Quantification of the Biological Age of the Brain Using Neuroimaging

Brain Age Estimation from Overnight Sleep Electroencephalography with Multi-Flow Sequence Learning

Purpose

This study aims to improve brain age estimation by developing a novel deep learning model utilizing overnight electroencephalography (EEG) data.

Methods

We address limitations in current brain age prediction methods by proposing a model trained and evaluated on multiple cohort data, covering a broad age range. The model employs a one-dimensional Swin Transformer to efficiently extract complex patterns from sleep EEG signals and a convolutional neural network with attentional mechanisms to summarize sleep structural features. A multi-flow learning-based framework attentively merges these two features, employing sleep structural information to direct and augment the EEG features. A post-prediction model is designed to integrate the age-related features throughout the night. Furthermore, we propose a DecadeCE loss function to address the problem of an uneven age distribution.

Results

We utilized 18,767 polysomnograms (PSGs) from 13,616 subjects to develop and evaluate the proposed model. The model achieves a mean absolute error (MAE) of 4.19 and a correlation of 0.97 on the mixed-cohort test set, and an MAE of 6.18 years and a correlation of 0.78 on an independent test set. Our brain age estimation work reduced the error by more than 1 year compared to other studies that also used EEG, achieving the level of neuroimaging. The estimated brain age index demonstrated longitudinal sensitivity and exhibited a significant increase of 1.27 years in individuals with psychiatric or neurological disorders relative to healthy individuals.

Conclusion

The multi-flow deep learning model proposed in this study, based on overnight EEG, represents a more accurate approach for estimating brain age. The utilization of overnight sleep EEG for the prediction of brain age is both cost-effective and adept at capturing dynamic changes. These findings demonstrate the potential of EEG in predicting brain age, presenting a noninvasive and accessible method for assessing brain aging.

Brain age as a biomarker for pathological versus healthy ageing - a REMEMBER study

OBJECTIVES

This study aimed to evaluate the potential clinical value of a new brain age prediction model as a single interpretable variable representing the condition of our brain. Among many clinical use cases, brain age could be a novel outcome measure to assess the preventive effect of life-style interventions.

METHODS

The REMEMBER study population (N = 742) consisted of cognitively healthy (HC,N = 91), subjective cognitive decline (SCD,N = 65), mild cognitive impairment (MCI,N = 319) and AD dementia (ADD,N = 267) subjects. Automated brain volumetry of global, cortical, and subcortical brain structures computed by the CE-labeled and FDA-cleared software icobrain dm (dementia) was retrospectively extracted from T1-weighted MRI sequences that were acquired during clinical routine at participating memory clinics from the Belgian Dementia Council. The volumetric features, along with sex, were combined into a weighted sum using a linear model, and were used to predict 'brain age' and 'brain predicted age difference' (BPAD = brain age-chronological age) for every subject.

RESULTS

MCI and ADD patients showed an increased brain age compared to their chronological age. Overall, brain age outperformed BPAD and chronological age in terms of classification accuracy across the AD spectrum. There was a weak-to-moderate correlation between total MMSE score and both brain age (r = -0.38,p < .001) and BPAD (r = -0.26,p < .001). Noticeable trends, but no significant correlations, were found between BPAD and incidence of conversion from MCI to ADD, nor between BPAD and conversion time from MCI to ADD. BPAD was increased in heavy alcohol drinkers compared to non-/sporadic (p = .014) and moderate (p = .040) drinkers.

CONCLUSIONS

Brain age and associated BPAD have the potential to serve as indicators for, and to evaluate the impact of lifestyle modifications or interventions on, brain health.

Prediction of brain age in individuals with and at risk for alcohol use disorder using brain morphological features

Brain age measures predicted from structural and functional brain features are increasingly being used to understand brain integrity, disorders, and health. While there is a vast literature showing aberrations in both structural and functional brain measures in individuals with and at risk for alcohol use disorder (AUD), few studies have investigated brain age in these groups. The current study examines brain age measures predicted using brain morphological features, such as cortical thickness and brain volume, in individuals with a lifetime diagnosis of AUD as well as in those at higher risk to develop AUD from families with multiple members affected with AUD (i.e., higher family history density (FHD) scores). The AUD dataset included a group of 30 adult males (mean age = 41.25 years) with a lifetime diagnosis of AUD and currently abstinent and a group of 30 male controls (mean age = 27.24 years) without any history of AUD. A second dataset of young adults who were categorized based on their FHD scores comprised a group of 40 individuals (20 males) with high FHD of AUD (mean age = 25.33 years) and a group of 31 individuals (18 males) with low FHD (mean age = 25.47 years). Brain age was predicted using 187 brain morphological features of cortical thickness and brain volume in an XGBoost regression model; a bias-correction procedure was applied to the predicted brain age. Results showed that both AUD and high FHD individuals showed an increase of 1.70 and 0.09 years (1.08 months), respectively, in their brain age relative to their chronological age, suggesting accelerated brain aging in AUD and risk for AUD. Increased brain age was associated with poor performance on neurocognitive tests of executive functioning in both AUD and high FHD individuals, indicating that brain age can also serve as a proxy for cognitive functioning and brain health. These findings on brain aging in these groups may have important implications for the prevention and treatment of AUD and ensuing cognitive decline.

Magnetic resonance image-based brain age as a discriminator of dementia conversion in patients with amyloid-negative amnestic mild cognitive impairment

Patients with amyloid-negative amnestic mild cognitive impairment (MCI) have a conversion rate of approximately 10% to dementia within 2 years. We aimed to investigate whether brain age is an important factor in predicting conversion to dementia in patients with amyloid-negative amnestic MCI. We conducted a retrospective cohort study of patients with amyloid-negative amnestic MCI. All participants underwent detailed neuropsychological evaluation, brain magnetic resonance imaging (MRI), and [18F]-florbetaben positron emission tomography. Brain age was determined by the volumetric assessment of 12 distinct brain regions using an automatic segmentation software. During the follow-up period, 38% of the patients converted from amnestic MCI to dementia. Further, 73% of patients had a brain age greater than their actual chronological age. When defining 'survival' as the non-conversion of MCI to dementia, these groups differed significantly in survival probability (p = 0.036). The low-educated female group with a brain age greater than their actual age had the lowest survival rate among all groups. Our findings suggest that the MRI-based brain age used in this study can contribute to predicting conversion to dementia in patients with amyloid-negative amnestic MCI.

Deep learning-based age estimation from clinical Computed Tomography image data of the thorax and abdomen in the adult population

Aging is an important risk factor for disease, leading to morphological change that can be assessed on Computed Tomography (CT) scans. We propose a deep learning model for automated age estimation based on CT- scans of the thorax and abdomen generated in a clinical routine setting. These predictions could serve as imaging biomarkers to estimate a "biological" age, that better reflects a patient's true physical condition. A pre-trained ResNet-18 model was modified to predict chronological age as well as to quantify its aleatoric uncertainty. The model was trained using 1653 non-pathological CT-scans of the thorax and abdomen of subjects aged between 20 and 85 years in a 5-fold cross-validation scheme. Generalization performance as well as robustness and reliability was assessed on a publicly available test dataset consisting of thorax-abdomen CT-scans of 421 subjects. Score-CAM saliency maps were generated for interpretation of model outputs. We achieved a mean absolute error of 5.76 ± 5.17 years with a mean uncertainty of 5.01 ± 1.44 years after 5-fold cross-validation. A mean absolute error of 6.50 ± 5.17 years with a mean uncertainty of 6.39 ± 1.46 years was obtained on the test dataset. CT-based age estimation accuracy was largely uniform across all age groups and between male and female subjects. The generated saliency maps highlighted especially the lumbar spine and abdominal aorta. This study demonstrates, that accurate and generalizable deep learning-based automated age estimation is feasible using clinical CT image data. The trained model proved to be robust and reliable. Methods of uncertainty estimation and saliency analysis improved the interpretability.

Extensive T1-weighted MRI Preprocessing Improves Generalizability of Deep Brain Age Prediction Models

Brain age is an estimate of chronological age obtained from T1-weighted magnetic resonance images (T1w MRI) and represents a simple diagnostic biomarker of brain ageing and associated diseases. While the current best accuracy of brain age predictions on T1w MRIs of healthy subjects ranges from two to three years, comparing results from different studies is challenging due to differences in the datasets, T1w preprocessing pipelines, and performance metrics used. This paper investigates the impact of T1w image preprocessing on the performance of four deep learning brain age models presented in recent literature. Four preprocessing pipelines were evaluated, differing in terms of registration, grayscale correction, and software implementation. The results showed that the choice of software or preprocessing steps can significantly affect the prediction error, with a maximum increase of 0.7 years in mean absolute error (MAE) for the same model and dataset. While grayscale correction had no significant impact on MAE, the affine registration, compared to the rigid registration of T1w images to brain atlas was shown to statistically significantly improve MAE. Models trained on 3D images with isotropic 1 mm3 resolution exhibited less sensitivity to the T1w preprocessing variations compared to 2D models or those trained on downsampled 3D images. Some proved invariant to the preprocessing pipeline, however only after offset correction. Our findings generally indicate that extensive T1w preprocessing enhances the MAE, especially when applied to a new dataset. This runs counter to prevailing research literature which suggests that models trained on minimally preprocessed T1w scans are better poised for age predictions on MRIs from unseen scanners. Regardless of model or T1w preprocessing used, we show that to enable generalization of model's performance on a new dataset with either the same or different T1w preprocessing than the one applied in model training, some form of offset correction should be applied.

MRI-based brain age prediction model for children under 3 years old using deep residual network

Early identification and intervention of abnormal brain development individual subjects are of great significance, especially during the earliest and most active stage of brain development in children aged under 3. Neuroimage-based brain's biological age has been associated with health, ability, and remaining life. However, the existing brain age prediction models based on neuroimage are predominantly adult-oriented. Here, we collected 658 T1-weighted MRI scans from 0 to 3 years old healthy controls and developed an accurate brain age prediction model for young children using deep learning techniques with high accuracy in capturing age-related changes. The performance of the deep learning-based model is comparable to that of the SVR-based model, showcasing remarkable precision and yielding a noteworthy correlation of 91% between the predicted brain age and the chronological age. Our results demonstrate the accuracy of convolutional neural network (CNN) brain-predicted age using raw T1-weighted MRI data with minimum preprocessing necessary. We also applied our model to children with low birth weight, premature delivery history, autism, and ADHD, and discovered that the brain age was delayed in children with extremely low birth weight (less than 1000 g) while ADHD may cause accelerated aging of the brain. Our child-specific brain age prediction model can be a valuable quantitative tool to detect abnormal brain development and can be helpful in the early identification and intervention of age-related brain disorders.

Total Sleep Deprivation Increases Brain Age Prediction Reversibly in Multisite Samples of Young Healthy Adults

Sleep loss pervasively affects the human brain at multiple levels. Age-related changes in several sleep characteristics indicate that reduced sleep quality is a frequent characteristic of aging. Conversely, sleep disruption may accelerate the aging process, yet it is not known what will happen to the age status of the brain if we can manipulate sleep conditions. To tackle this question, we used an approach of brain age to investigate whether sleep loss would cause age-related changes in the brain. We included MRI data of 134 healthy volunteers (mean chronological age of 25.3 between the age of 19 and 39 years, 42 females/92 males) from five datasets with different sleep conditions. Across three datasets with the condition of total sleep deprivation (>24 h of prolonged wakefulness), we consistently observed that total sleep deprivation increased brain age by 1-2 years regarding the group mean difference with the baseline. Interestingly, after one night of recovery sleep, brain age was not different from baseline. We also demonstrated the associations between the change in brain age after total sleep deprivation and the sleep variables measured during the recovery night. By contrast, brain age was not significantly changed by either acute (3 h time-in-bed for one night) or chronic partial sleep restriction (5 h time-in-bed for five continuous nights). Together, the convergent findings indicate that acute total sleep loss changes brain morphology in an aging-like direction in young participants and that these changes are reversible by recovery sleep.SIGNIFICANCE STATEMENT Sleep is fundamental for humans to maintain normal physical and psychological functions. Experimental sleep deprivation is a variable-controlling approach to engaging the brain among different sleep conditions for investigating the responses of the brain to sleep loss. Here, we quantified the response of the brain to sleep deprivation by using the change of brain age predictable with brain morphologic features. In three independent datasets, we consistently found increased brain age after total sleep deprivation, which was associated with the change in sleep variables. Moreover, no significant change in brain age was found after partial sleep deprivation in another two datasets. Our study provides new evidence to explain the brainwide effect of sleep loss in an aging-like direction.

Accelerated functional brain aging in major depressive disorder: evidence from a large scale fMRI analysis of Chinese participants

Major depressive disorder (MDD) is one of the most common mental health conditions that has been intensively investigated for its association with brain atrophy and mortality. Recent studies suggest that the deviation between the predicted and the chronological age can be a marker of accelerated brain aging to characterize MDD. However, current conclusions are usually drawn based on structural MRI information collected from Caucasian participants. The universality of this biomarker needs to be further validated by subjects with different ethnic/racial backgrounds and by different types of data. Here we make use of the REST-meta-MDD, a large scale resting-state fMRI dataset collected from multiple cohort participants in China. We develop a stacking machine learning model based on 1101 healthy controls, which estimates a subject's chronological age from fMRI with promising accuracy. The trained model is then applied to 1276 MDD patients from 24 sites. We observe that MDD patients exhibit a +4.43 years (p < 0.0001, Cohen's d = 0.31, 95% CI: 2.23-3.88) higher brain-predicted age difference (brain-PAD) compared to controls. In the MDD subgroup, we observe a statistically significant +2.09 years (p < 0.05, Cohen's d = 0.134525) brain-PAD in antidepressant users compared to medication-free patients. The statistical relationship observed is further checked by three different machine learning algorithms. The positive brain-PAD observed in participants in China confirms the presence of accelerated brain aging in MDD patients. The utilization of functional brain connectivity for age estimation verifies existing findings from a new dimension.

Age estimation from sleep studies using deep learning predicts life expectancy

Sleep disturbances increase with age and are predictors of mortality. Here, we present deep neural networks that estimate age and mortality risk through polysomnograms (PSGs). Aging was modeled using 2500 PSGs and tested in 10,699 PSGs from men and women in seven different cohorts aged between 20 and 90. Ages were estimated with a mean absolute error of 5.8 ± 1.6 years, while basic sleep scoring measures had an error of 14.9 ± 6.29 years. After controlling for demographics, sleep, and health covariates, each 10-year increment in age estimate error (AEE) was associated with increased all-cause mortality rate of 29% (95% confidence interval: 20-39%). An increase from -10 to +10 years in AEE translates to an estimated decreased life expectancy of 8.7 years (95% confidence interval: 6.1-11.4 years). Greater AEE was mostly reflected in increased sleep fragmentation, suggesting this is an important biomarker of future health independent of sleep apnea.

Mind the gap: Performance metric evaluation in brain-age prediction

Estimating age based on neuroimaging-derived data has become a popular approach to developing markers for brain integrity and health. While a variety of machine-learning algorithms can provide accurate predictions of age based on brain characteristics, there is significant variation in model accuracy reported across studies. We predicted age in two population-based datasets, and assessed the effects of age range, sample size and age-bias correction on the model performance metrics Pearson's correlation coefficient (r), the coefficient of determination (R² ), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The results showed that these metrics vary considerably depending on cohort age range; r and R² values are lower when measured in samples with a narrower age range. RMSE and MAE are also lower in samples with a narrower age range due to smaller errors/brain age delta values when predictions are closer to the mean age of the group. Across subsets with different age ranges, performance metrics improve with increasing sample size. Performance metrics further vary depending on prediction variance as well as mean age difference between training and test sets, and age-bias corrected metrics indicate high accuracy-also for models showing poor initial performance. In conclusion, performance metrics used for evaluating age prediction models depend on cohort and study-specific data characteristics, and cannot be directly compared across different studies. Since age-bias corrected metrics generally indicate high accuracy, even for poorly performing models, inspection of uncorrected model results provides important information about underlying model attributes such as prediction variance.

Assessment of brain age in posttraumatic stress disorder: Findings from the ENIGMA PTSD and brain age working groups

BACKGROUND

Posttraumatic stress disorder (PTSD) is associated with markers of accelerated aging. Estimates of brain age, compared to chronological age, may clarify the effects of PTSD on the brain and may inform treatment approaches targeting the neurobiology of aging in the context of PTSD.

METHOD

Adult subjects (N = 2229; 56.2% male) aged 18-69 years (mean = 35.6, SD = 11.0) from 21 ENIGMA-PGC PTSD sites underwent T1-weighted brain structural magnetic resonance imaging, and PTSD assessment (PTSD+, n = 884). Previously trained voxel-wise (brainageR) and region-of-interest (BARACUS and PHOTON) machine learning pipelines were compared in a subset of control subjects (n = 386). Linear mixed effects models were conducted in the full sample (those with and without PTSD) to examine the effect of PTSD on brain predicted age difference (brain PAD; brain age - chronological age) controlling for chronological age, sex, and scan site.

RESULTS

BrainageR most accurately predicted brain age in a subset (n = 386) of controls (brainageR: ICC = 0.71, R = 0.72, MAE = 5.68; PHOTON: ICC = 0.61, R = 0.62, MAE = 6.37; BARACUS: ICC = 0.47, R = 0.64, MAE = 8.80). Using brainageR, a three-way interaction revealed that young males with PTSD exhibited higher brain PAD relative to male controls in young and old age groups; old males with PTSD exhibited lower brain PAD compared to male controls of all ages.

DISCUSSION

Differential impact of PTSD on brain PAD in younger versus older males may indicate a critical window when PTSD impacts brain aging, followed by age-related brain changes that are consonant with individuals without PTSD. Future longitudinal research is warranted to understand how PTSD impacts brain aging across the lifespan.

Linking Brain Age Gap to Mental and Physical Health in the Berlin Aging Study II

From a biological perspective, humans differ in the speed they age, and this may manifest in both mental and physical health disparities. The discrepancy between an individual's biological and chronological age of the brain ("brain age gap") can be assessed by applying machine learning techniques to Magnetic Resonance Imaging (MRI) data. Here, we examined the links between brain age gap and a broad range of cognitive, affective, socioeconomic, lifestyle, and physical health variables in up to 335 adults of the Berlin Aging Study II. Brain age gap was assessed using a validated prediction model that we previously trained on MRI scans of 32,634 UK Biobank individuals. Our statistical analyses revealed overall stronger evidence for a link between higher brain age gap and less favorable health characteristics than expected under the null hypothesis of no effect, with 80% of the tested associations showing hypothesis-consistent effect directions and 23% reaching nominal significance. The most compelling support was observed for a cluster covering both cognitive performance variables (episodic memory, working memory, fluid intelligence, digit symbol substitution test) and socioeconomic variables (years of education and household income). Furthermore, we observed higher brain age gap to be associated with heavy episodic drinking, higher blood pressure, and higher blood glucose. In sum, our results point toward multifaceted links between brain age gap and human health. Understanding differences in biological brain aging may therefore have broad implications for future informed interventions to preserve mental and physical health in old age.

Brain aging in major depressive disorder: results from the ENIGMA major depressive disorder working group

Major depressive disorder (MDD) is associated with an increased risk of brain atrophy, aging-related diseases, and mortality. We examined potential advanced brain aging in adult MDD patients, and whether this process is associated with clinical characteristics in a large multicenter international dataset. We performed a mega-analysis by pooling brain measures derived from T1-weighted MRI scans from 19 samples worldwide. Healthy brain aging was estimated by predicting chronological age (18-75 years) from 7 subcortical volumes, 34 cortical thickness and 34 surface area, lateral ventricles and total intracranial volume measures separately in 952 male and 1236 female controls from the ENIGMA MDD working group. The learned model coefficients were applied to 927 male controls and 986 depressed males, and 1199 female controls and 1689 depressed females to obtain independent unbiased brain-based age predictions. The difference between predicted "brain age" and chronological age was calculated to indicate brain-predicted age difference (brain-PAD). On average, MDD patients showed a higher brain-PAD of +1.08 (SE 0.22) years (Cohen's d = 0.14, 95% CI: 0.08-0.20) compared with controls. However, this difference did not seem to be driven by specific clinical characteristics (recurrent status, remission status, antidepressant medication use, age of onset, or symptom severity). This highly powered collaborative effort showed subtle patterns of age-related structural brain abnormalities in MDD. Substantial within-group variance and overlap between groups were observed. Longitudinal studies of MDD and somatic health outcomes are needed to further assess the clinical value of these brain-PAD estimates.

Factors associated with brain ageing - a systematic review

Background

Brain age is a biomarker that predicts chronological age using neuroimaging features. Deviations of this predicted age from chronological age is considered a sign of age-related brain changes, or commonly referred to as brain ageing. The aim of this systematic review is to identify and synthesize the evidence for an association between lifestyle, health factors and diseases in adult populations, with brain ageing.

Methods

This systematic review was undertaken in accordance with the PRISMA guidelines. A systematic search of Embase and Medline was conducted to identify relevant articles using search terms relating to the prediction of age from neuroimaging data or brain ageing. The tables of two recent review papers on brain ageing were also examined to identify additional articles. Studies were limited to adult humans (aged 18 years and above), from clinical or general populations. Exposures and study design of all types were also considered eligible.

Results

A systematic search identified 52 studies, which examined brain ageing in clinical and community dwelling adults (mean age between 21 to 78 years, ~ 37% were female). Most research came from studies of individuals diagnosed with schizophrenia or Alzheimer’s disease, or healthy populations that were assessed cognitively. From these studies, psychiatric and neurologic diseases were most commonly associated with accelerated brain ageing, though not all studies drew the same conclusions. Evidence for all other exposures is nascent, and relatively inconsistent. Heterogenous methodologies, or methods of outcome ascertainment, were partly accountable.

Conclusion

This systematic review summarised the current evidence for an association between genetic, lifestyle, health, or diseases and brain ageing. Overall there is good evidence to suggest schizophrenia and Alzheimer’s disease are associated with accelerated brain ageing. Evidence for all other exposures was mixed or limited. This was mostly due to a lack of independent replication, and inconsistency across studies that were primarily cross sectional in nature. Future research efforts should focus on replicating current findings, using prospective datasets.

Trial registration

A copy of the review protocol can be accessed through PROSPERO, registration number CRD42020142817.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12883-021-02331-4.

Prominent health problems, socioeconomic deprivation, and higher brain age in lonely and isolated individuals: A population-based study

Loneliness is linked to increased risk for Alzheimer's disease, but little is known about factors potentially contributing to adverse brain health in lonely individuals. In this study, we used data from 24,867 UK Biobank participants to investigate risk factors related to loneliness and estimated brain age based on neuroimaging data. The results showed that on average, individuals who self-reported loneliness on a single yes/no item scored higher on neuroticism, depression, social isolation, and socioeconomic deprivation, performed less physical activity, and had higher BMI compared to individuals who did not report loneliness. In line with studies pointing to a genetic overlap of loneliness with neuroticism and depression, permutation feature importance ranked these factors as the most important for classifying lonely vs. not lonely individuals (ROC AUC = 0.83). While strongly linked to loneliness, neuroticism and depression were not associated with brain age estimates. Conversely, objective social isolation showed a main effect on brain age, and individuals reporting both loneliness and social isolation showed higher brain age relative to controls - as part of a prominent risk profile with elevated scores on socioeconomic deprivation and unhealthy lifestyle behaviours, in addition to neuroticism and depression. While longitudinal studies are required to determine causality, this finding may indicate that the combination of social isolation and a genetic predisposition for loneliness involves a risk for adverse brain health. Importantly, the results underline the complexity in associations between loneliness and adverse health outcomes, where observed risks likely depend on a combination of interlinked variables including genetic as well as social, behavioural, physical, and socioeconomic factors.

The stage-specifically accelerated brain aging in never-treated first-episode patients with depression

Depression associated with structural brain abnormalities is hypothesized to be related with accelerated brain aging. However, there is far from a unified conclusion because of clinical variations such as medication status, cumulative illness burden. To explore whether brain age is accelerated in never‐treated first‐episode patients with depression and its association with clinical characteristics, we constructed a prediction model where gray matter volumes measured by voxel‐based morphometry derived from T1‐weighted MRI scans were treated as features. The prediction model was first validated using healthy controls (HCs) in two Chinese Han datasets (Dataset 1, N = 130 for HCs and N = 195 for patients with depression; Dataset 2, N = 270 for HCs) separately or jointly, then the trained prediction model using HCs (N = 400) was applied to never‐treated first‐episode patients with depression (N = 195). The brain‐predicted age difference (brain‐PAD) scores defined as the difference between predicted brain age and chronological age, were calculated for all participants and compared between patients with age‐, gender‐, educational level‐matched HCs in Dataset 1. Overall, patients presented higher brain‐PAD scores suggesting patients with depression having an “older” brain than expected. More specially, this difference occurred at illness onset (illness duration <3 months) and following 2 years then disappeared as the illness further advanced (>2 years) in patients. This phenomenon was verified by another data‐driven method and significant correlation between brain‐PAD scores and illness duration in patients. Our results reveal that accelerated brain aging occurs at illness onset and suggest it is a stage‐dependent phenomenon in depression.

Brain-predicted age difference score is related to specific cognitive functions: a multi-site replication analysis

Brain-predicted age difference scores are calculated by subtracting chronological age from 'brain' age, which is estimated using neuroimaging data. Positive scores reflect accelerated ageing and are associated with increased mortality risk and poorer physical function. To date, however, the relationship between brain-predicted age difference scores and specific cognitive functions has not been systematically examined using appropriate statistical methods. First, applying machine learning to 1359 T1-weighted MRI scans, we predicted the relationship between chronological age and voxel-wise grey matter data. This model was then applied to MRI data from three independent datasets, significantly predicting chronological age in each dataset: Dokuz Eylül University (n = 175), the Cognitive Reserve/Reference Ability Neural Network study (n = 380), and The Irish Longitudinal Study on Ageing (n = 487). Each independent dataset had rich neuropsychological data. Brain-predicted age difference scores were significantly negatively correlated with performance on measures of general cognitive status (two datasets); processing speed, visual attention, and cognitive flexibility (three datasets); visual attention and cognitive flexibility (two datasets); and semantic verbal fluency (two datasets). As such, there is firm evidence of correlations between increased brain-predicted age differences and reduced cognitive function in some domains that are implicated in cognitive ageing.

Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data

Brain morphology varies across the ageing trajectory and the prediction of a person's age using brain features can aid the detection of abnormalities in the ageing process. Existing studies on such “brain age prediction” vary widely in terms of their methods and type of data, so at present the most accurate and generalisable methodological approach is unclear. Therefore, we used the UK Biobank data set (N = 10,824, age range 47–73) to compare the performance of the machine learning models support vector regression, relevance vector regression and Gaussian process regression on whole‐brain region‐based or voxel‐based structural magnetic resonance imaging data with or without dimensionality reduction through principal component analysis. Performance was assessed in the validation set through cross‐validation as well as an independent test set. The models achieved mean absolute errors between 3.7 and 4.7 years, with those trained on voxel‐level data with principal component analysis performing best. Overall, we observed little difference in performance between models trained on the same data type, indicating that the type of input data had greater impact on performance than model choice. All code is provided online in the hope that this will aid future research.

When your brain looks older than expected: combined lifestyle risk and BrainAGE

Lifestyle may be one source of unexplained variance in the great interindividual variability of the brain in age-related structural differences. While physical and social activity may protect against structural decline, other lifestyle behaviors may be accelerating factors. We examined whether riskier lifestyle correlates with accelerated brain aging using the BrainAGE score in 622 older adults from the 1000BRAINS cohort. Lifestyle was measured using a combined lifestyle risk score, composed of risk (smoking, alcohol intake) and protective variables (social integration and physical activity). We estimated individual BrainAGE from T1-weighted MRI data indicating accelerated brain atrophy by higher values. Then, the effect of combined lifestyle risk and individual lifestyle variables was regressed against BrainAGE. One unit increase in combined lifestyle risk predicted 5.04 months of additional BrainAGE. This prediction was driven by smoking (0.6 additional months of BrainAGE per pack-year) and physical activity (0.55 less months in BrainAGE per metabolic equivalent). Stratification by sex revealed a stronger association between physical activity and BrainAGE in males than females. Overall, our observations may be helpful with regard to lifestyle-related tailored prevention measures that slow changes in brain structure in older adults.

An automated machine learning approach to predict brain age from cortical anatomical measures

The use of machine learning (ML) algorithms has significantly increased in neuroscience. However, from the vast extent of possible ML algorithms, which one is the optimal model to predict the target variable? What are the hyperparameters for such a model? Given the plethora of possible answers to these questions, in the last years, automated ML (autoML) has been gaining attention. Here, we apply an autoML library called Tree-based Pipeline Optimisation Tool (TPOT) which uses a tree-based representation of ML pipelines and conducts a genetic programming-based approach to find the model and its hyperparameters that more closely predicts the subject's true age. To explore autoML and evaluate its efficacy within neuroimaging data sets, we chose a problem that has been the focus of previous extensive study: brain age prediction. Without any prior knowledge, TPOT was able to scan through the model space and create pipelines that outperformed the state-of-the-art accuracy for Freesurfer-based models using only thickness and volume information for anatomical structure. In particular, we compared the performance of TPOT (mean absolute error [MAE]: 4.612 ± .124 years) and a relevance vector regression (MAE 5.474 ± .140 years). TPOT also suggested interesting combinations of models that do not match the current most used models for brain prediction but generalise well to unseen data. AutoML showed promising results as a data-driven approach to find optimal models for neuroimaging applications.

Predicting Age with Deep Neural Networks from Polysomnograms

The aim of this study was to design a new deep learning framework for end-to-end processing of polysomnograms. This framework can be trained to analyze whole-night polysomnograms without the limitations of and bias towards clinical scoring guidelines. We validated the framework by predicting the age of subjects. We designed a hierarchical attention network architecture, which can be pre-trained to predict labels based on 5-minute epochs of data and fine-tuned to predict based on whole-night polysomnography recordings. The model was trained on 511 recordings from the Cleveland Family study and tested on 146 test subjects aged between 6 to 88 years. The proposed network achieved a mean absolute error of 7.36 years and a correlation to true age of 0.857. Sleep can be analyzed using our end-to-end deep learning framework, which we expect can generalize to learning other subject-specific labels such as sleep disorders. The difference in the predicted and chronological age is further proposed as an estimate of biological age.

Longitudinal Assessment of Multiple Sclerosis with the Brain-Age Paradigm

OBJECTIVE

During the natural course of multiple sclerosis (MS), the brain is exposed to aging as well as disease effects. Brain aging can be modeled statistically; the so-called "brain-age" paradigm. Here, we evaluated whether brain-predicted age difference (brain-PAD) was sensitive to the presence of MS, clinical progression, and future outcomes.

METHODS

In a longitudinal, multicenter sample of 3,565 magnetic resonance imaging (MRI) scans, in 1,204 patients with MS and clinically isolated syndrome (CIS) and 150 healthy controls (mean follow-up time: patients 3.41 years, healthy controls 1.97 years), we measured "brain-predicted age" using T1-weighted MRI. We compared brain-PAD among patients with MS and patients with CIS and healthy controls, and between disease subtypes. Relationships between brain-PAD and Expanded Disability Status Scale (EDSS) were explored.

RESULTS

Patients with MS had markedly higher brain-PAD than healthy controls (mean brain-PAD +10.3 years; 95% confidence interval [CI] = 8.5-12.1] versus 4.3 years; 95% CI = 2.1 to 6.4; p < 0.001). The highest brain-PADs were in secondary-progressive MS (+13.3 years; 95% CI = 11.3-15.3). Brain-PAD at study entry predicted time-to-disability progression (hazard ratio 1.02; 95% CI = 1.01-1.03; p < 0.001); although normalized brain volume was a stronger predictor. Greater annualized brain-PAD increases were associated with greater annualized EDSS score (r = 0.26; p < 0.001).

INTERPRETATION

The brain-age paradigm is sensitive to MS-related atrophy and clinical progression. A higher brain-PAD at baseline was associated with more rapid disability progression and the rate of change in brain-PAD related to worsening disability. Potentially, "brain-age" could be used as a prognostic biomarker in early-stage MS, to track disease progression or stratify patients for clinical trial enrollment. ANN NEUROL 2020 ANN NEUROL 2020;88:93-105.

Brain-Age Prediction Using Shallow Machine Learning: Predictive Analytics Competition 2019

As we age, our brain structure changes and our cognitive capabilities decline. Although brain aging is universal, rates of brain aging differ markedly, which can be associated with pathological mechanism of psychiatric and neurological diseases. Predictive models have been applied to neuroimaging data to learn patterns associated with this variability and develop a neuroimaging biomarker of the brain condition. Aiming to stimulate the development of more accurate brain-age predictors, the Predictive Analytics Competition (PAC) 2019 provided a challenge that included a dataset of 2,640 participants. Here, we present our approach which placed between the top 10 of the challenge. We developed an ensemble of shallow machine learning methods (e.g., Support Vector Regression and Decision Tree-based regressors) that combined voxel-based and surface-based morphometric data. We used normalized brain volume maps (i.e., gray matter, white matter, or both) and features of cortical regions and anatomical structures, like cortical thickness, volume, and mean curvature. In order to fine-tune the hyperparameters of the machine learning methods, we combined the use of genetic algorithms and grid search. Our ensemble had a mean absolute error of 3.7597 years on the competition, showing the potential that shallow methods still have in predicting brain-age.