Biological brain age prediction using machine learning on structural neuroimaging data: Multi-cohort validation against biomarkers of Alzheimer's disease and neurodegeneration stratified by sex

The mediating role of neuroimaging-derived biological brain age in the association between risk factors for dementia and cognitive decline in middle-aged and older individuals without cognitive impairment: a cohort study

BACKGROUND

Neuroimaging-based brain-age delta has been shown to be a mediator linking cardiovascular risk factors to cognitive function. We aimed to assess the mediating role of brain-age delta in the association between modifiable risk factors of dementia and longitudinal cognitive decline in middle-aged and older individuals who are asymptomatic, stratified by Alzheimer's disease pathology. We also explored whether the mediation effect is specific to cognitive domain.

METHODS

In this cohort study, we included participants from the ALFA+ cohort aged between 45 years and 65 years who were cognitively unimpaired and who had available structural MRI, cerebrospinal fluid β-amyloid (Aβ)42 and Aβ40 measurements obtained within 1 year of each other, modifiable risk factors assessment, and cognitive evaluation over 3 years. Participants were recruited from the Barcelonaβeta Brain Research Center (Barcelona, Spain). Included individuals underwent a first assessment between Oct 25, 2016, and Jan 28, 2020, and a follow-up cognitive assessment 3·28 (SD 0·27) years later. We computed brain-age delta and composites of different cognitive function domains (preclinical Alzheimer's cognitive composite [PACC], attention, executive function, episodic memory, visual processing, and language). We used partial least squares path modelling to explore mediation effects in the associations between modifiable risk factors (including cardiovascular, mental health, mood, metabolic or endocrine history, and alcohol use) and changes in cognitive composites. To assess the role of Alzheimer's disease pathology, we computed separate models for Aβ-negative and Aβ-positive individuals.

FINDINGS

Of the 419 participants enrolled in ALFA+, 302 met our inclusion criteria, of which 108 participants were classified as Aβ-positive and 194 as Aβ-negative. In Aβ-positive individuals, brain-age delta partially mediated (percent mediation proportion 15·73% [95% CI 14·22-16·66]) the association between modifiable risk factors and decline in overall cognition (across cognitive domains). Brain-age delta fully mediated (mediation proportion 28·03% [26·25-29·21]) the effect of modifiable risk factors on the PACC, wherein increased values for risk factors correlated with an older brain-age delta, and, consequently, an older brain-age delta was linked to greater PACC decline. This effect appears to be primarily driven by memory decline. Mediation was not significant in Aβ-negative individuals (3·52% [0·072-4·17]) on PACC, although path coefficients were not significantly different from those in the Aβ-positive group.

INTERPRETATION

Our findings suggest that brain-age delta captures the association between modifiable risk factors and longitudinal cognitive decline in middle-aged and older people. In asymptomatic middle-aged and older individuals who are Aβ-positive, the pathology might be the strongest driver of cognitive decline, whereas the effect of risk factors is smaller. Our results highlight the potential of brain-age delta as an objective outcome measure for preventive lifestyle interventions targeting cognitive decline.

FUNDING

La Caixa Foundation, the TriBEKa Imaging Platform, and the Universities and Research Secretariat of the Catalan Government.

TRANSLATION

For the Spanish translation of the abstract see Supplementary Materials section.

Application of AI in biological age prediction

The development of anti-aging interventions requires quantitative measurement of biological age. Machine learning models, known as "aging clocks," are built by leveraging diverse aging biomarkers that vary across lifespan to predict biological age. In addition to traditional aging clocks harnessing epigenetic signatures derived from bulk samples, emerging technologies allow the biological age estimating at single-cell level to dissect cellular diversity in aging tissues. Moreover, imaging-based aging clocks are increasingly employed with the advantage of non-invasive measurement, making it suitable for large-scale human cohort studies. To fully capture the features in the ever-growing multi-modal and high-dimensional aging-related data and uncover disease associations, deep-learning based approaches, which are effective to learn complex and non-linear relationships without relying on pre-defined features, are increasingly applied. The use of big data and AI-based aging clocks has achieved high accuracy, interpretability and generalizability, guiding clinical applications to delay age-related diseases and extend healthy lifespans.

Structural indices of brain aging in methamphetamine use disorder

BACKGROUND

Methamphetamine use is surging globally. It has been linked to premature stroke, Parkinsonism, and dementia, suggesting that it may accelerate brain aging.

METHODS

We performed a retrospective study to determine if structural indices of brain aging were more prevalent prior to old age (26 - 54 years) in individuals with Methamphetamine Use Disorder (MUD), who were in early abstinence (M ± SD = 22.1 ± 25.6 days) than in healthy control (HC) participants. We compared T1-weighted MRI brain scans in age- and sex-matched groups (n = 89/group) on three structural features of brain aging: the brain volume/cerebrospinal fluid (BV/CSF) index, volume of white matter hypointensities/lesions, and choroid plexus volume.

RESULTS

The MUD group had a lower mean BV/CSF index and larger volumes of white matter hypointensities and choroid plexus (p-values < 0.01). Regression analyses showed significant age-by-group effects, indicating different age trajectories of the BV/CSF index and choroid plexus volume, consistent with abnormal global brain atrophy and choroid plexus pathology in the MUD group. Significant age and group main effects reflected a larger volume of white matter hypointensities for older participants across groups and for the MUD group irrespective of age. None of the three measures of brain aging correlated significantly with recent use or duration of recent abstinence from methamphetamine.

CONCLUSIONS

Premature brain pathology, which may reflect cerebrovascular damage and dysfunction of the choroid plexus, occurs in people with MUD. Such pathology may affect cognition and thereby efficacy of behavioral treatments for MUD.

Structure-decoupled functional connectome-based brain age prediction provides higher association to cognition

Brain age prediction as well as the prediction difference has been well examined to be a potential biomarker for brain disease or abnormal aging process. However, less knowledge was reported for the cognitive association within normal population. In this study, we proposed a novel approach to brain age prediction by structure-decoupled functional connectome. The original functional connectome was decomposed and decoupled into a structure-decoupled functional connectome using structural connectome harmonics. Our method was applied to a large dataset of normal aging individuals and achieved a high correlation between predicted and chronological age (r = 0.77). Both the original FC and structure-decoupled FC could be well-trained in a brain age prediction model. Significant remarkable relationships between the brain age prediction difference (predicted age minus chronological age) and cognitive scores were discovered. However, the brain age-predicted difference driven by structure-decoupled FC showed a stronger correction to the two cognitive scores (MMSE: r = -0.27, P -value = 0.002; MoCA: r = -0.32, P -value = 0.0003). Our findings suggest that our structure-decoupled functional connectivity approach could provide a more individual-specific functional network, leading to improved brain age prediction performance and a better understanding of cognitive decline in aging.

A deep neural network estimation of brain age is sensitive to cognitive impairment and decline

The greatest known risk factor for Alzheimer's disease (AD) is age. While both normal aging and AD pathology involve structural changes in the brain, their trajectories of atrophy are not the same. Recent developments in artificial intelligence have encouraged studies to leverage neuroimaging-derived measures and deep learning approaches to predict brain age, which has shown promise as a sensitive biomarker in diagnosing and monitoring AD. However, prior efforts primarily involved structural magnetic resonance imaging and conventional diffusion MRI (dMRI) metrics without accounting for partial volume effects. To address this issue, we post-processed our dMRI scans with an advanced free-water (FW) correction technique to compute distinct FW-corrected fractional anisotropy (FAFWcorr) and FW maps that allow for the separation of tissue from fluid in a scan. We built 3 densely connected neural networks from FW-corrected dMRI, T1-weighted MRI, and combined FW+T1 features, respectively, to predict brain age. We then investigated the relationship of actual age and predicted brain ages with cognition. We found that all models accurately predicted actual age in cognitively unimpaired (CU) controls (FW: r=0.66, p=1.62x10-32; T1: r=0.61, p=1.45x10-26, FW+T1: r=0.77, p=6.48x10-50) and distinguished between CU and mild cognitive impairment participants (FW: p=0.006; T1: p=0.048; FW+T1: p=0.003), with FW+T1-derived age showing best performance. Additionally, all predicted brain age models were significantly associated with cross-sectional cognition (memory, FW: β=-1.094, p=6.32x10-7; T1: β=-1.331, p=6.52x10-7; FW+T1: β=-1.476, p=2.53x10-10; executive function, FW: β=-1.276, p=1.46x10-9; T1: β=-1.337, p=2.52x10-7; FW+T1: β=-1.850, p=3.85x10-17) and longitudinal cognition (memory, FW: β=-0.091, p=4.62x10-11; T1: β=-0.097, p=1.40x10-8; FW+T1: β=-0.101, p=1.35x10-11; executive function, FW: β=-0.125, p=1.20x10-10; T1: β=-0.163, p=4.25x10-12; FW+T1: β=-0.158, p=1.65x10-14). Our findings provide evidence that both T1-weighted MRI and dMRI measures improve brain age prediction and support predicted brain age as a sensitive biomarker of cognition and cognitive decline.

eXplainable Artificial Intelligence (XAI) in aging clock models

XAI is a rapidly progressing field of machine learning, aiming to unravel the predictions of complex models. XAI is especially required in sensitive applications, e.g. in health care, when diagnosis, recommendations and treatment choices might rely on the decisions made by artificial intelligence systems. AI approaches have become widely used in aging research as well, in particular, in developing biological clock models and identifying biomarkers of aging and age-related diseases. However, the potential of XAI here awaits to be fully appreciated. We discuss the application of XAI for developing the "aging clocks" and present a comprehensive analysis of the literature categorized by the focus on particular physiological systems.

Advanced structural brain aging in preclinical autosomal dominant Alzheimer disease

BACKGROUND

"Brain-predicted age" estimates biological age from complex, nonlinear features in neuroimaging scans. The brain age gap (BAG) between predicted and chronological age is elevated in sporadic Alzheimer disease (AD), but is underexplored in autosomal dominant AD (ADAD), in which AD progression is highly predictable with minimal confounding age-related co-pathology.

METHODS

We modeled BAG in 257 deeply-phenotyped ADAD mutation-carriers and 179 non-carriers from the Dominantly Inherited Alzheimer Network using minimally-processed structural MRI scans. We then tested whether BAG differed as a function of mutation and cognitive status, or estimated years until symptom onset, and whether it was associated with established markers of amyloid (PiB PET, CSF amyloid-β-42/40), phosphorylated tau (CSF and plasma pTau-181), neurodegeneration (CSF and plasma neurofilament-light-chain [NfL]), and cognition (global neuropsychological composite and CDR-sum of boxes). We compared BAG to other MRI measures, and examined heterogeneity in BAG as a function of ADAD mutation variants, APOE ε4 carrier status, sex, and education.

RESULTS

Advanced brain aging was observed in mutation-carriers approximately 7 years before expected symptom onset, in line with other established structural indicators of atrophy. BAG was moderately associated with amyloid PET and strongly associated with pTau-181, NfL, and cognition in mutation-carriers. Mutation variants, sex, and years of education contributed to variability in BAG.

CONCLUSIONS

We extend prior work using BAG from sporadic AD to ADAD, noting consistent results. BAG associates well with markers of pTau, neurodegeneration, and cognition, but to a lesser extent, amyloid, in ADAD. BAG may capture similar signal to established MRI measures. However, BAG offers unique benefits in simplicity of data processing and interpretation. Thus, results in this unique ADAD cohort with few age-related confounds suggest that brain aging attributable to AD neuropathology can be accurately quantified from minimally-processed MRI.

Brain-predicted age difference estimated using DeepBrainNet is significantly associated with pain and function-a multi-institutional and multiscanner study

ABSTRACT

Brain age predicted differences (brain-PAD: predicted brain age minus chronological age) have been reported to be significantly larger for individuals with chronic pain compared with those without. However, a debate remains after one article showed no significant differences. Using Gaussian Process Regression, an article provides evidence that these negative results might owe to the use of mixed samples by reporting a differential effect of chronic pain on brain-PAD across pain types. However, some remaining methodological issues regarding training sample size and sex-specific effects should be tackled before settling this controversy. Here, we explored differences in brain-PAD between musculoskeletal pain types and controls using a novel convolutional neural network for predicting brain-PADs, ie, DeepBrainNet. Based on a very large, multi-institutional, and heterogeneous training sample and requiring less magnetic resonance imaging preprocessing than other methods for brain age prediction, DeepBrainNet offers robust and reproducible brain-PADs, possibly highly sensitive to neuropathology. Controlling for scanner-related variability, we used a large sample (n = 660) with different scanners, ages (19-83 years), and musculoskeletal pain types (chronic low back [CBP] and osteoarthritis [OA] pain). Irrespective of sex, brain-PAD of OA pain participants was ∼3 to 4.7 years higher than that of CBP and controls, whereas brain-PAD did not significantly differ among controls and CBP. Moreover, brain-PAD was significantly related to multiple variables underlying the multidimensional pain experience. This comprehensive work adds evidence of pain type-specific effects of chronic pain on brain age. This could help in the clarification of the debate around possible relationships between brain aging mechanisms and pain.

A deep neural network estimation of brain age is sensitive to cognitive impairment and decline

The greatest known risk factor for Alzheimer's disease (AD) is age. While both normal aging and AD pathology involve structural changes in the brain, their trajectories of atrophy are not the same. Recent developments in artificial intelligence have encouraged studies to leverage neuroimaging-derived measures and deep learning approaches to predict brain age, which has shown promise as a sensitive biomarker in diagnosing and monitoring AD. However, prior efforts primarily involved structural magnetic resonance imaging and conventional diffusion MRI (dMRI) metrics without accounting for partial volume effects. To address this issue, we post-processed our dMRI scans with an advanced free-water (FW) correction technique to compute distinct FW-corrected fractional anisotropy (FAFWcorr) and FW maps that allow for the separation of tissue from fluid in a scan. We built 3 densely connected neural networks from FW-corrected dMRI, T1-weighted MRI, and combined FW+T1 features, respectively, to predict brain age. We then investigated the relationship of actual age and predicted brain ages with cognition. We found that all models accurately predicted actual age in cognitively unimpaired (CU) controls (FW: r=0.66, p=1.62×10-32; T1: r=0.61, p=1.45×10-26, FW+T1: r=0.77, p=6.48×10-50) and distinguished between CU and mild cognitive impairment participants (FW: p=0.006; T1: p=0.048; FW+T1: p=0.003), with FW+T1-derived age showing best performance. Additionally, all predicted brain age models were significantly associated with cross-sectional cognition (memory, FW: β=-1.094, p=6.32×10-7; T1: β=-1.331, p=6.52×10-7; FW+T1: β=-1.476, p=2.53×10-10; executive function, FW: β=-1.276, p=1.46×10-9; T1: β=-1.337, p=2.52×10-7; FW+T1: β=-1.850, p=3.85×10-17) and longitudinal cognition (memory, FW: β=-0.091, p=4.62×10-11; T1: β=-0.097, p=1.40×10-8; FW+T1: β=-0.101, p=1.35×10-11; executive function, FW: β=-0.125, p=1.20×10-10; T1: β=-0.163, p=4.25×10-12; FW+T1: β=-0.158, p=1.65×10-14). Our findings provide evidence that both T1-weighted MRI and dMRI measures improve brain age prediction and support predicted brain age as a sensitive biomarker of cognition and cognitive decline.