Multi-cohort and longitudinal Bayesian clustering study of stage and subtype in Alzheimer's disease

Atrophy trajectories in Alzheimer's disease: how sex matters

INTRODUCTION

Longitudinal subtypes in Alzheimer's disease (AD) have been identified based on their distinct brain atrophy trajectories, encompassing mediotemporal and cortical pathways. These subtypes include minimal atrophy, limbic predominant, limbic predominant plus, diffuse atrophy and hippocampal sparing. The impact of sex on the progression of these subtypes remains a crucial area of investigation.

METHODS

We analysed MRI data from 320 amyloid-β positive individuals with AD from three international cohorts (ADNI, J-ADNI and AIBL). Longitudinal clustering was conducted to identify atrophy trajectories over eight years from the clinical disease onset, with separate trajectories delineated for women and men.

RESULTS

Women consistently exhibited earlier hippocampal atrophy and a higher burden of white matter abnormalities compared to men, yet women displayed less cognitive decline over time. Additionally, specific risk factors and distinct neuropsychiatric symptoms were associated with sex within specific trajectories.

CONCLUSIONS

AD subtypes show sex-specific differences in disease progression, highlighting the need to account for these differences from the early disease stages. Integrating imaging biomarkers with sex differences can enable the identification of more precise treatments for each patient, ensuring that both women and men have equal access to tailored care.

Identifying Alzheimer's Disease Progression Subphenotypes via a Graph-based Framework using Electronic Health Records

PURPOSE

Understanding the heterogeneity of neurodegeneration in Alzheimer's disease (AD) development, as well as identifying AD progression pathways, is vital for enhancing diagnosis, treatment, prognosis, and prevention strategies. To identify disease progression subphenotypes in patients with mild cognitive impairment (MCI) and AD using electronic health records (EHRs).

METHODS

We identified patients with mild cognitive impairment (MCI) and AD from the electronic health records from the OneFlorida+ Clinical Research Consortium. We proposed an outcome-oriented graph neural network-based model to identify progression pathways from MCI to AD.

RESULTS

Of the included 2,525 patients, 61.66% were female, and the mean age was 76. In this cohort, 64.83% were Non-Hispanic White (NHW), 16.48% were Non-Hispanic Black (NHB), and 2.53% were of other races. Additionally, there were 274 Hispanic patients, accounting for 10.85% of the total patient population. The average duration from the first MCI diagnosis to the transition to AD was 891 days. We identified four progression subphenotypes, each with distinct characteristics. The average progression times from MCI to AD varied among these subphenotypes, ranging from 805 to 1,236 days.

CONCLUSION

The findings suggest that AD does not follow uniform transitions of disease states but rather exhibits heterogeneous progression pathways. Our proposed framework holds the potential to identify AD progression subphenotypes, providing valuable and explainable insights for the development of the disease.

Antimicrobial resistance recommendations via electronic health records with graph representation and patient population modeling

BACKGROUND

Antimicrobial resistance (AMR), which refers to the ability of pathogenic bacteria to withstand the effects of antibiotics, is a critical global health issue. Traditional methods for identifying AMRs in clinical settings rely on in-lab testing, which hampers timely medical decision-making. Moreover, there is a notable delay in updating empirical treatment guidelines in response to the rapid evolution of pathogens. Recent advances in AMR research have illuminated the potential of machine learning-based patient information analysis using electronic health records (EHRs).

METHODS

Against this backdrop, our study introduces a novel deep learning framework designed to leverage EHR data for generating AMR recommendations. This framework is anchored in three critical innovations. Firstly, we employ a deep graph neural network to model the correlations between various medical events, using structural information to enhance the representation of binary medical events. Secondly, in acknowledgment of the commonalities in pathogen evolution among populations, we incorporate population-level observation by modeling patient graphical structures. This strategy also addresses the issue of imbalance in rare AMR labels. Finally, we adopt a multi-task learning strategy, enabling simultaneous recommendations on multiple AMRs. Extensive experimental evaluations on a large dataset of over 110,000 patients with urinary tract infections validate the superiority of our approach.

RESULTS

It achieves notable improvements in areas under receiver operating characteristic curves (AUROCs) for four distinct AMR labels, with increments of 0.04, 0.02, 0.06, and 0.10 surpassing the baselines.

CONCLUSIONS

Further medical analysis underscores the efficacy of our approach, demonstrating the potential of EHR-based systems in AMR recommendation.

Multivariate longitudinal clustering reveals neuropsychological factors as dementia predictors in an Alzheimer's disease progression study

Dementia due to Alzheimer's disease (AD) is a multifaceted neurodegenerative disorder characterized by various cognitive and behavioral decline factors. In this work, we propose an extension of the traditional k-means clustering for multivariate time series data to cluster joint trajectories of different features describing progression over time. The algorithm we propose here enables the joint analysis of various longitudinal features to explore co-occurring trajectory factors among markers indicative of cognitive decline in individuals participating in an AD progression study. By examining how multiple variables co-vary and evolve together, we identify distinct subgroups within the cohort based on their longitudinal trajectories. Our clustering method enhances the understanding of individual development across multiple dimensions and provides deeper medical insights into the trajectories of cognitive decline. In addition, the proposed algorithm is also able to make a selection of the most significant features in separating clusters by considering trajectories over time. This process, together with a preliminary pre-processing on the OASIS-3 dataset, reveals an important role of some neuropsychological factors. In particular, the proposed method has identified a significant profile compatible with a syndrome known as Mild Behavioral Impairment (MBI), displaying behavioral manifestations of individuals that may precede the cognitive symptoms typically observed in AD patients. The findings underscore the importance of considering multiple longitudinal features in clinical modeling, ultimately supporting more effective and individualized patient management strategies.

Mixture Disease Progression Model to Predict and Cluster the Long-Term Trajectory of Cognitive Decline in Alzheimer's Disease

BACKGROUND

Alzheimer's disease (AD) is a neurodegenerative disease for which many clinical trials failed to detect treatment effects, possibly due to the heterogeneity of disease progression among the patients. Predicting and clustering a long-term trajectory of cognitive decline from the short-term cognition data of individual patients would help develop therapeutic interventions for AD.

METHODS

This study developed mixture disease progression model to predict and cluster the long-term trajectory of cognitive decline in the population. We predicted the 30-year long-term trajectories of the three cognitive scales and categorized the individuals into rapid and slow cognitive decliners by applying the method, which was based on the two-component normal mixture nonlinear mixed-effects model, to the short-term follow-up data of the Mini-Mental State Examination, the 13-item Alzheimer's Disease Assessment Scale-Cognitive, and the Clinical Dementia Rating Scale-sum of boxes collected in patients with mild cognitive impairment and AD in the Alzheimer's Disease Neuroimaging Initiative.

RESULTS

For each cognitive scale, the models identified two distinct subpopulations, including a population of comprising approximately 10-20% of individuals experiencing rapid cognitive decline, wherein the posterior means of the differences in cognitive decline speed between the two groups ranged from 2 to 3 years. We also identified baseline background factors associated with rapid decliners for three cognitive scales.

CONCLUSION

Identifying the risk factors associated with rapid decline of cognition by the proposed method aids in planning eligibility criteria and allocation strategy for accounting for the varying disease progression speeds among the patients enrolled in clinical trials for AD.

Identifying time patterns in Huntington's disease trajectories using dynamic time warping-based clustering on multi-modal data

One of the principal goals of Precision Medicine is to stratify patients by accounting for individual variability. However, extracting meaningful information from Real-World Data, such as Electronic Health Records, still remains challenging due to methodological and computational issues. A Dynamic Time Warping-based unsupervised-clustering methodology is presented in this paper for the clustering of patient trajectories of multi-modal health data on the basis of shared temporal characteristics. Building on an earlier methodology, a new dimension of time-varying clinical and imaging features is incorporated, through an adapted cost-minimization algorithm for clustering on different, possibly overlapping, feature subsets. The model disease chosen is Huntington's disease (HD), characterized by progressive neurodegeneration. From a wide range of examined user-defined parameters, four case examples are highlighted to demonstrate the identified temporal patterns in multi-modal HD trajectories and to study how these differ due to the combined effects of feature weights and granularity threshold. For each identified cluster, polynomial fits that describe the time behavior of the assessed features are provided for an informative comparison, together with their averaged values. The proposed data-mining methodology permits the stratification of distinct time patterns of multi-modal health data in individuals that share a diagnosis, by employing user-customized criteria beyond the current clinical practice. Overall, this work bears implications for better analysis of individual variability in disease progression, opening doors to personalized preventative, diagnostic and therapeutic strategies.

Spectral normative modeling of brain structure

Normative modeling in neuroscience aims to characterize interindividual variation in brain phenotypes and thus establish reference ranges, or brain charts, against which individual brains can be compared. Normative models are typically limited to coarse spatial scales due to computational constraints, limiting their spatial specificity. They additionally depend on fixed regions from fixed parcellation atlases, restricting their adaptability to alternative parcellation schemes. To overcome these key limitations, we propose spectral normative modeling (SNM), which leverages brain eigenmodes for efficient spatial reconstruction to generate normative ranges for arbitrary new regions of interest. Benchmarking against conventional counterparts, SNM achieves a 98.3% speedup in computing accurate normative ranges across spatial scales, from millimeters to the whole brain. We demonstrate its utility by elucidating high-resolution individual cortical atrophy patterns and characterizing the heterogeneous nature of neurodegeneration in Alzheimer's disease. SNM lays the groundwork for a new generation of spatially precise brain charts, offering substantial potential to drive advances in individualized precision medicine.

The Transition From Homogeneous to Heterogeneous Machine Learning in Neuropsychiatric Research

Despite the advantage of neuroimaging-based machine learning (ML) models as pivotal tools for investigating brain-behavior relationships in neuropsychiatric studies, these data-driven predictive approaches have yet to yield substantial, clinically actionable insights for mental health care. A notable impediment lies in the inadequate accommodation of most ML research to the natural heterogeneity within large samples. Although commonly thought of as individual-level analyses, many ML algorithms are unimodal and homogeneous and thus incapable of capturing the potentially heterogeneous relationships between biology and psychopathology. We review the current landscape of computational research targeting population heterogeneity and argue that there is a need to expand from brain subtyping and behavioral phenotyping to analyses that focus on heterogeneity at the relational level. To this end, we review and suggest several existing ML models with the capacity to discern how external environmental and sociodemographic factors moderate the brain-behavior mapping function in a data-driven fashion. These heterogeneous ML models hold promise for enhancing the discovery of individualized brain-behavior associations and advancing precision psychiatry.

A Multiform Heterogeneity Framework for Alzheimer's Disease Based on Multimodal Neuroimaging

Understanding the heterogeneity of Alzheimer's disease (AD) is crucial for advancing precision medicine specifically tailored to this disorder. Recent research has deepened our understanding of AD heterogeneity; however, translating these insights from bench to bedside via neuroimaging heterogeneity frameworks presents significant challenges. In this review, we systematically revisit prior studies and summarize the existing methodology of data-driven neuroimaging studies for AD heterogeneity. We organized the current methodology into 1) a subtyping clustering strategy for patients with AD, and we also subdivided it into subtyping analysis based on cross-sectional multimodal neuroimaging profiles and the identification of long-term disease progression from short-term datasets; 2) a stratified strategy that integrates neuroimaging measures with biomarkers; and 3) individual-specific abnormal patterns based on the normative model. Then, we evaluated the characteristics of these studies along 2 dimensions: 1) the understanding of pathology and 2) clinical application. We systematically address the limitations, challenges, and future directions of research into AD heterogeneity. Our goal is to enhance the neuroimaging heterogeneity framework for AD, thereby facilitating its transition from bench to bedside.

Brain derived β-interferon is a potential player in Alzheimer's disease pathogenesis and cognitive impairment

BACKGROUND

Recent research has postulated that the activation of cGAS-STING-interferon signalling pathways could be implicated in the pathogenesis of Alzheimer's disease (AD). However, the precise types of interferons and related cytokines, both from the brain and periphery, responsible for cognitive impairment in patients with AD remain unclear.

METHODS

A total of 131 participants (78 [59.5%] female and 53 [40.5%] male; mean [SD] age, 61.5 [7.6] years) with normal cognition and cognitive impairment from the China Aging and Neurodegenerative Initiative cohort were included. CSF and serum IFNα-2a, IFN-β, IFN-γ, TNF-α, IL-6, IL-10, MCP-1and CXCL-10 were tested. The correlation between these interferons and related cytokines with AD core biomarkers in the CSF and plasma, cognition performance, and brain MRI measures were analysed.

RESULTS

We found that only CSF IFN-β levels were significantly elevated in Alzheimer's disease compared to normal cognition. Furthermore, CSF IFN-β levels were significantly associated with AD core biomarkers (CSF P-tau and Aβ42/Aβ40 ratio) and cognitive performance (MMSE and CDR score). Additionally, the CSF IFN-β levels were significantly correlated with the typical pattern of brain atrophy in AD (such as hippocampus, amygdala, and precuneus). In contrast, CSF IL-6 levels were significantly elevated in non-AD cognitively impaired patients compared to other groups. Moreover, CSF IL-6 levels were significantly associated with cognitive performance in non-AD individuals and correlated with the vascular cognitive impairment-related MRI markers (such as white matter hyperintensity).

CONCLUSION

Our findings demonstrate that distinct inflammatory molecules are associated with different cognitive disorders. Notably, CSF IFN-β levels are significantly linked to the pathology and cognitive performance of AD, identifying this interferon as a potential target for AD therapy.

Heterogeneity of cerebral atrophic rate in mild cognitive impairment and its interactive association with proteins related to microglia activity on longitudinal cognitive changes

BACKGROUND

Heterogeneity of cerebral atrophic rate commonly exists in mild cognitive impairment (MCI), which may be associated with microglia-involved neuropathology and have an influence on cognitive outcomes.

OBJECTIVE

We aim to explore the heterogeneity of cerebral atrophic rate among MCI and its association with plasma proteins related to microglia activity, with further investigation of their interaction effects on long-term cognition.

SUBJECTS

A total of 630 MCI subjects in the ADNI database were included, of which 260 subjects were available with baseline data on plasma proteins.

METHODS

Group-based multi-trajectory modeling (GBMT) was used to identify the latent classes with heterogeneous cerebral atrophic rates. Associations between latent classes and plasma proteins related to microglia activity were investigated with generalized linear models. Linear mixed effect models (LME) were implemented to explore the interaction effects between proteins related to microglia activity and identified latent classes on longitudinal cognitive changes.

RESULTS

Two latent classes were identified and labeled as the slow-atrophy class and the fast-atrophy class. Associations were found between such heterogeneity of atrophic rates and plasma proteins related to microglia activity, especially AXL receptor tyrosine kinase (AXL), CD40 antigen (CD40), and tumor necrosis factor receptor-like 2 (TNF-R2). Interaction effects on longitudinal cognitive changes showed that higher CD40 was associated with faster cognitive decline in the slow-atrophy class and higher AXL or TNF-R2 was associated with slower cognitive decline in the fast-atrophy class.

CONCLUSIONS

Heterogeneity of atrophic rates at the MCI stage is associated with several plasma proteins related to microglia activity, which show either protective or adverse effects on long-term cognition depending on the variability of atrophic rates.

Divergent neurodegenerative patterns: Comparison of [18F] fluorodeoxyglucose-PET- and MRI-based Alzheimer's disease subtypes

[18F] fluorodeoxyglucose (FDG)-PET and MRI are key imaging markers for neurodegeneration in Alzheimer's disease. It has been well established that parieto-temporal hypometabolism on FDG-PET is closely associated with medial temporal atrophy on MRI in Alzheimer's disease. Substantial biological heterogeneity, expressed as distinct subtypes of hypometabolism or atrophy patterns, has been previously described in Alzheimer's disease using data-driven and hypothesis-driven methods. However, the link between these two imaging modalities has not yet been explored in the context of Alzheimer's disease subtypes. To investigate this link, the current study utilized FDG-PET and MRI scans from 180 amyloid-beta positive Alzheimer's disease dementia patients, 339 amyloid-beta positive mild cognitive impairment and 176 amyloid-beta negative cognitively normal controls from the Alzheimer's Disease Neuroimaging Initiative. Random forest hierarchical clustering, a data-driven model for identifying subtypes, was implemented in the two modalities: one with standard uptake value ratios and the other with grey matter volumes. Five hypometabolism- and atrophy-based subtypes were identified, exhibiting both cortical-predominant and limbic-predominant patterns although with differing percentages and clinical presentations. Three cortical-predominant hypometabolism subtypes found were Cortical Predominant (32%), Cortical Predominant+ (11%) and Cortical Predominant posterior (8%), and two limbic-predominant hypometabolism subtypes found were Limbic Predominant (36%) and Limbic Predominant frontal (13%). In addition, little atrophy (minimal) and widespread (diffuse) neurodegeneration subtypes were observed from the MRI data. The five atrophy subtypes found were Cortical Predominant (19%), Limbic Predominant (27%), Diffuse (29%), Diffuse+ (6%) and Minimal (19%). Inter-modality comparisons showed that all FDG-PET subtypes displayed medial temporal atrophy, whereas the distinct MRI subtypes showed topographically similar hypometabolic patterns. Further, allocations of FDG-PET and MRI subtypes were not consistent when compared at an individual level. Additional analysis comparing the data-driven clustering model with prior hypothesis-driven methods showed only partial agreement between these subtyping methods. FDG-PET subtypes had greater differences between limbic-predominant and cortical-predominant patterns, and MRI subtypes had greater differences in severity of atrophy. In conclusion, this study highlighted that Alzheimer's disease subtypes identified using both FDG-PET and MRI capture distinct pathways showing cortical versus limbic predominance of neurodegeneration. However, the subtypes do not share a bidirectional relationship between modalities and are thus not interchangeable.

Frontoparietal atrophy trajectories in cognitively unimpaired elderly individuals using longitudinal Bayesian clustering

INTRODUCTION

Frontal and/or parietal atrophy has been reported during aging. To disentangle the heterogeneity previously observed, this study aimed to uncover different clusters of grey matter profiles and trajectories within cognitively unimpaired individuals.

METHODS

Structural magnetic resonance imaging (MRI) data of 307 Aβ-negative cognitively unimpaired individuals were modelled between ages 60-85 from three cohorts worldwide. We applied unsupervised clustering using a novel longitudinal Bayesian approach and characterized the clusters' cerebrovascular and cognitive profiles.

RESULTS

Four clusters were identified with different grey matter profiles and atrophy trajectories. Differences were mainly observed in frontal and parietal brain regions. These distinct frontoparietal grey matter profiles and longitudinal trajectories were differently associated with cerebrovascular burden and cognitive decline.

DISCUSSION

Our findings suggest a conciliation of the frontal and parietal theories of aging, uncovering coexisting frontoparietal GM patterns. This could have important future implications for better stratification and identification of at-risk individuals.

Population clustering of structural brain aging and its association with brain development

Structural brain aging has demonstrated strong inter-individual heterogeneity and mirroring patterns with brain development. However, due to the lack of large-scale longitudinal neuroimaging studies, most of the existing research focused on the cross-sectional changes of brain aging. In this investigation, we present a data-driven approach that incorporate both cross-sectional changes and longitudinal trajectories of structural brain aging and identified two brain aging patterns among 37,013 healthy participants from UK Biobank. Participants with accelerated brain aging also demonstrated accelerated biological aging, cognitive decline and increased genetic susceptibilities to major neuropsychiatric disorders. Further, by integrating longitudinal neuroimaging studies from a multi-center adolescent cohort, we validated the 'last in, first out' mirroring hypothesis and identified brain regions with manifested mirroring patterns between brain aging and brain development. Genomic analyses revealed risk loci and genes contributing to accelerated brain aging and delayed brain development, providing molecular basis for elucidating the biological mechanisms underlying brain aging and related disorders.

Beyond the usual suspects: multi-factorial computational models in the search for neurodegenerative disease mechanisms

From Alzheimer's disease to amyotrophic lateral sclerosis, the molecular cascades underlying neurodegenerative disorders remain poorly understood. The clinical view of neurodegeneration is confounded by symptomatic heterogeneity and mixed pathology in almost every patient. While the underlying physiological alterations originate, proliferate, and propagate potentially decades before symptomatic onset, the complexity and inaccessibility of the living brain limit direct observation over a patient's lifespan. Consequently, there is a critical need for robust computational methods to support the search for causal mechanisms of neurodegeneration by distinguishing pathogenic processes from consequential alterations, and inter-individual variability from intra-individual progression. Recently, promising advances have been made by data-driven spatiotemporal modeling of the brain, based on in vivo neuroimaging and biospecimen markers. These methods include disease progression models comparing the temporal evolution of various biomarkers, causal models linking interacting biological processes, network propagation models reproducing the spatial spreading of pathology, and biophysical models spanning cellular- to network-scale phenomena. In this review, we discuss various computational approaches for integrating cross-sectional, longitudinal, and multi-modal data, primarily from large observational neuroimaging studies, to understand (i) the temporal ordering of physiological alterations, i(i) their spatial relationships to the brain's molecular and cellular architecture, (iii) mechanistic interactions between biological processes, and (iv) the macroscopic effects of microscopic factors. We consider the extents to which computational models can evaluate mechanistic hypotheses, explore applications such as improving treatment selection, and discuss how model-informed insights can lay the groundwork for a pathobiological redefinition of neurodegenerative disorders.

MRI subtypes in Parkinson's disease across diverse populations and clustering approaches

Parkinson's disease (PD) is clinically heterogeneous, which suggests the existence of subtypes; however, there has been no consensus regarding their characteristics. This study included 633 PD individuals across distinct cohorts: unmedicated de novo PD, medicated PD, mild-moderate PD, and a cohort based on diagnostic work-up in clinical practice. Additionally, 233 controls were included. Clustering based on cortical and subcortical gray matter measures was conducted with and without adjusting for global atrophy in the entire PD sample and validated within each cohort. Subtypes were characterized using baseline and longitudinal demographic and clinical data. Unadjusted results identified three clusters showing a gradient of neurodegeneration and symptom severity across the entire sample and the individual cohorts. When adjusting for global atrophy eight clusters were identified in the entire sample, lacking consistency in individual cohorts. This study identified atrophy-based subtypes in PD, emphasizing the significant impact of global atrophy on subtype number, patterns, and interpretation in cross-sectional analyses.

Disentangling brain atrophy heterogeneity in Alzheimer's disease: A deep self-supervised approach with interpretable latent space

Alzheimer's disease (AD) is heterogeneous, but existing methods for capturing this heterogeneity through dimensionality reduction and unsupervised clustering have limitations when it comes to extracting intricate atrophy patterns. In this study, we propose a deep learning based self-supervised framework that characterizes complex atrophy features using latent space representation. It integrates feature engineering, classification, and clustering to synergistically disentangle heterogeneity in Alzheimer's disease. Through this representation learning, we trained a clustered latent space with distinct atrophy patterns and clinical characteristics in AD, and replicated the findings in prodromal Alzheimer's disease. Moreover, we discovered that these clusters are not solely attributed to subtypes but also reflect disease progression in the latent space, representing the core dimensions of heterogeneity, namely progression and subtypes. Furthermore, longitudinal latent space analysis revealed two distinct disease progression pathways: medial temporal and parietotemporal pathways. The proposed approach enables effective latent representations that can be integrated with individual-level cognitive profiles, thereby facilitating a comprehensive understanding of AD heterogeneity.

Machine learning on longitudinal multi-modal data enables the understanding and prognosis of Alzheimer's disease progression

Alzheimer's disease (AD) is a complex pathophysiological disease. Allowing for heterogeneity, not only in disease manifestations but also in different progression patterns, is critical for developing effective disease models that can be used in clinical and research settings. We introduce a machine learning model for identifying underlying patterns in Alzheimer's disease (AD) trajectory using longitudinal multi-modal data from the ADNI cohort and the AIBL cohort. Ten biologically and clinically meaningful disease-related states were identified from data, which constitute three non-overlapping stages (i.e., neocortical atrophy [NCA], medial temporal atrophy [MTA], and whole brain atrophy [WBA]) and two distinct disease progression patterns (i.e., NCA → WBA and MTA → WBA). The index of disease-related states provided a remarkable performance in predicting the time to conversion to AD dementia (C-Index: 0.923 ± 0.007). Our model shows potential for promoting the understanding of heterogeneous disease progression and early predicting the conversion time to AD dementia.

A generalizable data-driven model of atrophy heterogeneity and progression in memory clinic settings

Memory clinic patients are a heterogeneous population representing various aetiologies of pathological ageing. It is not known whether divergent spatiotemporal progression patterns of brain atrophy, as previously described in Alzheimer's disease patients, are prevalent and clinically meaningful in this group of older adults. To uncover distinct atrophy subtypes, we applied the Subtype and Stage Inference (SuStaIn) algorithm to baseline structural MRI data from 813 participants enrolled in the DELCODE cohort (mean ± standard deviation, age = 70.67 ± 6.07 years, 52% females). Participants were cognitively unimpaired (n = 285) or fulfilled diagnostic criteria for subjective cognitive decline (n = 342), mild cognitive impairment (n = 118) or dementia of the Alzheimer's type (n = 68). Atrophy subtypes were compared in baseline demographics, fluid Alzheimer's disease biomarker levels, the Preclinical Alzheimer Cognitive Composite (PACC-5) as well as episodic memory and executive functioning. PACC-5 trajectories over up to 240 weeks were examined. To test whether baseline atrophy subtype and stage predicted clinical trajectories before manifest cognitive impairment, we analysed PACC-5 trajectories and mild cognitive impairment conversion rates of cognitively unimpaired participants and those with subjective cognitive decline. Limbic-predominant and hippocampal-sparing atrophy subtypes were identified. Limbic-predominant atrophy initially affected the medial temporal lobes, followed by further temporal regions and, finally, the remaining cortical regions. At baseline, this subtype was related to older age, more pathological Alzheimer's disease biomarker levels, APOE ε4 carriership and an amnestic cognitive impairment. Hippocampal-sparing atrophy initially occurred outside the temporal lobe, with the medial temporal lobe spared up to advanced atrophy stages. This atrophy pattern also affected individuals with positive Alzheimer's disease biomarkers and was associated with more generalized cognitive impairment. Limbic-predominant atrophy, in all participants and in only unimpaired participants, was linked to more negative longitudinal PACC-5 slopes than observed in participants without or with hippocampal-sparing atrophy and increased the risk of mild cognitive impairment conversion. SuStaIn modelling was repeated in a sample from the Swedish BioFINDER-2 cohort. Highly similar atrophy progression patterns and associated cognitive profiles were identified. Cross-cohort model generalizability, at both the subject and the group level, was excellent, indicating reliable performance in previously unseen data. The proposed model is a promising tool for capturing heterogeneity among older adults at early at-risk states for Alzheimer's disease in applied settings. The implementation of atrophy subtype- and stage-specific end points might increase the statistical power of pharmacological trials targeting early Alzheimer's disease.

Co-Assembled Nanoparticles toward Multi-Target Combinational Therapy of Alzheimer's Disease by Making Full Use of Molecular Recognition and Self-Assembly

The complex pathologies in Alzheimer's disease (AD) severely limit the effectiveness of single-target pharmic interventions, thus necessitating multi-pronged therapeutic strategies. While flexibility is essentially demanded in constructing such multi-target systems, for achieving optimal synergies and also accommodating the inherent heterogeneity within AD. Utilizing the dynamic reversibility of supramolecular strategy for conferring sufficient tunability in component substitution and proportion adjustment, amphiphilic calixarenes are poised to be a privileged molecular tool for facilely achieving function integration. Herein, taking β-amyloid (Aβ) fibrillation and oxidative stress as model combination pattern, a supramolecular multifunctional integration is proposed by co-assembling guanidinium-modified calixarene with ascorbyl palmitate and loading dipotassium phytate within calixarene cavity. Serial pivotal events can be simultaneously addressed by this versatile system, including 1) inhibition of Aβ production and aggregation, 2) disintegration of Aβ fibrils, 3) acceleration of Aβ metabolic clearance, and 4) regulation of oxidative stress, which is verified to significantly ameliorate the cognitive impairment of 5×FAD mice, with reduced Aβ plaque content, neuroinflammation, and neuronal apoptosis. Confronted with the extremely intricate clinical realities of AD, the strategy presented here exhibits ample adaptability for necessary alterations on combinations, thereby may immensely expedite the advancement of AD combinational therapy through providing an exceptionally convenient platform.

Hypothesis tests in ordinal predictive models with optimal accuracy

In real-world applications involving multi-class ordinal discrimination, a common approach is to aggregate multiple predictive variables into a linear combination, aiming to develop a classifier with high prediction accuracy. Assessment of such multi-class classifiers often utilizes the hypervolume under ROC manifolds (HUM). When dealing with a substantial pool of potential predictors and achieving optimal HUM, it becomes imperative to conduct appropriate statistical inference. However, prevalent methodologies in existing literature are computationally expensive. We propose to use the jackknife empirical likelihood method to address this issue. The Wilks' theorem under moderate conditions is established and the power analysis under the Pitman alternative is provided. We also introduce a novel network-based rapid computation algorithm specifically designed for computing a general multi-sample $U$-statistic in our test procedure. To compare our approach against existing approaches, we conduct extensive simulations. Results demonstrate the superior performance of our method in terms of test size, power, and implementation time. Furthermore, we apply our method to analyze a real medical dataset and obtain some new findings.

Population clustering of structural brain aging and its association with brain development

Structural brain aging has demonstrated strong inter-individual heterogeneity and mirroring patterns with brain development. However, due to the lack of large-scale longitudinal neuroimaging studies, most of the existing research focused on the cross-sectional changes of brain aging. In this investigation, we present a data-driven approach that incorporate both cross-sectional changes and longitudinal trajectories of structural brain aging and identified two brain aging patterns among 37,013 healthy participants from UK Biobank. Participants with accelerated brain aging also demonstrated accelerated biological aging, cognitive decline and increased genetic susceptibilities to major neuropsychiatric disorders. Further, by integrating longitudinal neuroimaging studies from a multi-center adolescent cohort, we validated the "last in, first out" mirroring hypothesis and identified brain regions with manifested mirroring patterns between brain aging and brain development. Genomic analyses revealed risk loci and genes contributing to accelerated brain aging and delayed brain development, providing molecular basis for elucidating the biological mechanisms underlying brain aging and related disorders.

Identifying Progression-Specific Alzheimer's Subtypes Using Multimodal Transformer

Alzheimer's disease (AD) is the most prevalent neurodegenerative disease, yet its current treatments are limited to stopping disease progression. Moreover, the effectiveness of these treatments remains uncertain due to the heterogeneity of the disease. Therefore, it is essential to identify disease subtypes at a very early stage. Current data-driven approaches can be used to classify subtypes during later stages of AD or related disorders, but making predictions in the asymptomatic or prodromal stage is challenging. Furthermore, the classifications of most existing models lack explainability, and these models rely solely on a single modality for assessment, limiting the scope of their analysis. Thus, we propose a multimodal framework that utilizes early-stage indicators, including imaging, genetics, and clinical assessments, to classify AD patients into progression-specific subtypes at an early stage. In our framework, we introduce a tri-modal co-attention mechanism (Tri-COAT) to explicitly capture cross-modal feature associations. Data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (slow progressing = 177, intermediate = 302, and fast = 15) were used to train and evaluate Tri-COAT using a 10-fold stratified cross-testing approach. Our proposed model outperforms baseline models and sheds light on essential associations across multimodal features supported by known biological mechanisms. The multimodal design behind Tri-COAT allows it to achieve the highest classification area under the receiver operating characteristic curve while simultaneously providing interpretability to the model predictions through the co-attention mechanism.

Multi-pathological contributions toward atrophy patterns in the Alzheimer's disease continuum

Introduction

Heterogeneity in downstream atrophy in Alzheimer's disease (AD) is predominantly investigated in relation to pathological hallmarks (Aβ, tau) and co-pathologies (cerebrovascular burden) independently. However, the proportional contribution of each pathology in determining atrophy pattern remains unclear. We assessed heterogeneity in atrophy using two recently conceptualized dimensions: typicality (typical AD atrophy at the center and deviant atypical atrophy on either extreme including limbic predominant to hippocampal sparing patterns) and severity (overall neurodegeneration spanning minimal atrophy to diffuse typical AD atrophy) in relation to Aβ, tau, and cerebrovascular burden.

Methods

We included 149 Aβ + individuals on the AD continuum (cognitively normal, prodromal AD, AD dementia) and 163 Aβ- cognitively normal individuals from the ADNI. We modeled heterogeneity in MRI-based atrophy with continuous-scales of typicality (ratio of hippocampus to cortical volume) and severity (total gray matter volume). Partial correlation models investigated the association of typicality/severity with (a) Aβ (global Aβ PET centiloid), tau (global tau PET SUVR), cerebrovascular (total white matter hypointensity volume) burden (b) four cognitive domains (memory, executive function, language, visuospatial composites). Using multiple regression, we assessed the association of each pathological burden and typicality/severity with cognition.

Results

(a) In the AD continuum, typicality (r = -0.31, p < 0.001) and severity (r = -0.37, p < 0.001) were associated with tau burden after controlling for Aβ, cerebrovascular burden and age. Findings imply greater tau pathology in limbic predominant atrophy and diffuse atrophy. (b) Typicality was associated with memory (r = 0.49, p < 0.001) and language scores (r = 0.19, p = 0.02). Severity was associated with memory (r = 0.26, p < 0.001), executive function (r = 0.24, p = 0.003) and language scores (r = 0.29, p < 0.001). Findings imply better cognitive performance in hippocampal sparing and minimal atrophy patterns. Beyond typicality/severity, tau burden but not Aβ and cerebrovascular burden explained cognition.

Conclusion

In the AD continuum, atrophy-based severity was more strongly associated with tau burden than typicality after accounting for Aβ and cerebrovascular burden. Cognitive performance in memory, executive function and language domains was explained by typicality and/or severity and additionally tau pathology. Typicality and severity may differentially reflect burden arising from tau pathology but not Aβ or cerebrovascular pathologies which need to be accounted for when investigating AD heterogeneity.

Longitudinal trajectories of cognitive reserve in hypometabolic subtypes of Alzheimer's disease

Previous studies have demonstrated resilience to AD-related neuropathology in a form of cognitive reserve (CR). In this study we investigated a relationship between CR and hypometabolic subtypes of AD, specifically the typical and the limbic-predominant subtypes. We analyzed data from 59 Aβ-positive cognitively normal (CN), 221 prodromal Alzheimer's disease (AD) and 174 AD dementia participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) from ADNI and ADNIGO/2 phases. For replication, we analyzed data from 5 Aβ-positive CN, 89 prodromal AD and 43 AD dementia participants from ADNI3. CR was estimated as standardized residuals in a model predicting cognition from temporoparietal grey matter volumes and covariates. Higher CR estimates predicted slower cognitive decline. Typical and limbic-predominant hypometabolic subtypes demonstrated similar baseline CR, but the results suggested a faster decline of CR in the typical subtype. These findings support the relationship between subtypes and CR, specifically longitudinal trajectories of CR. Results also underline the importance of longitudinal analyses in research on CR.

Cognitively defined Alzheimer's dementia subgroups have distinct atrophy patterns

INTRODUCTION

We sought to determine structural magnetic resonance imaging (MRI) characteristics across subgroups defined based on relative cognitive domain impairments using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and to compare cognitively defined to imaging-defined subgroups.

METHODS

We used data from 584 people with Alzheimer's disease (AD) (461 amyloid positive, 123 unknown amyloid status) and 118 amyloid-negative controls. We used voxel-based morphometry to compare gray matter volume (GMV) for each group compared to controls and to AD-Memory.

RESULTS

There was pronounced bilateral lower medial temporal lobe atrophy with relative cortical sparing for AD-Memory, lower left hemisphere GMV for AD-Language, anterior lower GMV for AD-Executive, and posterior lower GMV for AD-Visuospatial. Formal asymmetry comparisons showed substantially more asymmetry in the AD-Language group than any other group (p = 1.15 × 10-10 ). For overlap between imaging-defined and cognitively defined subgroups, AD-Memory matched up with an imaging-defined limbic predominant group.

DISCUSSION

MRI findings differ across cognitively defined AD subgroups.

A review of neuroimaging-based data-driven approach for Alzheimer's disease heterogeneity analysis

Alzheimer's disease (AD) is a complex form of dementia and due to its high phenotypic variability, its diagnosis and monitoring can be quite challenging. Biomarkers play a crucial role in AD diagnosis and monitoring, but interpreting these biomarkers can be problematic due to their spatial and temporal heterogeneity. Therefore, researchers are increasingly turning to imaging-based biomarkers that employ data-driven computational approaches to examine the heterogeneity of AD. In this comprehensive review article, we aim to provide health professionals with a comprehensive view of past applications of data-driven computational approaches in studying AD heterogeneity and planning future research directions. We first define and offer basic insights into different categories of heterogeneity analysis, including spatial heterogeneity, temporal heterogeneity, and spatial-temporal heterogeneity. Then, we scrutinize 22 articles relating to spatial heterogeneity, 14 articles relating to temporal heterogeneity, and five articles relating to spatial-temporal heterogeneity, highlighting the strengths and limitations of these strategies. Furthermore, we discuss the importance of understanding spatial heterogeneity in AD subtypes and their clinical manifestations, biomarkers for abnormal orderings and AD stages, the recent advancements in spatial-temporal heterogeneity analysis for AD, and the emerging role of omics data integration in advancing personalized diagnosis and treatment for AD patients. By emphasizing the significance of understanding AD heterogeneity, we hope to stimulate further research in this field to facilitate the development of personalized interventions for AD patients.

Resolving heterogeneity in Alzheimer's disease based on individualized structural covariance network

The heterogeneity of Alzheimer's disease (AD) poses a challenge to precision medicine. We aimed to identify distinct subtypes of AD based on the individualized structural covariance network (IDSCN) analysis and to research the underlying neurobiology mechanisms. In this study, 187 patients with AD (age = 73.57 ± 6.00, 50% female) and 143 matched normal controls (age = 74.30 ± 7.80, 44% female) were recruited from the Alzheimer's Disease Neuroimaging Initiative (ADNI) project database, and T1 images were acquired. We utilized the IDSCN analysis to generate individual-level altered structural covariance network and performed k-means clustering to subtype AD based on structural covariance network. Cognition, disease progression, morphological features, and gene expression profiles were further compared between subtypes, to characterize the heterogeneity in AD. Two distinct AD subtypes were identified in a reproducible manner, and we named the two subtypes as slow progression type (subtype 1, n = 104, age = 76.15 ± 6.44, 42% female) and rapid progression type (subtype 2, n = 83, age = 71.98 ± 8.72, 47% female), separately. Subtype 1 had better baseline visuospatial function than subtype 2 (p < 0.05), whereas subtype 2 had better baseline memory function than subtype 1 (p < 0.05). Subtype 2 showed worse progression in memory (p = 0.003), language (p = 0.003), visuospatial function (p = 0.020), and mental state (p = 0.038) than subtype 1. Subtype 1 often shared increased structural covariance network, mainly in the frontal lobe and temporal lobe regions, whereas subtype 2 often shared increased structural covariance network, mainly in occipital lobe regions and temporal lobe regions. Functional annotation further revealed that all differential structural covariance network between the two AD subtypes were mainly implicated in memory, learning, emotion, and cognition. Additionally, differences in gray matter volume (GMV) between AD subtypes were identified, and genes associated with GMV differences were found to be enriched in the terms potassium ion transport, synapse organization, and histone modification and the pathways viral infection, neurodegeneration-multiple diseases, and long-term depression. The two distinct AD subtypes were identified and characterized with neuroanatomy, cognitive trajectories, and gene expression profiles. These comprehensive results have implications for neurobiology mechanisms and precision medicine.

Data-driven modelling of neurodegenerative disease progression: thinking outside the black box

Data-driven disease progression models are an emerging set of computational tools that reconstruct disease timelines for long-term chronic diseases, providing unique insights into disease processes and their underlying mechanisms. Such methods combine a priori human knowledge and assumptions with large-scale data processing and parameter estimation to infer long-term disease trajectories from short-term data. In contrast to 'black box' machine learning tools, data-driven disease progression models typically require fewer data and are inherently interpretable, thereby aiding disease understanding in addition to enabling classification, prediction and stratification. In this Review, we place the current landscape of data-driven disease progression models in a general framework and discuss their enhanced utility for constructing a disease timeline compared with wider machine learning tools that construct static disease profiles. We review the insights they have enabled across multiple neurodegenerative diseases, notably Alzheimer disease, for applications such as determining temporal trajectories of disease biomarkers, testing hypotheses about disease mechanisms and uncovering disease subtypes. We outline key areas for technological development and translation to a broader range of neuroscience and non-neuroscience applications. Finally, we discuss potential pathways and barriers to integrating disease progression models into clinical practice and trial settings.

Robustly uncovering the heterogeneity of neurodegenerative disease by using data-driven subtyping in neuroimaging: A review

Neurodegenerative diseases are associated with heterogeneity in genetics, pathology, and clinical manifestation. Understanding this heterogeneity is particularly relevant for clinical prognosis and stratifying patients for disease modifying treatments. Recently, data-driven methods based on neuroimaging have been applied to investigate the subtyping of neurodegenerative disease, helping to disentangle this heterogeneity. We reviewed brain-based subtyping studies in aging and representative neurodegenerative diseases, including Alzheimer's disease, mild cognitive impairment, frontotemporal dementia, and Lewy body dementia, from January 2000 to November 2022. We summarized clustering methods, validation, robustness, reproducibility, and clinical relevance of 71 eligible studies in the present study. We found vast variations in approaches between studies, including ten neuroimaging modalities, 24 cluster algorithms, and 41 methods of cluster number determination. The clinical relevance of subtyping studies was evaluated by summarizing the analysis method of clinical measurements, showing a relatively low clinical utility in the current studies. Finally, we conclude that future studies of heterogeneity in neurodegenerative disease should focus on validation, comparison between subtyping approaches, and prioritise clinical utility.

Identification of Outcome-Oriented Progression Subtypes from Mild Cognitive Impairment to Alzheimer's Disease Using Electronic Health Records

Alzheimer's disease (AD) is a complex heterogeneous neurodegenerative disease that requires an in-depth understanding of its progression pathways and contributing factors to develop effective risk stratification and prevention strategies. In this study, we proposed an outcome-oriented model to identify progression pathways from mild cognitive impairment (MCI) to AD using electronic health records (EHRs) from the OneFlorida+ Clinical Research Consortium. To achieve this, we employed the long short-term memory (LSTM) network to extract relevant information from the sequential records of each patient. The hierarchical agglomerative clustering was then applied to the learned representation to group patients based on their progression subtypes. Our approach identified multiple progression pathways, each of which represented distinct patterns of disease progression from MCI to AD. These pathways can serve as a valuable resource for researchers to understand the factors influencing AD progression and to develop personalized interventions to delay or prevent the onset of the disease.

Alzheimer's Disease: An Attempt of Total Recall

This review is an attempt to compile existing hypotheses on the mechanisms underlying the initiation and progression of Alzheimer's disease (AD), starting from sensory impairments observed in AD and concluding with molecular events that are typically associated with the disease. These events include spreading of amyloid plaques and tangles of hyperphosphorylated tau and formation of Hirano and Biondi bodies as well as the development of oxidative stress. We have detailed the degenerative changes that occur in several neuronal populations, including the cholinergic neurons in the nucleus basalis of Meynert, the histaminergic neurons in the tuberomammillary nucleus, the serotonergic neurons in the raphe nuclei, and the noradrenergic neurons in the locus coeruleus. Furthermore, we discuss the potential role of iron accumulation in the brains of subjects with AD in the disease progression which served as a basis for the idea that iron chelation in the brain may mitigate oxidative stress and decelerate disease development. We also draw attention to possible role of sympathetic system and, more specifically, noradrenergic neurons of the superior cervical ganglion in triggering of the disease. We also explore the alternative possibility of compensatory protective changes that may occur in these neurons to support cholinergic function in the forebrain of subjects with AD.

Early Diagnosing and Transformation Prediction of Alzheimer's Disease Using Multi-Scaled Self-Attention Network on Structural MRI Images with Occlusion Sensitivity Analysis

BACKGROUND

Structural magnetic resonance imaging (sMRI) is vital for early Alzheimer's disease (AD) diagnosis, though confirming specific biomarkers remains challenging. Our proposed Multi-Scale Self-Attention Network (MUSAN) enhances classification of cognitively normal (CN) and AD individuals, distinguishing stable (sMCI) from progressive mild cognitive impairment (pMCI).

OBJECTIVE

This study leverages AD structural atrophy properties to achieve precise AD classification, combining different scales of brain region features. The ultimate goal is an interpretable algorithm for this method.

METHODS

The MUSAN takes whole-brain sMRI as input, enabling automatic extraction of brain region features and modeling of correlations between different scales of brain regions, and achieves personalized disease interpretation of brain regions. Furthermore, we also employed an occlusion sensitivity algorithm to localize and visualize brain regions sensitive to disease.

RESULTS

Our method is applied to ADNI-1, ADNI-2, and ADNI-3, and achieves high performance on the classification of CN from AD with accuracy (0.93), specificity (0.82), sensitivity (0.96), and area under curve (AUC) (0.95), as well as notable performance on the distinguish of sMCI from pMCI with accuracy (0.85), specificity (0.84), sensitivity (0.74), and AUC (0.86). Our sensitivity masking algorithm identified key regions in distinguishing CN from AD: hippocampus, amygdala, and vermis. Moreover, cingulum, pallidum, and inferior frontal gyrus are crucial for sMCI and pMCI discrimination. These discoveries align with existing literature, confirming the dependability of our model in AD research.

CONCLUSION

Our method provides an effective AD diagnostic and conversion prediction method. The occlusion sensitivity algorithm enhances deep learning interpretability, bolstering AD research reliability.

Prediction of misfolded proteins spreading in Alzheimer's disease using machine learning and spreading models

The pervasive impact of Alzheimer's disease on aging society represents one of the main challenges at this time. Current investigations highlight 2 specific misfolded proteins in its development: Amyloid-$\beta$ and tau. Previous studies focused on spreading for misfolded proteins exploited simulations, which required several parameters to be empirically estimated. Here, we provide an alternative view based on 2 machine learning approaches which we compare with known simulation models. The first approach applies an autoregressive model constrained by structural connectivity, while the second is based on graph convolutional networks. The aim is to predict concentrations of Amyloid-$\beta$ 2 yr after a provided baseline. We also evaluate its real-world effectiveness and suitability by providing a web service for physicians and researchers. In experiments, the autoregressive model generally outperformed state-of-the-art models resulting in lower prediction errors. While it is important to note that a comprehensive prognostic plan cannot solely rely on amyloid beta concentrations, their prediction, achieved by the discussed approaches, can be valuable for planning therapies and other cures, especially when dealing with asymptomatic patients for whom novel therapies could prove effective.

Identifying underlying patterns in Alzheimer's disease trajectory: a deep learning approach and Mendelian randomization analysis

Background

Alzheimer's disease (AD) is a heterogeneously progressive neurodegeneration disorder with varied rates of deterioration, either between subjects or within different stages of a certain subject. Estimating the course of AD at early stages has treatment implications. We aimed to analyze disease progression to identify distinct patterns in AD trajectory.

Methods

We proposed a deep learning model to identify underlying patterns in the trajectory from cognitively normal (CN) to a state of mild cognitive impairment (MCI) to AD dementia, by jointly predicting time-to-conversion and clustering out distinct subgroups characterized by comprehensive features as well as varied progression rates. We designed and validated our model on the ADNI dataset (1370 participants). Prediction of time-to-conversion in AD trajectory was used to validate the expression of the identified patterns. Causality between patterns and time-to-conversion was further inferred using Mendelian randomization (MR) analysis. External validation was performed on the AIBL dataset (233 participants).

Findings

The proposed model clustered out patterns characterized by significantly different biomarkers and varied progression rates. The discovered patterns also showed a strong prediction ability, as indicated by hazard ratio (CN→MCI, HR = 3.51, p < 0.001; MCI→AD, HR = 8.11, p < 0.001), C-Index (CN→MCI, 0.618; MCI→AD, 0.718), and AUC (CN→MCI, 3 years 0.802, 5 years 0.876; MCI→AD, 3 years 0.914, 5 years 0.957). In the external validation cohort, our model demonstrated competitive performance on conversion time prediction (CN→MCI, C-Index = 0.693; MCI→AD, C-Index = 0.752). Moreover, suggestive associations between CN→MCI/MCI→AD patterns with four/three SNPs were mediated and MR analysis indicated a causal link between MCI→AD patterns and time-to-conversion in the first three years.

Interpretation

Our proposed model identifies biologically and clinically meaningful patterns from real-world data and provides promising performance on time-to-conversion prediction in AD trajectory, which could promote the understanding of disease progression, facilitate clinical trial design, and provide potential for decision-making.

Funding

The National Key Research and Development Program of China, the Key R&D Program of Zhejiang, and the National Nature Science Foundation of China.

Identification of Outcome-Oriented Progression Subtypes from Mild Cognitive Impairment to Alzheimer's Disease Using Electronic Health Records

Alzheimer's disease (AD) is a complex heterogeneous neurodegenerative disease that requires an in-depth understanding of its progression pathways and contributing factors to develop effective risk stratification and prevention strategies. In this study, we proposed an outcome-oriented model to identify progression pathways from mild cognitive impairment (MCI) to AD using electronic health records (EHRs) from the OneFlorida+ Clinical Research Consortium. To achieve this, we employed the long short-term memory (LSTM) network to extract relevant information from the sequential records of each patient. The hierarchical agglomerative clustering was then applied to the learned representation to group patients based on their progression subtypes. Our approach identified multiple progression pathways, each of which represented distinct patterns of disease progression from MCI to AD. These pathways can serve as a valuable resource for researchers to understand the factors influencing AD progression and to develop personalized interventions to delay or prevent the onset of the disease.

An Alzheimer's disease category progression sub-grouping analysis using manifold learning on ADNI

Many current statistical and machine learning methods have been used to explore Alzheimer's disease (AD) and its associated patterns that contribute to the disease. However, there has been limited success in understanding the relationship between cognitive tests, biomarker data, and patient AD category progressions. In this work, we perform exploratory data analysis of AD health record data by analyzing various learned lower dimensional manifolds to separate early-stage AD categories further. Specifically, we used Spectral embedding, Multidimensional scaling, Isomap, t-Distributed Stochastic Neighbour Embedding, Uniform Manifold Approximation and Projection, and sparse denoising autoencoder based manifolds on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. We then determine the clustering potential of the learned embeddings and then determine if category sub-groupings or sub-categories can be found. We then used a Kruskal-sWallis H test to determine the statistical significance of the discovered AD subcategories. Our results show that the existing AD categories do exhibit sub-groupings, especially in mild cognitive impairment transitions in many of the tested manifolds, showing there may be a need for further subcategories to describe AD progression.

Differential response to donepezil in MRI subtypes of mild cognitive impairment

BACKGROUND

Donepezil is an approved therapy for the treatment of Alzheimer's disease (AD). Results across clinical trials have been inconsistent, which may be explained by design-methodological issues, the pathophysiological heterogeneity of AD, and diversity of included study participants. We investigated whether response to donepezil differs in mild cognitive impaired (MCI) individuals demonstrating different magnetic resonance imaging (MRI) subtypes.

METHODS

From the Hippocampus Study double-blind, randomized clinical trial, we included 173 MCI individuals (donepezil = 83; placebo = 90) with structural MRI data, at baseline and at clinical follow-up assessments (6-12-month). Efficacy outcomes were the annualized percentage change (APC) in hippocampal, ventricular, and total grey matter volumes, as well as in the AD cortical thickness signature. Participants were classified into MRI subtypes as typical AD, limbic-predominant, hippocampal-sparing, or minimal atrophy at baseline. We primarily applied a subtyping approach based on continuous scale of two subtyping dimensions. We also used the conventional categorical subtyping approach for comparison.

RESULTS

Donepezil-treated MCI individuals showed slower atrophy rates compared to the placebo group, but only if they belonged to the minimal atrophy or hippocampal-sparing subtypes. Importantly, only the continuous subtyping approach, but not the conventional categorical approach, captured this differential response.

CONCLUSIONS

Our data suggest that individuals with MCI, with hippocampal-sparing or minimal atrophy subtype, may have improved benefit from donepezil, as compared with MCI individuals with typical or limbic-predominant patterns of atrophy. The newly proposed continuous subtyping approach may have advantages compared to the conventional categorical approach. Future research is warranted to demonstrate the potential of subtype stratification for disease prognosis and response to treatment.

TRIAL REGISTRATION

ClinicalTrial.gov NCT00403520. Submission Date: November 21, 2006.

MRI data-driven clustering reveals different subtypes of Dementia with Lewy bodies

Dementia with Lewy bodies (DLB) is a neurodegenerative disorder with a wide heterogeneity of symptoms, which suggests the existence of different subtypes. We used data-driven analysis of magnetic resonance imaging (MRI) data to investigate DLB subtypes. We included 165 DLB from the Mayo Clinic and 3 centers from the European DLB consortium and performed a hierarchical cluster analysis to identify subtypes based on gray matter (GM) volumes. To characterize the subtypes, we used demographic and clinical data, as well as β-amyloid, tau, and cerebrovascular biomarkers at baseline, and cognitive decline over three years. We identified 3 subtypes: an older subtype with reduced cortical GM volumes, worse cognition, and faster cognitive decline (n = 49, 30%); a subtype with low GM volumes in fronto-occipital regions (n = 76, 46%); and a subtype of younger patients with the highest cortical GM volumes, proportionally lower GM volumes in basal ganglia and the highest frequency of cognitive fluctuations (n = 40, 24%). This study shows the existence of MRI subtypes in DLB, which may have implications for clinical workout, research, and therapeutic decisions.

The hippocampal sparing subtype of Alzheimer's disease assessed in neuropathology and in vivo tau positron emission tomography: a systematic review

Neuropathology and neuroimaging studies have identified several subtypes of Alzheimer's disease (AD): hippocampal sparing AD, typical AD, and limbic predominant AD. An unresolved question is whether hippocampal sparing AD cases can present with neurofibrillary tangles (NFT) in association cortices while completely sparing the hippocampus. To address that question, we conducted a systematic review and performed original analyses on tau positron emission tomography (PET) data. We searched EMBASE, PubMed, and Web of Science databases until October 2022. We also implemented several methods for AD subtyping on tau PET to identify hippocampal sparing AD cases. Our findings show that seven out of the eight reviewed neuropathologic studies included cases at Braak stages IV or higher and therefore, could not identify hippocampal sparing cases with NFT completely sparing the hippocampus. In contrast, tau PET did identify AD participants with tracer retention in the association cortex while completely sparing the hippocampus. We conclude that tau PET can identify hippocampal sparing AD cases with NFT completely sparing the hippocampus. Based on the accumulating data, we suggest two possible pathways of tau spread: (1) a canonical pathway with early involvement of transentorhinal cortex and subsequent involvement of limbic regions and association cortices, and (2) a less common pathway that affects association cortices with limbic involvement observed at end stages of the disease or not at all.