The concept of ‘brain age’, derived from neuroimaging data, serves as a crucial biomarker reflecting cognitive vitality and neurodegenerative trajectories. In the past decade, machine learning (ML) and deep learning (DL) integration has transformed the field, providing advanced models for brain age estimation. However, achieving precise brain age prediction across all ages remains a significant analytical challenge. This comprehensive review scrutinizes advancements in ML- and DL-based brain age prediction, analyzing 52 peer-reviewed studies from 2020 to 2024. It assesses various model architectures, highlighting their effectiveness and nuances in lifespan brain age studies. By comparing ML and DL, strengths in forecasting and methodological limitations are revealed. Finally, key findings from the reviewed articles are summarized and a number of major issues related to ML/DL-based lifespan brain age prediction are discussed. Through this study, we aim at the synthesis of the current state of brain age prediction, emphasizing both advancements and persistent challenges, guiding future research, technological advancements, and improving early intervention strategies for neurodegenerative diseases.

Background/Objectives: Alzheimer’s disease (AD) has a prolonged preclinical phase and marked heterogeneity. Brain age and the Brain Age Gap (BAG), derived from neuroimaging and machine learning (ML), offer a non-invasive, system-level indicator of brain integrity, with potential relevance for early detection, risk stratification, and intervention monitoring. This review summarizes the conceptual basis, imaging characteristics, biological relevance, and explores its potential clinical utility of BAG across the AD continuum. Methods: We conducted a narrative synthesis of evidence from morphometric structural magnetic resonance imaging (sMRI), connectivity-based functional magnetic resonance imaging (fMRI), positron emission tomography (PET), and diffusion tensor imaging (DTI), alongside recent advances in deep learning architectures and multimodal fusion techniques. We further examined associations between BAG and the Amyloid/Tau/Neurodegeneration (A/T/N) framework, neuroinflammation, cognitive reserve, and lifestyle interventions. Results: BAG may reflect neurodegeneration associated with AD, showing greater deviations in individuals with mild cognitive impairment (MCI) and early AD, and is correlated with tau pathology, neuroinflammation, and metabolic or functional network dysregulation. Multimodal and deep learning approaches enhance the sensitivity of BAG to disease-related deviations. Longitudinal BAG changes outperform static BAG in forecasting cognitive decline, and lifestyle or exercise interventions can attenuate BAG acceleration. Conclusions: BAG emerges as a promising, dynamic, integrative, and modifiable complementary biomarker with the potential for assessing neurobiological resilience, disease staging, and personalized intervention monitoring in AD. While further standardization and large-scale validation are essential to support clinical translation, BAG provides a novel systems-level perspective on brain health across the AD continuum.

The intricate dynamics of brain aging, especially the neurodegenerative mechanisms driving accelerated (ABA) and resilient brain aging (RBA), are pivotal in neuroscience. Understanding the temporal dynamics of these phenotypes is crucial for identifying vulnerabilities to cognitive decline and neurodegenerative diseases. Currently, there is a lack of comprehensive understanding of the temporal dynamics and neuroimaging biomarkers linked to ABA and RBA. This study addressed this gap by utilizing a large-scale UK Biobank (UKB) cohort, with the aim to elucidate brain aging heterogeneity and establish the foundation for targeted interventions. Employing Lasso regression on multimodal neuroimaging data, structural MRI (sMRI), diffusion MRI (dMRI), and resting-state functional MRI (rsfMRI), we predicted the brain age and classified individuals into ABA and RBA cohorts. Our findings identified 1949 subjects (6.2%) as representative of the ABA subpopulation and 3203 subjects (10.1%) as representative of the RBA subpopulation. Additionally, the Discriminative Event-Based Model (DEBM) was applied to estimate the sequence of biomarker changes across aging trajectories. Our analysis unveiled distinct central ordering patterns between the ABA and RBA cohorts, with profound implications for understanding cognitive decline and vulnerability to neurodegenerative disorders. Specifically, the ABA cohort exhibited early degeneration in four functional networks and two cognitive domains, with cortical thinning initially observed in the right hemisphere, followed by the temporal lobe. In contrast, the RBA cohort demonstrated initial degeneration in the three functional networks, with cortical thinning predominantly in the left hemisphere and white matter microstructural degeneration occurring at more advanced stages. The detailed aging progression timeline constructed through our DEBM analysis positioned subjects according to their estimated stage of aging, offering a nuanced view of the aging brain’s alterations. This study holds promise for the development of targeted interventions aimed at mitigating age-related cognitive decline.

Temporal lobe epilepsy (TLE) is considered a network disorder rather than a localized lesion, making it essential to study the network mechanisms underlying TLE. In this study, we constructed directed brain networks based on clinical MEG data using the Granger Causality Analysis (GCA) method, aiming to provide new insights into the network mechanisms of TLE. MEG data from 13 lTLE and 21 rTLE patients and 14 healthy controls (HCs) were analyzed. The preprocessed MEG data were used to construct directed brain networks using the GCA method and undirected brain networks using the Pearson Correlation Coefficient (PCC) method. Graph theoretical analysis extracted global and local topologies from the binary matrix, and SVM classified topologies with significant differences (p < 0.05). Comparative studies were performed on connectivity strengths, graph theory metrics, and SVM classifications between GCA and PCC, with an additional analysis of GCA-weighted network connectivity. The results show that TLE patients showed significantly increased functional connectivity based on GCA compared to the control group; similarities of the hub brain regions between lTLE and rTLE patients and the cortical–limbic–thalamic–cortical loop were identified; TLE patients exhibited a significant increase in GCA-based Global Clustering Coefficient (GCC) and Global Local Efficiency (GLE); most brain regions with abnormal local topological properties in TLE patients overlapped with their hub regions. The directionality of brain connectivity has played a significantly more pivotal role in research on TLE. GCA may be a potential tool in MEG analysis to distinguish TLE patients and HC effectively.

This study proposes a novel brain-region-level aging assessment paradigm based on Shapley value interpretation, aiming to overcome the interpretability limitations of traditional brain age prediction models. Although deep-learning-based brain age prediction models using neuroimaging data have become crucial tools for evaluating abnormal brain aging, their unidimensional brain age–chronological age discrepancy metric fails to characterize the regional heterogeneity of brain aging. Meanwhile, despite Shapley additive explanations having demonstrated potential for revealing regional heterogeneity, their application in complex deep learning algorithms has been hindered by prohibitive computational complexity. To address this, we innovatively developed a computational framework featuring efficient Shapley value approximation through a novel multi-stage computational strategy that significantly reduces complexity, thereby enabling an interpretable analysis of deep learning models. By establishing a reference system based on standard Shapley values from healthy populations, we constructed an anatomically specific Regional Brain Aging Deviation Index (RBADI) that maintains age-related validity. Experimental validation using UK Biobank data demonstrated that our framework successfully identified the thalamus (THA) and hippocampus (HIP) as core contributors to brain age prediction model decisions, highlighting their close associations with physiological aging. Notably, it revealed significant correlations between the insula (INS) and alcohol consumption, as well as between the inferior frontal gyrus opercular part (IFGoperc) and smoking history. Crucially, the RBADI exhibited superior performance in the tri-class classification of prodromal neurodegenerative diseases (HCs vs. MCI vs. AD: AUC = 0.92; HCs vs. pPD vs. PD: AUC = 0.86). This framework not only enables the practical implementation of Shapley additive explanations in brain age prediction deep learning models but also establishes anatomically interpretable biomarkers. These advancements provide a novel spatial analytical dimension for investigating brain aging mechanisms and demonstrate significant clinical translational value for early neurodegenerative disease screening, ultimately offering a new methodological tool for deciphering the neural mechanisms of aging.