Deep neural networks learn general and clinically relevant representations of the ageing brain

s-TBN: A New Neural Decoding Model to Identify Stimulus Categories From Brain Activity Patterns

Neural decoding is still a challenging and a hot topic in neurocomputing science. Recently, many studies have shown that brain network patterns containing rich spatiotemporal structural information represent the brain's activation information under external stimuli. In the traditional method, brain network features are directly obtained using the standard machine learning method and provide to a classifier, subsequently decoding external stimuli. However, this method cannot effectively extract the multidimensional structural information hidden in the brain network. Furthermore, studies on tensors have show that the tensor decomposition model can fully mine unique spatiotemporal structural characteristics of a spatiotemporal structure in data with a multidimensional structure. This research proposed a stimulus-constrained Tensor Brain Network (s-TBN) model that involves the tensor decomposition and stimulus category-constraint information. The model was verified on real neuroimaging data obtained via magnetoencephalograph and functional mangetic resonance imaging). Experimental results show that the s-TBN model achieve accuracy matrices of greater than 11.06% and 18.46% on the accuracy matrix compared with other methods on two modal datasets. These results prove the superiority of extracting discriminative characteristics using the STN model, especially for decoding object stimuli with semantic information.

The effect of head motion on brain age prediction using deep convolutional neural networks

Deep learning can be used effectively to predict participants' age from brain magnetic resonance imaging (MRI) data, and a growing body of evidence suggests that the difference between predicted and chronological age-referred to as brain-predicted age difference (brain-PAD)-is related to various neurological and neuropsychiatric disease states. A crucial aspect of the applicability of brain-PAD as a biomarker of individual brain health is whether and how brain-predicted age is affected by MR image artifacts commonly encountered in clinical settings. To investigate this issue, we trained and validated two different 3D convolutional neural network architectures (CNNs) from scratch and tested the models on a separate dataset consisting of motion-free and motion-corrupted T1-weighted MRI scans from the same participants, the quality of which were rated by neuroradiologists from a clinical diagnostic point of view. Our results revealed a systematic increase in brain-PAD with worsening image quality for both models. This effect was also observed for images that were deemed usable from a clinical perspective, with brains appearing older in medium than in good quality images. These findings were also supported by significant associations found between the brain-PAD and standard image quality metrics indicating larger brain-PAD for lower-quality images. Our results demonstrate a spurious effect of advanced brain aging as a result of head motion and underline the importance of controlling for image quality when using brain-predicted age based on structural neuroimaging data as a proxy measure for brain health.

Constructing personalized characterizations of structural brain aberrations in patients with dementia using explainable artificial intelligence

Deep learning approaches for clinical predictions based on magnetic resonance imaging data have shown great promise as a translational technology for diagnosis and prognosis in neurological disorders, but its clinical impact has been limited. This is partially attributed to the opaqueness of deep learning models, causing insufficient understanding of what underlies their decisions. To overcome this, we trained convolutional neural networks on structural brain scans to differentiate dementia patients from healthy controls, and applied layerwise relevance propagation to procure individual-level explanations of the model predictions. Through extensive validations we demonstrate that deviations recognized by the model corroborate existing knowledge of structural brain aberrations in dementia. By employing the explainable dementia classifier in a longitudinal dataset of patients with mild cognitive impairment, we show that the spatially rich explanations complement the model prediction when forecasting transition to dementia and help characterize the biological manifestation of disease in the individual brain. Overall, our work exemplifies the clinical potential of explainable artificial intelligence in precision medicine.

Dissecting unique and common variance across body and brain health indicators using age prediction

Ageing is a heterogeneous multisystem process involving different rates of decline in physiological integrity across biological systems. The current study dissects the unique and common variance across body and brain health indicators and parses inter-individual heterogeneity in the multisystem ageing process. Using machine-learning regression models on the UK Biobank data set (N = 32,593, age range 44.6-82.3, mean age 64.1 years), we first estimated tissue-specific brain age for white and gray matter based on diffusion and T1-weighted magnetic resonance imaging (MRI) data, respectively. Next, bodily health traits, including cardiometabolic, anthropometric, and body composition measures of adipose and muscle tissue from bioimpedance and body MRI, were combined to predict 'body age'. The results showed that the body age model demonstrated comparable age prediction accuracy to models trained solely on brain MRI data. The correlation between body age and brain age predictions was 0.62 for the T1 and 0.64 for the diffusion-based model, indicating a degree of unique variance in brain and bodily ageing processes. Bayesian multilevel modelling carried out to quantify the associations between health traits and predicted age discrepancies showed that higher systolic blood pressure and higher muscle-fat infiltration were related to older-appearing body age compared to brain age. Conversely, higher hand-grip strength and muscle volume were related to a younger-appearing body age. Our findings corroborate the common notion of a close connection between somatic and brain health. However, they also suggest that health traits may differentially influence age predictions beyond what is captured by the brain imaging data, potentially contributing to heterogeneous ageing rates across biological systems and individuals.

Fusion of biomedical imaging studies for increased sample size and diversity: a case study of brain MRI

Data collection, curation, and cleaning constitute a crucial phase in Machine Learning (ML) projects. In biomedical ML, it is often desirable to leverage multiple datasets to increase sample size and diversity, but this poses unique challenges, which arise from heterogeneity in study design, data descriptors, file system organization, and metadata. In this study, we present an approach to the integration of multiple brain MRI datasets with a focus on homogenization of their organization and preprocessing for ML. We use our own fusion example (approximately 84,000 images from 54,000 subjects, 12 studies, and 88 individual scanners) to illustrate and discuss the issues faced by study fusion efforts, and we examine key decisions necessary during dataset homogenization, presenting in detail a database structure flexible enough to accommodate multiple observational MRI datasets. We believe our approach can provide a basis for future similarly-minded biomedical ML projects.

Examining the reliability of brain age algorithms under varying degrees of participant motion

Brain age algorithms using data science and machine learning techniques show promise as biomarkers for neurodegenerative disorders and aging. However, head motion during MRI scanning may compromise image quality and influence brain age estimates. We examined the effects of motion on brain age predictions in adult participants with low, high, and no motion MRI scans (Original N = 148; Analytic N = 138). Five popular algorithms were tested: brainageR, DeepBrainNet, XGBoost, ENIGMA, and pyment. Evaluation metrics, intraclass correlations (ICCs), and Bland-Altman analyses assessed reliability across motion conditions. Linear mixed models quantified motion effects. Results demonstrated motion significantly impacted brain age estimates for some algorithms, with ICCs dropping as low as 0.609 and errors increasing up to 11.5 years for high motion scans. DeepBrainNet and pyment showed greatest robustness and reliability (ICCs = 0.956-0.965). XGBoost and brainageR had the largest errors (up to 13.5 RMSE) and bias with motion. Findings indicate motion artifacts influence brain age estimates in significant ways. Furthermore, our results suggest certain algorithms like DeepBrainNet and pyment may be preferable for deployment in populations where motion during MRI acquisition is likely. Further optimization and validation of brain age algorithms is critical to use brain age as a biomarker relevant for clinical outcomes.

Parental status and markers of brain and cellular age: A 3D convolutional network and classification study

Recent research shows prominent effects of pregnancy and the parenthood transition on structural brain characteristics in humans. Here, we present a comprehensive study of how parental status and number of children born/fathered links to markers of brain and cellular ageing in 36,323 UK Biobank participants (age range 44.57-82.06 years; 52% female). To assess global effects of parenting on the brain, we trained a 3D convolutional neural network on T1-weighted magnetic resonance images, and estimated brain age in a held-out test set. To investigate regional specificity, we extracted cortical and subcortical volumes using FreeSurfer, and ran hierarchical clustering to group regional volumes based on covariance. Leukocyte telomere length (LTL) derived from DNA was used as a marker of cellular ageing. We employed linear regression models to assess relationships between number of children, brain age, regional brain volumes, and LTL, and included interaction terms to probe sex differences in associations. Lastly, we used the brain measures and LTL as features in binary classification models, to determine if markers of brain and cellular ageing could predict parental status. The results showed associations between a greater number of children born/fathered and younger brain age in both females and males, with stronger effects observed in females. Volume-based analyses showed maternal effects in striatal and limbic regions, which were not evident in fathers. We found no evidence for associations between number of children and LTL. Classification of parental status showed an Area under the ROC Curve (AUC) of 0.57 for the brain age model, while the models using regional brain volumes and LTL as predictors showed AUCs of 0.52. Our findings align with previous population-based studies of middle- and older-aged parents, revealing subtle but significant associations between parental experience and neuroimaging-based surrogate markers of brain health. The findings further corroborate results from longitudinal cohort studies following parents across pregnancy and postpartum, potentially indicating that the parenthood transition is associated with long-term influences on brain health.

Assessing brain involvement in Fabry disease with deep learning and the brain-age paradigm

While neurological manifestations are core features of Fabry disease (FD), quantitative neuroimaging biomarkers allowing to measure brain involvement are lacking. We used deep learning and the brain-age paradigm to assess whether FD patients' brains appear older than normal and to validate brain-predicted age difference (brain-PAD) as a possible disease severity biomarker. MRI scans of FD patients and healthy controls (HCs) from a single Institution were, retrospectively, studied. The Fabry stabilization index (FASTEX) was recorded as a measure of disease severity. Using minimally preprocessed 3D T1-weighted brain scans of healthy subjects from eight publicly available sources (N = 2160; mean age = 33 years [range 4-86]), we trained a model predicting chronological age based on a DenseNet architecture and used it to generate brain-age predictions in the internal cohort. Within a linear modeling framework, brain-PAD was tested for age/sex-adjusted associations with diagnostic group (FD vs. HC), FASTEX score, and both global and voxel-level neuroimaging measures. We studied 52 FD patients (40.6 ± 12.6 years; 28F) and 58 HC (38.4 ± 13.4 years; 28F). The brain-age model achieved accurate out-of-sample performance (mean absolute error = 4.01 years, R2 = .90). FD patients had significantly higher brain-PAD than HC (estimated marginal means: 3.1 vs. -0.1, p = .01). Brain-PAD was associated with FASTEX score (B = 0.10, p = .02), brain parenchymal fraction (B = -153.50, p = .001), white matter hyperintensities load (B = 0.85, p = .01), and tissue volume reduction throughout the brain. We demonstrated that FD patients' brains appear older than normal. Brain-PAD correlates with FD-related multi-organ damage and is influenced by both global brain volume and white matter hyperintensities, offering a comprehensive biomarker of (neurological) disease severity.

The genetic architecture of multimodal human brain age

The complex biological mechanisms underlying human brain aging remain incompletely understood. This study investigated the genetic architecture of three brain age gaps (BAG) derived from gray matter volume (GM-BAG), white matter microstructure (WM-BAG), and functional connectivity (FC-BAG). We identified sixteen genomic loci that reached genome-wide significance (P-value < 5×10-8). A gene-drug-disease network highlighted genes linked to GM-BAG for treating neurodegenerative and neuropsychiatric disorders and WM-BAG genes for cancer therapy. GM-BAG displayed the most pronounced heritability enrichment in genetic variants within conserved regions. Oligodendrocytes and astrocytes, but not neurons, exhibited notable heritability enrichment in WM and FC-BAG, respectively. Mendelian randomization identified potential causal effects of several chronic diseases on brain aging, such as type 2 diabetes on GM-BAG and AD on WM-BAG. Our results provide insights into the genetics of human brain aging, with clinical implications for potential lifestyle and therapeutic interventions. All results are publicly available at https://labs.loni.usc.edu/medicine .

Optimising brain age estimation through transfer learning: A suite of pre-trained foundation models for improved performance and generalisability in a clinical setting

Estimated age from brain MRI data has emerged as a promising biomarker of neurological health. However, the absence of large, diverse, and clinically representative training datasets, along with the complexity of managing heterogeneous MRI data, presents significant barriers to the development of accurate and generalisable models appropriate for clinical use. Here, we present a deep learning framework trained on routine clinical data (N up to 18,890, age range 18-96 years). We trained five separate models for accurate brain age prediction (all with mean absolute error ≤4.0 years, R2  ≥ .86) across five different MRI sequences (T2 -weighted, T2 -FLAIR, T1 -weighted, diffusion-weighted, and gradient-recalled echo T2 *-weighted). Our trained models offer dual functionality. First, they have the potential to be directly employed on clinical data. Second, they can be used as foundation models for further refinement to accommodate a range of other MRI sequences (and therefore a range of clinical scenarios which employ such sequences). This adaptation process, enabled by transfer learning, proved effective in our study across a range of MRI sequences and scan orientations, including those which differed considerably from the original training datasets. Crucially, our findings suggest that this approach remains viable even with limited data availability (as low as N = 25 for fine-tuning), thus broadening the application of brain age estimation to more diverse clinical contexts and patient populations. By making these models publicly available, we aim to provide the scientific community with a versatile toolkit, promoting further research in brain age prediction and related areas.

Brain asymmetries from mid- to late life and hemispheric brain age

The human brain demonstrates structural and functional asymmetries which have implications for ageing and mental and neurological disease development. We used a set of magnetic resonance imaging (MRI) metrics derived from structural and diffusion MRI data in N=48,040 UK Biobank participants to evaluate age-related differences in brain asymmetry. Most regional grey and white matter metrics presented asymmetry, which were higher later in life. Informed by these results, we conducted hemispheric brain age (HBA) predictions from left/right multimodal MRI metrics. HBA was concordant to conventional brain age predictions, using metrics from both hemispheres, but offers a supplemental general marker of brain asymmetry when setting left/right HBA into relationship with each other. In contrast to WM brain asymmetries, left/right discrepancies in HBA are lower at higher ages. Our findings outline various sex-specific differences, particularly important for brain age estimates, and the value of further investigating the role of brain asymmetries in brain ageing and disease development.

A review on brain age prediction models

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

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

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

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

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

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

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

An augmented Mendelian randomization approach provides causality of brain imaging features on complex traits in a single biobank-scale dataset

Mendelian randomization (MR) is an effective approach for revealing causal risk factors that underpin complex traits and diseases. While MR has been more widely applied under two-sample settings, it is more promising to be used in one single large cohort given the rise of biobank-scale datasets that simultaneously contain genotype data, brain imaging data, and matched complex traits from the same individual. However, most existing multivariable MR methods have been developed for two-sample setting or a small number of exposures. In this study, we introduce a one-sample multivariable MR method based on partial least squares and Lasso regression (MR-PL). MR-PL is capable of considering the correlation among exposures (e.g., brain imaging features) when the number of exposures is extremely upscaled, while also correcting for winner's curse bias. We performed extensive and systematic simulations, and demonstrated the robustness and reliability of our method. Comprehensive simulations confirmed that MR-PL can generate more precise causal estimates with lower false positive rates than alternative approaches. Finally, we applied MR-PL to the datasets from UK Biobank to reveal the causal effects of 36 white matter tracts on 180 complex traits, and showed putative white matter tracts that are implicated in smoking, blood vascular function-related traits, and eating behaviors.

NeuropsychBrainAge: A biomarker for conversion from mild cognitive impairment to Alzheimer's disease

INTRODUCTION

BrainAge models based on neuroimaging data have diagnostic classification power but have replicability issues due to site and patient variability. BrainAge models trained on neuropsychological tests could help distinguish stable mild cognitive impairment (sMCI) from progressive MCI (pMCI) to Alzheimer's disease (AD).

METHODS

A linear regressor BrainAge model was trained on healthy controls using neuropsychological tests and neuroimaging features separately. The BrainAge delta, predicted age minus chronological age, was used to distinguish between sMCI and pMCI.

RESULTS

The cross-validated area under the receiver-operating characteristic (ROC) curve for sMCI versus pMCI was 0.91 for neuropsychological features in contrast to 0.68 for neuroimaging features. The BrainAge delta was correlated with the time to conversion, the time taken for a pMCI subject to convert to AD.

DISCUSSION

The BrainAge delta from neuropsychological tests is a good biomarker to distinguish between sMCI and pMCI. Other neurological and psychiatric disorders could be studied using this strategy.

Highlights

BrainAge models based on neuropsychological tests outperform models based on neuroimaging features when distinguishing between stable mild cognitive impairment (sMCI) from progressive MCI (pMCI) to Alzheimer's disease (AD).The combination of neuropsychological tests with neuroimaging features does not lead to an improvement in sMCI versus pMCI classification compared to using neuropsychological tests on their own.BrainAge delta of both neuroimaging and neuropsychological models was correlated with the time to conversion, the time taken for a pMCI subject to convert to AD.

Considerations on brain age predictions from repeatedly sampled data across time

INTRODUCTION

Brain age, the estimation of a person's age from magnetic resonance imaging (MRI) parameters, has been used as a general indicator of health. The marker requires however further validation for application in clinical contexts. Here, we show how brain age predictions perform for the same individual at various time points and validate our findings with age-matched healthy controls.

METHODS

We used densely sampled T1-weighted MRI data from four individuals (from two densely sampled datasets) to observe how brain age corresponds to age and is influenced by acquisition and quality parameters. For validation, we used two cross-sectional datasets. Brain age was predicted by a pretrained deep learning model.

RESULTS

We found small within-subject correlations between age and brain age. We also found evidence for the influence of field strength on brain age which replicated in the cross-sectional validation data and inconclusive effects of scan quality.

CONCLUSION

The absence of maturation effects for the age range in the presented sample, brain age model bias (including training age distribution and field strength), and model error are potential reasons for small relationships between age and brain age in densely sampled longitudinal data. Clinical applications of brain age models should consider of the possibility of apparent biases caused by variation in the data acquisition process.

Diagnostic accuracy of brain age prediction in a memory clinic population and comparison with clinically available volumetric measures

The aim of this study was to assess the diagnostic validity of a deep learning-based method estimating brain age based on magnetic resonance imaging (MRI) and to compare it with volumetrics obtained using NeuroQuant (NQ) in a clinical cohort. Brain age prediction was performed on minimally processed MRI data using deep convolutional neural networks and an independent training set. The brain age gap (difference between chronological and biological age) was calculated, and volumetrics were performed in 110 patients with dementia (Alzheimer's disease, frontotemporal dementia (FTD), and dementia with Lewy bodies), and 122 with non-dementia (subjective and mild cognitive impairment). Area-under-the-curve (AUC) based on receiver operating characteristics and logistic regression analyses were performed. The mean age was 67.1 (9.5) years and 48.7% (113) were females. The dementia versus non-dementia sensitivity and specificity of the volumetric measures exceeded 80% and yielded higher AUCs compared to BAG. The explained variance of the prediction of diagnostic stage increased when BAG was added to the volumetrics. Further, BAG separated patients with FTD from other dementia etiologies with > 80% sensitivity and specificity. NQ volumetrics outperformed BAG in terms of diagnostic discriminatory power but the two methods provided complementary information, and BAG discriminated FTD from other dementia etiologies.

Machine-learning-derived heart and brain age are independently associated with cognition

BACKGROUND AND PURPOSE

A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated.

METHODS

Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40-85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis.

RESULTS

Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3-36) of the HDA effect on the tapping test score was mediated through BDA.

DISCUSSION

Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.

Genetic architecture of brain age and its causal relations with brain and mental disorders

The difference between chronological age and the apparent age of the brain estimated from brain imaging data-the brain age gap (BAG)-is widely considered a general indicator of brain health. Converging evidence supports that BAG is sensitive to an array of genetic and nongenetic traits and diseases, yet few studies have examined the genetic architecture and its corresponding causal relationships with common brain disorders. Here, we estimate BAG using state-of-the-art neural networks trained on brain scans from 53,542 individuals (age range 3-95 years). A genome-wide association analysis across 28,104 individuals (40-84 years) from the UK Biobank revealed eight independent genomic regions significantly associated with BAG (p < 5 × 10-8) implicating neurological, metabolic, and immunological pathways - among which seven are novel. No significant genetic correlations or causal relationships with BAG were found for Parkinson's disease, major depressive disorder, or schizophrenia, but two-sample Mendelian randomization indicated a causal influence of AD (p = 7.9 × 10-4) and bipolar disorder (p = 1.35 × 10-2) on BAG. These results emphasize the polygenic architecture of brain age and provide insights into the causal relationship between selected neurological and neuropsychiatric disorders and BAG.

Bio-psycho-social factors' associations with brain age: a large-scale UK Biobank diffusion study of 35,749 participants

Brain age refers to age predicted by brain features. Brain age has previously been associated with various health and disease outcomes and suggested as a potential biomarker of general health. Few previous studies have systematically assessed brain age variability derived from single and multi-shell diffusion magnetic resonance imaging data. Here, we present multivariate models of brain age derived from various diffusion approaches and how they relate to bio-psycho-social variables within the domains of sociodemographic, cognitive, life-satisfaction, as well as health and lifestyle factors in midlife to old age (N = 35,749, 44.6-82.8 years of age). Bio-psycho-social factors could uniquely explain a small proportion of the brain age variance, in a similar pattern across diffusion approaches: cognitive scores, life satisfaction, health and lifestyle factors adding to the variance explained, but not socio-demographics. Consistent brain age associations across models were found for waist-to-hip ratio, diabetes, hypertension, smoking, matrix puzzles solving, and job and health satisfaction and perception. Furthermore, we found large variability in sex and ethnicity group differences in brain age. Our results show that brain age cannot be sufficiently explained by bio-psycho-social variables alone. However, the observed associations suggest to adjust for sex, ethnicity, cognitive factors, as well as health and lifestyle factors, and to observe bio-psycho-social factor interactions' influence on brain age in future studies.

Multiscale functional connectivity patterns of the aging brain learned from harmonized rsfMRI data of the multi-cohort iSTAGING study

To learn multiscale functional connectivity patterns of the aging brain, we built a brain age prediction model of functional connectivity measures at seven scales on a large fMRI dataset, consisting of resting-state fMRI scans of 4186 individuals with a wide age range (22 to 97 years, with an average of 63) from five cohorts. We computed multiscale functional connectivity measures of individual subjects using a personalized functional network computational method, harmonized the functional connectivity measures of subjects from multiple datasets in order to build a functional brain age model, and finally evaluated how functional brain age gap correlated with cognitive measures of individual subjects. Our study has revealed that functional connectivity measures at multiple scales were more informative than those at any single scale for the brain age prediction, the data harmonization significantly improved the brain age prediction performance, and the data harmonization in the functional connectivity measures' tangent space worked better than in their original space. Moreover, brain age gap scores of individual subjects derived from the brain age prediction model were significantly correlated with clinical and cognitive measures. Overall, these results demonstrated that multiscale functional connectivity patterns learned from a large-scale multi-site rsfMRI dataset were informative for characterizing the aging brain and the derived brain age gap was associated with cognitive and clinical measures.

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

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

Linking brain maturation and puberty during early adolescence using longitudinal brain age prediction in the ABCD cohort

The temporal characteristics of adolescent neurodevelopment are shaped by a complex interplay of genetic, biological, and environmental factors. Using a large longitudinal dataset of children aged 9-13 from the Adolescent Brain Cognitive Development (ABCD) study we tested the associations between pubertal status and brain maturation. Brain maturation was assessed using brain age prediction based on convolutional neural networks and minimally processed T1-weighted structural MRI data. Brain age prediction provided highly accurate and reliable estimates of individual age, with an overall mean absolute error of 0.7 and 1.4 years at the two timepoints respectively, and an intraclass correlation of 0.65. Linear mixed effects (LME) models accounting for age and sex showed that on average, a one unit increase in pubertal maturational level was associated with a 2.22 months higher brain age across time points (β = 0.10, p < .001). Moreover, annualized change in pubertal development was weakly related to the rate of change in brain age (β = .047, p = 0.04). These results demonstrate a link between sexual development and brain maturation in early adolescence, and provides a basis for further investigations of the complex sociobiological impacts of puberty on life outcomes.

Benchmarking the generalizability of brain age models: Challenges posed by scanner variance and prediction bias

Machine learning has been increasingly applied to neuroimaging data to predict age, deriving a personalized biomarker with potential clinical applications. The scientific and clinical value of these models depends on their applicability to independently acquired scans from diverse sources. Accordingly, we evaluated the generalizability of two brain age models that were trained across the lifespan by applying them to three distinct early-life samples with participants aged 8-22 years. These models were chosen based on the size and diversity of their training data, but they also differed greatly in their processing methods and predictive algorithms. Specifically, one brain age model was built by applying gradient tree boosting (GTB) to extracted features of cortical thickness, surface area, and brain volume. The other model applied a 2D convolutional neural network (DBN) to minimally preprocessed slices of T1-weighted scans. Additional model variants were created to understand how generalizability changed when each model was trained with data that became more similar to the test samples in terms of age and acquisition protocols. Our results illustrated numerous trade-offs. The GTB predictions were relatively more accurate overall and yielded more reliable predictions when applied to lower quality scans. In contrast, the DBN displayed the most utility in detecting associations between brain age gaps and cognitive functioning. Broadly speaking, the largest limitations affecting generalizability were acquisition protocol differences and biased brain age estimates. If such confounds could eventually be removed without post-hoc corrections, brain age predictions may have greater utility as personalized biomarkers of healthy aging.

Predicting age from resting-state scalp EEG signals with deep convolutional neural networks on TD-brain dataset

Introduction

Brain age prediction has been shown to be clinically relevant, with errors in its prediction associated with various psychiatric and neurological conditions. While the prediction from structural and functional magnetic resonance imaging data has been feasible with high accuracy, whether the same results can be achieved with electroencephalography is unclear.

Methods

The current study aimed to create a new deep learning solution for brain age prediction using raw resting-state scalp EEG. To this end, we utilized the TD-BRAIN dataset, including 1,274 subjects (both healthy controls and individuals with various psychiatric disorders, with a total of 1,335 recording sessions). To achieve the best age prediction, we used data augmentation techniques to increase the diversity of the training set and developed a deep convolutional neural network model.

Results

The model's training was done with 10-fold cross-subject cross-validation, with the EEG recordings of the subjects used for training not considered to test the model. In training, using the relative rather than the absolute loss function led to a better mean absolute error of 5.96 years in cross-validation. We found that the best performance could be achieved when both eyes-open and eyes-closed states are used simultaneously. The frontocentral electrodes played the most important role in age prediction.

Discussion

The architecture and training method of the proposed deep convolutional neural networks (DCNN) improve state-of-the-art metrics in the age prediction task using raw resting-state EEG data by 13%. Given that brain age prediction might be a potential biomarker of numerous brain diseases, inexpensive and precise EEG-based estimation of brain age will be in demand for clinical practice.

Development and validation of a dynamic deep learning algorithm using electrocardiogram to predict dyskalaemias in patients with multiple visits

Aims

Deep learning models (DLMs) have shown superiority in electrocardiogram (ECG) analysis and have been applied to diagnose dyskalaemias. However, no study has explored the performance of DLM-enabled ECG in continuous follow-up scenarios. Therefore, we proposed a dynamic revision of DLM-enabled ECG to use personal pre-annotated ECGs to enhance the accuracy in patients with multiple visits.

Methods and results

We retrospectively collected 168 450 ECGs with corresponding serum potassium (K⁺) levels from 103 091 patients as development samples. In the internal/external validation sets, the numbers of ECGs with corresponding K⁺ were 37 246/47 604 from 13 555/20 058 patients. Our dynamic revision method showed better performance than the traditional direct prediction for diagnosing hypokalaemia [area under the receiver operating characteristic curve (AUC) = 0.730/0.720-0.788/0.778] and hyperkalaemia (AUC = 0.884/0.888-0.915/0.908) in patients with multiple visits.

Conclusion

Our method has shown a distinguishable improvement in DLMs for diagnosing dyskalaemias in patients with multiple visits, and we also proved its application in ejection fraction prediction, which could further improve daily clinical practice.

Graph Empirical Mode Decomposition-Based Data Augmentation Applied to Gifted Children MRI Analysis

Gifted children and normal controls can be distinguished by analyzing the structural connectivity (SC) extracted from MRI data. Previous studies have improved classification accuracy by extracting several features of the brain regions. However, the limited size of the database may lead to degradation when training deep neural networks as classification models. To this end, we propose to use a data augmentation method by adding artificial samples generated using graph empirical mode decomposition (GEMD). We decompose the training samples by GEMD to obtain the intrinsic mode functions (IMFs). Then, the IMFs are randomly recombined to generate the new artificial samples. After that, we use the original training samples and the new artificial samples to enlarge the training set. To evaluate the proposed method, we use a deep neural network architecture called BrainNetCNN to classify the SCs of MRI data with and without data augmentation. The results show that the data augmentation with GEMD can improve the average classification performance from 55.7 to 78%, while we get a state-of-the-art classification accuracy of 93.3% by using GEMD in some cases. Our results demonstrate that the proposed GEMD augmentation method can effectively increase the limited number of samples in the gifted children dataset, improving the classification accuracy. We also found that the classification accuracy is improved when specific features extracted from brain regions are used, achieving 93.1% for some feature selection methods.