attained superager status at follow-up showed a slower annual rate of change in BAG compared to those who remained or became typical older adults.

CONCLUSIONS

Superaging brains manifested maintained neurobiological youthfulness in terms of a more youthful brain aging status and a reduced speed of brain aging. These findings suggest that cognitive resilience, and potentially broader functional resilience, exhibited by superagers during the aging process may be attributable to their younger brains.

Exploring the Link Between Periodontitis and Alzheimer's Disease-Could a Nanoparticulate Vaccine Break It?

Alzheimer's disease (AD) is the most prevalent neurodegenerative disorder, as approximately 55 million people worldwide are affected, with a significant tendency to increase. It reveals three main pathological features: amyloid plaques, neurofibrillary tangles, and neuroinflammation, responsible for the neurodegenerative changes that slowly lead to deterioration of personality and cognitive control. Over a century after the first case report, effective treatments remain elusive, likely due to an incomplete understanding of the precise mechanisms driving its pathogenesis. Recent studies provide growing evidence of an infectious aetiology for AD, a hypothesis reinforced by findings that amyloid beta functions as an antimicrobial peptide. Among the microorganisms already associated with AD, Porphyromonas gingivalis (Pg), the keystone pathogen of periodontitis (PeD), has received particular attention as a possible aetiological agent for AD development. Herein, we review the epidemiological and genetic evidence linking PeD and Pg to AD, highlighting the identification of periodontal bacteria in post mortem analysis of AD patients' brains and identifying putative mechanistic links relevant to the biological plausibility of the association. With the focus on AD research shifting from cure to prevention, the proposed mechanisms linking PeD to AD open the door for unravelling new prophylactic approaches able to reduce the global burden of AD. As hypothesised in this review, these could include a bionanotechnological approach involving the development of an oral nanoparticulate vaccine based on Pg-specific antigens. Such a vaccine could prevent Pg antigens from progressing to the brain and triggering AD pathology, representing a promising step toward innovative and effective AD prevention.

Childhood maltreatment and brain aging during adulthood

Importance

Childhood maltreatment (CM) is associated with the early onset of psychiatric and medical disorders and accelerated biological aging.

Objective

To identify types of maltreatment and developmental sensitive periods that are associated with accelerated adult brain aging.

Design

Participants were mothers of infants recruited from the community into a study assessing the effects of CM on maternal behavior, infant attachment, and maternal and infant neurobiology. Data were collected from July 2015 to November 2019 and were analyzed from July 2023 to October 2024.

Setting

Academic medical centers.

Participants

High-quality MRI scans were obtained on 92 of 150 mothers enrolled in the study. The main exclusion criteria for neuroimaging were histories of head trauma with loss of consciousness or concussion, psychotropic use before age 18, pregnancy, and customary MRI exclusions (e.g., metal implant). The primary reasons for non-completion of the neuroimaging study were unwillingness to be scanned, inability to attend the MRI study visit due to work and/or childcare, metal implants, or pregnancy.

Main Outcomes and Measures

The Maltreatment and Abuse Chronology of Exposure scale was used to retrospectively assess the annual severity of exposure to ten types of CM from birth to age 18 years. Brain age was calculated from T1-weighted 3T MRI Scans using a previously published machine learning algorithm. Sensitive periods were identified using random forest regression with conditional inference trees.

Results

Forty-nine (53.3%) of the 92 mothers (mean [SD] age, 32.4 [4.3] years) reported experiencing one or more types of CM. Total CM severity was associated with accelerated brain aging (β=0.05, 95% CI, 0.02 to 0.09, p<.005). The most robust type/time risk factors for accelerated brain aging were parental physical abuse between ages 4 to 6 years, witnessing sibling violence between ages 4 to 15 years, parental verbal abuse between ages 10 to 12 years, and parental emotional neglect between ages 16 to 18 years.

Conclusions and Relevance

Several types of CM between ages 4-18 years were associated with accelerated brain aging. Understanding how these specific types and ages of exposure contribute to accelerated brain aging may provide important insights into preventing key clinical consequences of CM.

SUMMARY

Question: How does childhood adversity relate to brain aging in adulthood, and are there sensitive periods for this association? Findings: In this cohort-based study of adult women, we observed sensitive periods for the association between adult brain aging and five classes of childhood maltreatment: parental physical abuse, parental verbal abuse, parental emotional neglect, and witnessing sibling violence. Meaning: These findings suggest that maltreatment subtype and age at exposure may be important factors contributing to the impact of childhood adversity on brain aging later in life.

Brain Age Modeling and Cognitive Outcomes in Young Adults With and Without Sickle Cell Anemia

Importance

Both sickle cell anemia (SCA) and socioeconomic status have been associated with altered brain structure and cognitive disability, yet precise mechanisms underlying these associations are unclear.

Objective

To determine whether brains of individuals with and without SCA appear older than chronological age and if brain age modeling using brain age gap (BAG) can estimate cognitive outcomes and mediate the association of socioeconomic status and disease with these outcomes.

Design, Setting, and Participants

In this cross-sectional study of 230 adults with and without SCA, individuals underwent brain magnetic resonance imaging (MRI) and cognitive assessment. Brain age was estimated using DeepBrainNet, a model trained to estimate chronological age from 14 468 structural MRIs from healthy individuals across the lifespan. BAG was defined as estimated brain age minus chronological age. Linear regression examined clinical factors associated with BAG and the ability of BAG to estimate cognitive performance compared to neuroimaging metrics of brain health and ischemic brain injury, such as normalized whole brain volume, white matter mean diffusivity (MD), and infarct volume. BAG and white matter MD were tested further as mediators of the association of socioeconomic status and SCA with cognitive performance. Data were analyzed from October 15, 2023, to July 1, 2024.

Exposures

SCA disease status and economic deprivation as measured using the area deprivation index (ADI).

Main Outcome and Measures

Executive function, crystallized function, processing speed, and full-scale intelligence quotient (FSIQ) were derived from the National Institutes of Health (NIH) Toolbox and Wechsler Abbreviated Scale of Intelligence, Second Edition.

Results

Among 230 included adults, 123 individuals had SCA (median [IQR] age, 26.4 [21.8-34.3] years; 77 female [63%]) and 107 individuals did not (control cohort; median [IQR] age, 30.1 [26.3-34.8] years; 77 female [72%]). Participants with SCA had a larger median (IQR) BAG compared to individuals in the control cohort (14.2 [8.0-19.2] vs 7.3 [3.2-11.1] years; median difference, 6.13 years; 95% CI, 4.29-8.05 years; P < .001). Individuals in the control cohort demonstrated a larger BAG relative to the reference population (mean difference, 7.52 years; 95% CI, 6.32-8.72 years; P < .001). Higher economic deprivation was associated with BAG in the control cohort (β [SE] per 1% ADI increase, 0.079 [0.028]; 95% CI, 0.023 to 0.135; P = .006), while intracranial vasculopathy (β [SE], 6.562 [1.883]; 95% CI, 2.828 to 10.296; P < .001) and hemoglobin S percentage (β [SE] per 1% increase, 0.089 [0.032]; 95% CI, 0.026 to 0.151; P = .006) were associated with BAG in participants with SCA. Across neuroimaging metrics of brain health, BAG demonstrated the largest effect size for cognitive outcomes in the control cohort (eg, executive function: r = -0.430; P = .001), while white matter MD demonstrated the largest effect size for cognitive outcomes (eg, executive function: r = -0.365; P = .001) in the SCA cohort. Across the study population, BAG mediated the association of ADI with cognitive performance (eg, executive function: β [SE] per 1-unit decrease in ADI, -0.031 [0.014]; 95% CI, -0.061 to -0.006), while BAG (eg, FSIQ: β [SE], -3.79 [1.42]; 95% CI, -6.87 to -1.40) and white matter MD (eg, FSIQ: β [SE], -4.55 [1.82]; 95% CI, -8.14 to -0.94) mediated the association of SCA with cognitive performance.

Conclusions and Relevance

Adults with SCA and a healthy control cohort with greater economic deprivation demonstrated older brain age, suggestive of insufficient brain development, premature brain aging, or both. Brain estimates of chronological age may inform mechanisms of the association between chronic disease and socioeconomic status with cognitive outcomes in healthy and SCA populations, yet will require confirmation in larger and longitudinal studies.

Age-disproportionate atrophy in Alzheimer's disease and Parkinson's disease spectra

INTRODUCTION

Brain age gap (BAG), defined as the difference between MRI-predicted 'brain age' and chronological age, can capture information underlying various neurological disorders. We investigated the pathophysiological significance of the BAG across neurodegenerative disorders.

METHODS

We developed a brain age estimator using structural MRIs of healthy-aged individuals from one cohort study. Subsequently, we applied this estimator to people with Alzheimer's disease spectra (AD) and Parkinson's disease (PD) from another cohort study. We investigated brain sources responsible for BAGs among these groups.

RESULTS

Both AD and PD exhibited a positive BAG. Brain sources showed overlapping, yet partially segregated, neuromorphological differences between these groups. Furthermore, employing with t-distributed stochastic neighbor embedding on the brain sources, we subclassified PD into two groups with and without cognitive impairment.

DISCUSSION

Our findings suggest that brain age estimation becomes a clinically relevant method for finely stratifying neurodegenerative disorders.

Highlights

Brain age estimated from structure MRI data was greater than chronological age in patients with Alzheimer's disease/mild cognitive impairment or Parkinson's disease.Brain regions attributed to brain age estimation were located mainly in the fronto-temporo-parietal cortices but not in the motor cortex or subcortical regions.Brain sources responsible for the brain age gaps revealed roughly overlapping, yet partially segregated, neuromorphological differences between participants with Alzheimer's disease/mild cognitive impairment and Parkinson's disease.Participants with Parkinson's disease were subclassified into two groups (with and without cognitive impairment) based on brain sources responsible for the brain age gaps.

Explainable brain age prediction: a comparative evaluation of morphometric and deep learning pipelines

Brain age, a biomarker reflecting brain health relative to chronological age, is increasingly used in neuroimaging to detect early signs of neurodegenerative diseases and support personalized treatment plans. Two primary approaches for brain age prediction have emerged: morphometric feature extraction from MRI scans and deep learning (DL) applied to raw MRI data. However, a systematic comparison of these methods regarding performance, interpretability, and clinical utility has been limited. In this study, we present a comparative evaluation of two pipelines: one using morphometric features from FreeSurfer and the other employing 3D convolutional neural networks (CNNs). Using a multisite neuroimaging dataset, we assessed both model performance and the interpretability of predictions through eXplainable Artificial Intelligence (XAI) methods, applying SHAP to the feature-based pipeline and Grad-CAM and DeepSHAP to the CNN-based pipeline. Our results show comparable performance between the two pipelines in Leave-One-Site-Out (LOSO) validation, achieving state-of-the-art performance on the independent test set ( M A E = 3.21 with DNN and morphometric features and M A E = 3.08 with a DenseNet-121 architecture). SHAP provided the most consistent and interpretable results, while DeepSHAP exhibited greater variability. Further work is needed to assess the clinical utility of Grad-CAM. This study addresses a critical gap by systematically comparing the interpretability of multiple XAI methods across distinct brain age prediction pipelines. Our findings underscore the importance of integrating XAI into clinical practice, offering insights into how XAI outputs vary and their potential utility for clinicians.

Predicting Subject Traits From Brain Spectral Signatures: An Application to Brain Ageing

The prediction of subject traits using brain data is an important goal in neuroscience, with relevant applications in clinical research, as well as in the study of differential psychology and cognition. While previous prediction work has predominantly been done on neuroimaging data, our focus is on electroencephalography (EEG), a relatively inexpensive, widely available and non-invasive data modality. However, EEG data is complex and needs some form of feature extraction for subsequent prediction. This process is sometimes done manually, risking biases and suboptimal decisions. Here we investigate the use of data-driven Kernel methods for prediction from single channels using the EEG spectrogram, which reflects macro-scale neural oscillations in the brain. Specifically, we introduce the idea of reinterpreting the spectrogram of each channel as a probability distribution, so that we can leverage advanced machine learning techniques that can handle probability distributions with mathematical rigour and without the need for manual feature extraction. We explore how the resulting technique, Kernel mean embedding regression, compares to a standard application of Kernel ridge regression as well as to a non-Kernelised approach. Overall, we found that the Kernel methods exhibit improved performance thanks to their capacity to handle nonlinearities in the relation between the EEG spectrogram and the trait of interest. We leveraged this method to predict biological age in a multinational EEG data set, HarMNqEEG, showing the method's capacity to generalise across experiments and acquisition setups.

Critical review of aging clocks and factors that may influence the pace of aging

Background and objectives

Aging clocks are computational models designed to measure biological age and aging rate based on age-related markers including epigenetic, proteomic, and immunomic changes, gut and skin microbiota, among others. In this narrative review, we aim to discuss the currently available aging clocks, ranging from epigenetic aging clocks to visual skin aging clocks.

Methods

We performed a literature search on PubMed/MEDLINE databases with keywords including: "aging clock," "aging," "biological age," "chronological age," "epigenetic," "proteomic," "microbiome," "telomere," "metabolic," "inflammation," "glycomic," "lifestyle," "nutrition," "diet," "exercise," "psychosocial," and "technology."

Results

Notably, several CpG regions, plasma proteins, inflammatory and immune biomarkers, microbiome shifts, neuroimaging changes, and visual skin aging parameters demonstrated roles in aging and aging clock predictions. Further analysis on the most predictive CpGs and biomarkers is warranted. Limitations of aging clocks include technical noise which may be corrected with additional statistical techniques, and the diversity and applicability of samples utilized.

Conclusion

Aging clocks have significant therapeutic potential to better understand aging and the influence of chronic inflammation and diseases in an expanding older population.

Evidence of compensatory neural hyperactivity in a subgroup of breast cancer survivors treated with chemotherapy and its association with brain aging

Introduction

Chemotherapy-related cognitive impairment (CRCI) remains poorly understood in terms of the mechanisms of cognitive decline. Neural hyperactivity has been reported on average in cancer survivors, but it is unclear which patients demonstrate this neurophenotype, limiting precision medicine in this population.

Methods

We evaluated a retrospective sample of 80 breast cancer survivors and 80 non-cancer controls, aged 35-73, for which we had previously identified and validated three data-driven, biological subgroups (biotypes) of CRCI. We measured neural activity using the z-normalized percent amplitude of fluctuation from resting-state functional magnetic resonance imaging (MRI). We tested established, quantitative criteria to determine whether hyperactivity can accurately be considered compensatory. We also calculated the brain age gap by applying a previously validated algorithm to anatomic MRI.

Results

We found that neural activity differed across the three CRCI biotypes and controls (F = 13.5, p < 0.001), with Biotype 2 demonstrating significant hyperactivity compared to the other groups (p < 0.004, corrected), primarily in prefrontal regions. Alternatively, Biotypes 1 and 3 demonstrated significant hypoactivity (p < 0.02, corrected). Hyperactivity in Biotype 2 met several of the criteria to be considered compensatory. However, we also found a positive relationship between neural activity and the brain age gap in these patients (r = 0.45, p = 0.042).

Discussion

Our results indicated that neural hyperactivity is specific to a subgroup of breast cancer survivors and, while it seems to support preserved cognitive function, it could also increase the risk of accelerated brain aging. These findings could inform future neuromodulatory interventions with respect to the risks and benefits of upregulation or downregulation of neural activity.

Generative models of MRI-derived neuroimaging features and associated dataset of 18,000 samples

Availability of large and diverse medical datasets is often challenged by privacy and data sharing restrictions. Successful application of machine learning techniques for disease diagnosis, prognosis, and precision medicine, requires large amounts of data for model building and optimization. To help overcome such limitations in the context of brain MRI, we present GenMIND: a collection of generative models of normative regional volumetric features derived from structural brain imaging. GenMIND models are trained on real brain imaging regional volumetric measures from the iSTAGING consortium, which encompasses over 40,000 MRI scans across 13 studies, incorporating covariates such as age, sex, and race. Leveraging GenMIND, we produce and offer 18,000 synthetic samples spanning the adult lifespan (ages 22-90 years), alongside the model's capability to generate unlimited data. Experimental results indicate that samples generated from GenMIND align well with the distributions observed in real data. Most importantly, the generated normative data significantly enhances the accuracy of downstream machine learning models on tasks such as disease classification. Dataset and the generative models are publicly available.

Exploring the link between tooth loss, cognitive function, and brain wellness in the context of healthy aging

AIMS

The aim of this study was to evaluate the utility of using MRI-derived tooth count, an indirect and nonspecific indicator of oral/periodontal health, and brain age gap (BAG), an MRI-based measure of premature brain aging, in predicting cognition in a population of otherwise healthy adults.

METHODS

This retrospective study utilized data from 329 participants from the University of South Carolina's Aging Brain Cohort Repository. Participants underwent neuropsychological testing including the Montreal Cognitive Assessment (MoCA), completed an oral/periodontal health questionnaire, and submitted to high-resolution structural MRI imaging. The study compared variability on cognitive scores (MoCA) accounted for by MRI-derived BAG, MRI-derived total tooth count, and self-reported oral/periodontal health.

RESULTS

We report a significant positive correlation between the total number of teeth and MoCA total scores after controlling for age, sex, and race, indicating a robust relationship between tooth count and cognition, r(208) = .233, p < .001. In a subsample of participants identified as being at risk for MCI (MoCA <= 25, N = 36) inclusion of MRI-based tooth count resulted in an R2 change of .192 (H0 = 0.138 → H1 = 0.330), F(1,31) = 8.86, p = .006. Notably, inclusion of BAG, a valid and reliable measure of overall brain health, did not significantly improve prediction of MoCA scores in similar linear regression models.

CONCLUSIONS

Our data support the idea that inclusion of MRI-based total tooth count may enhance the ability to predict clinically meaningful differences in cognitive abilities in healthy adults. This study contributes to the growing body of evidence linking oral/periodontal health with cognitive function.

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

Brain Age Gap has been associated with dementia in old age. Less is known relating brain age gap to dementia risk-factors or cognitive performance in middle-age. Cognitively healthy, middle-aged subjects from PREVENT-Dementia had comprehensive neuropsychological, neuroimaging and genetic assessments. Brain Ages were predicted from T1-weighted 3T MRI scans. Cognition was assessed using the COGNITO computerized test battery. 552 middle-aged participants (median [interquartile range] age 52.8 [8.7] years, 60.0% female) had baseline data, of whom 95 had amyloid PET data. Brain age gap in middle-age was associated with hypertension (P = 0.007) and alcohol intake (P = 0.008) but not apolipoprotein E epsilon 4 allele (P = 0.14), amyloid centiloids (P = 0.39) or cognitive performance (P = 0.74). Brain age gap in middle-age is associated with modifiable dementia risk-factors, but not with genetic risk for Alzheimer's disease, amyloid deposition or cognitive performance. These results are important for understanding brain-age in middle-aged populations, which might be optimally targeted by future dementia-preventing therapies.

Multimodal Brain Age Indicators of Internalizing Problems in Early Adolescence: A Longitudinal Investigation

BACKGROUND

Adolescence is a time of increased risk for the onset of internalizing problems, particularly in females. However, how individual differences in brain maturation are related to the increased vulnerability for internalizing problems in adolescence remains poorly understood due to a scarcity of longitudinal studies.

METHODS

Using ABCD (Adolescent Brain Cognitive Development) Study data, we examined longitudinal associations between multimodal brain age and youth internalizing problems. Brain age models were trained, validated, and tested independently on T1-weighted imaging (n = 9523), diffusion tensor imaging (n = 8834), and resting-state functional magnetic resonance imaging (n = 8233) data at baseline (meanage = 9.9 years) and 2-year follow-up (meanage = 11.9 years). Self-reported internalizing problems were measured at 3-year follow-up (meanage = 12.9 years) using the Brief Problem Monitor.

RESULTS

Latent change score models demonstrated that although brain age gap (BAG) at baseline was not related to later internalizing problems, an increase in BAG between time points was positively associated with internalizing problems at 3-year follow-up in females but not males. This association between an increasing BAG and higher internalizing problems was observed in the T1-weighted imaging (β = 0.067, SE = 0.050, false discovery rate [FDR]-corrected p = .020) and resting-state functional magnetic resonance imaging (β = 0.090, SE = 0.025, pFDR = .007) models but not diffusion tensor imaging (β = -0.002, SE = 0.053, pFDR = .932) and remained significant when accounting for earlier internalizing problems.

CONCLUSIONS

A greater increase in BAG in early adolescence may reflect the heightened vulnerability shown by female youth to internalizing problems. Longitudinal research is necessary to understand whether this increasing BAG signifies accelerated brain development and its relationship to the trajectory of internalizing problems throughout adolescence.

Adolescent brain maturation associated with environmental factors: a multivariate analysis

Human adolescence marks a crucial phase of extensive brain development, highly susceptible to environmental influences. Employing brain age estimation to assess individual brain aging, we categorized individuals (N = 7,435, aged 9-10 years old) from the Adolescent Brain and Cognitive Development (ABCD) cohort into groups exhibiting either accelerated or delayed brain maturation, where the accelerated group also displayed increased cognitive performance compared to their delayed counterparts. A 4-way multi-set canonical correlation analysis integrating three modalities of brain metrics (gray matter density, brain morphological measures, and functional network connectivity) with nine environmental factors unveiled a significant 4-way canonical correlation between linked patterns of neural features, air pollution, area crime, and population density. Correlations among the three brain modalities were notably strong (ranging from 0.65 to 0.77), linking reduced gray matter density in the middle temporal gyrus and precuneus to decreased volumes in the left medial orbitofrontal cortex paired with increased cortical thickness in the right supramarginal and bilateral occipital regions, as well as increased functional connectivity in occipital sub-regions. These specific brain characteristics were significantly more pronounced in the accelerated brain aging group compared to the delayed group. Additionally, these brain regions exhibited significant associations with air pollution, area crime, and population density, where lower air pollution and higher area crime and population density were correlated to brain variations more prominently in the accelerated brain aging group.

Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations

Introduction

Over the past few decades, numerous researchers have explored the application of machine learning for assessing children's neurological development. Developmental changes in the brain could be utilized to gauge the alignment of its maturation status with the child's chronological age. AI is trained to analyze changes in different modalities and estimate the brain age of subjects. Disparities between the predicted and chronological age can be viewed as a biomarker for a pathological condition. This literature review aims to illuminate research studies that have employed AI to predict children's brain age.

Methods

The inclusion criteria for this study were predicting brain age via AI in healthy children up to 12 years. The search term was centered around the keywords "pediatric," "artificial intelligence," and "brain age" and was utilized in PubMed and IEEEXplore. The selected literature was then examined for information on data acquisition methods, the age range of the study population, pre-processing, methods and AI techniques utilized, the quality of the respective techniques, model explanation, and clinical applications.

Results

Fifty one publications from 2012 to 2024 were included in the analysis. The primary modality of data acquisition was MRI, followed by EEG. Structural and functional MRI-based studies commonly used publicly available datasets, while EEG-based studies typically relied on self-recruitment. Many studies utilized pre-processing pipelines provided by toolkit suites, particularly in MRI-based research. The most frequently used model type was kernel-based learning algorithms, followed by convolutional neural networks. Overall, prediction accuracy may improve when multiple acquisition modalities are used, but comparing studies is challenging. In EEG, the prediction error decreases as the number of electrodes increases. Approximately one-third of the studies used explainable artificial intelligence methods to explain the model and chosen parameters. However, there is a significant clinical translation gap as no study has tested their model in a clinical routine setting.

Discussion

Further research should test on external datasets and include low-quality routine images for MRI. T2-weighted MRI was underrepresented. Furthermore, different kernel types should be compared on the same dataset. Implementing modern model architectures, such as convolutional neural networks, should be the next step in EEG-based research studies.

Fusing multi-scale functional connectivity patterns via Multi-Branch Vision Transformer (MB-ViT) for macaque brain age prediction

Brain age (BA) is defined as a measure of brain maturity and could help characterize both the typical brain development and neuropsychiatric disorders in mammals. Various biological phenotypes have been successfully applied to predict BA of human using chronological age (CA) as label. However, whether the BA of macaque, one of the most important animal models, can also be reliably predicted is largely unknown. To address this question, we propose a novel deep learning model called Multi-Branch Vision Transformer (MB-ViT) to fuse multi-scale (i.e., from coarse-grained to fine-grained) brain functional connectivity (FC) patterns derived from resting state functional magnetic resonance imaging (rs-fMRI) data to predict BA of macaques. The discriminative functional connections and the related brain regions contributing to the prediction are further identified based on Gradient-weighted Class Activation Mapping (Grad-CAM) method. Our proposed model successfully predicts BA of 450 normal rhesus macaques from the publicly available PRIMatE Data Exchange (PRIME-DE) dataset with lower mean absolute error (MAE) and mean square error (MSE) as well as higher Pearson's correlation coefficient (PCC) and coefficient of determination (R2) compared to other baseline models. The correlation between the predicted BA and CA reaches as high as 0.82 of our proposed method. Furthermore, our analysis reveals that the functional connections predominantly contributing to the prediction results are situated in the primary motor cortex (M1), visual cortex, area v23 in the posterior cingulate cortex, and dysgranular temporal pole. In summary, our proposed deep learning model provides an effective tool to accurately predict BA of primates (macaque in this study), and lays a solid foundation for future studies of age-related brain diseases in those animal models.

Exploring associations between psychotic experiences and structural brain age: a population-based study in late adolescence

Neuroimaging studies show advanced structural "brain age" in schizophrenia and related psychotic disorders, potentially reflecting aberrant brain ageing or maturation. The extent to which altered brain age is associated with subthreshold psychotic experiences (PE) in youth remains unclear. We investigated the association between PE and brain-predicted age difference (brain-PAD) in late adolescence using a population-based sample of 117 participants with PE and 115 without PE (aged 19-21 years) from the Avon Longitudinal Study of Parents and Children. Brain-PAD was estimated using a publicly available machine learning model previously trained on a combination of region-wise T1-weighted grey-matter measures. We found little evidence for an association between PEs and brain-PAD after adjusting for age and sex (Cohen's d = -0.21 [95% CI -0.47, 0.05], p = 0.11). While there was some evidence for lower brain-PAD in those with PEs relative to those without PEs after additionally adjusting for parental social class (Cohen's d = -0.31 [95% CI -0.58, -0.03], p = 0.031) or birth weight (Cohen's d = -0.29 [95% CI -0.55, -0.03], p = 0.038), adjusting for maternal education or childhood IQ did not alter the primary results. These findings do not support the notion of advanced brain age in older adolescents with PEs. However, they weakly suggest there might be a younger-looking brain in those individuals, indicative of subtle delays in structural brain maturation. Future studies with larger samples covering a wider age range and multimodal measures could further investigate brain age as a marker of psychotic experiences in youth.

A perspective on brain-age estimation and its clinical promise

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

Generative models of MRI-derived neuroimaging features and associated dataset of 18,000 samples

Availability of large and diverse medical datasets is often challenged by privacy and data sharing restrictions. For successful application of machine learning techniques for disease diagnosis, prognosis, and precision medicine, large amounts of data are necessary for model building and optimization. To help overcome such limitations in the context of brain MRI, we present GenMIND: a collection of generative models of normative regional volumetric features derived from structural brain imaging. GenMIND models are trained on real brain imaging regional volumetric measures from the iSTAGING consortium, which encompasses over 40,000 MRI scans across 13 studies, incorporating covariates such as age, sex, and race. Leveraging GenMIND, we produce and offer 18,000 synthetic samples spanning the adult lifespan (ages 22-90 years), alongside the model's capability to generate unlimited data. Experimental results indicate that samples generated from GenMIND agree with the distributions obtained from real data. Most importantly, the generated normative data significantly enhance the accuracy of downstream machine learning models on tasks such as disease classification. Data and models are available at: https://huggingface.co/spaces/rongguangw/GenMIND.