Impact of the Alzheimer's Disease Neuroimaging Initiative, 2004 to 2014

Mapping Knowledge Landscapes and Emerging Trends in AI for Dementia Biomarkers: Bibliometric and Visualization Analysis

BACKGROUND

With the rise of artificial intelligence (AI) in the field of dementia biomarker research, exploring its current developmental trends and research focuses has become increasingly important. This study, using literature data mining, analyzes and assesses the key contributions and development scale of AI in dementia biomarker research.

OBJECTIVE

The aim of this study was to comprehensively evaluate the current state, hot topics, and future trends of AI in dementia biomarker research globally.

METHODS

This study thoroughly analyzed the literature in the application of AI to dementia biomarkers across various dimensions, such as publication volume, authors, institutions, journals, and countries, based on the Web of Science Core Collection. In addition, scales, trends, and potential connections between AI and biomarkers were extracted and deeply analyzed through multiple expert panels.

RESULTS

To date, the field includes 1070 publications across 362 journals, involving 74 countries and 1793 major research institutions, with a total of 6455 researchers. Notably, 69.41% (994/1432) of the researchers ceased their studies before 2019. The most prevalent algorithms used are support vector machines, random forests, and neural networks. Current research frequently focuses on biomarkers such as imaging biomarkers, cerebrospinal fluid biomarkers, genetic biomarkers, and blood biomarkers. Recent advances have highlighted significant discoveries in biomarkers related to imaging, genetics, and blood, with growth in studies on digital and ophthalmic biomarkers.

CONCLUSIONS

The field is currently in a phase of stable development, receiving widespread attention from numerous countries, institutions, and researchers worldwide. Despite this, stable clusters of collaborative research have yet to be established, and there is a pressing need to enhance interdisciplinary collaboration. Algorithm development has shown prominence, especially the application of support vector machines and neural networks in imaging studies. Looking forward, newly discovered biomarkers are expected to undergo further validation, and new types, such as digital biomarkers, will garner increased research interest and attention.

Data sharing as the foundation of discovery: ADNI and breakthroughs in Alzheimer's disease

The COVID pandemic has shown that when the research community comes together, we can conquer the most complex biomedical challenges. Collaboration and teamwork among federal agencies, private organizations, and researchers have been crucial in the development of vaccines and therapeutics against COVID. Possibly the first example of such cross-functional collaboration is the Alzheimer's Disease Neuroimaging Initiative (ADNI), the largest and longest continually monitored Alzheimer's study. ADNI was designed and operated as a public-private partnership, managed by the Foundation for the National Institutes of Health. This article shows how recent successes in the Alzheimer's field are directly a result of ADNI's open and transparent sharing of knowledge, expertise, and resources, which have allowed researchers to advance their understanding of Alzheimer's and tackle challenges in a relatively short period of time. ADNI's approach to open-source innovation also served as a model for addressing other complex diseases and led to numerous collaborative research initiatives. HIGHLIGHTS: The Alzheimer's Disease Neuroimaging Initiative (ADNI) was designed, structured, and operated as a public-private partnership, managed by the Foundation for the National Institutes of Health. The recent successes in the Alzheimer's field are directly a result of ADNI's efforts. Open and transparent sharing of knowledge, expertise, and resources allowed researchers to advance their understanding of Alzheimer's and tackle challenges in a relatively short period of time.

Choroid plexus volumes and auditory verbal learning scores are associated with conversion from mild cognitive impairment to Alzheimer's disease

PURPOSE

Mild cognitive impairment (MCI) can be the prodromal phase of Alzheimer's disease (AD) where appropriate intervention might prevent or delay conversion to AD. Given this, there has been increasing interest in using magnetic resonance imaging (MRI) and neuropsychological testing to predict conversion from MCI to AD. Recent evidence suggests that the choroid plexus (ChP), neural substrates implicated in brain clearance, undergo volumetric changes in MCI and AD. Whether the ChP is involved in memory changes observed in MCI and can be used to predict conversion from MCI to AD has not been explored.

METHOD

The current study used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database to investigate whether later progression from MCI to AD (progressive MCI [pMCI], n = 115) or stable MCI (sMCI, n = 338) was associated with memory scores using the Rey Auditory Verbal Learning Test (RAVLT) and ChP volumes as calculated from MRI. Classification analyses identifying pMCI or sMCI group membership were performed to compare the predictive ability of the RAVLT and ChP volumes.

FINDING

The results indicated a significant difference between pMCI and sMCI groups for right ChP volume, with the pMCI group showing significantly larger right ChP volume (p = .01, 95% confidence interval [-.116, -.015]). A significant linear relationship between the RAVLT scores and right ChP volume was found across all participants, but not for the two groups separately. Classification analyses showed that a combination of left ChP volume and auditory verbal learning scores resulted in the most accurate classification performance, with group membership accurately predicted for 72% of the testing data.

CONCLUSION

These results suggest that volumetric ChP changes appear to occur before the onset of AD and might provide value in predicting conversion from MCI to AD.

Gliovascular transcriptional perturbations in Alzheimer's disease reveal molecular mechanisms of blood brain barrier dysfunction

To uncover molecular changes underlying blood-brain-barrier dysfunction in Alzheimer's disease, we performed single nucleus RNA sequencing in 24 Alzheimer's disease and control brains and focused on vascular and astrocyte clusters as main cell types of blood-brain-barrier gliovascular-unit. The majority of the vascular transcriptional changes were in pericytes. Of the vascular molecular targets predicted to interact with astrocytic ligands, SMAD3, upregulated in Alzheimer's disease pericytes, has the highest number of ligands including VEGFA, downregulated in Alzheimer's disease astrocytes. We validated these findings with external datasets comprising 4,730 pericyte and 150,664 astrocyte nuclei. Blood SMAD3 levels are associated with Alzheimer's disease-related neuroimaging outcomes. We determined inverse relationships between pericytic SMAD3 and astrocytic VEGFA in human iPSC and zebrafish models. Here, we detect vast transcriptome changes in Alzheimer's disease at the gliovascular-unit, prioritize perturbed pericytic SMAD3-astrocytic VEGFA interactions, and validate these in cross-species models to provide a molecular mechanism of blood-brain-barrier disintegrity in Alzheimer's disease.

A new and unified method for regression analysis of interval-censored failure time data under semiparametric transformation models with missing covariates

This paper discusses regression analysis of interval-censored failure time data arising from semiparametric transformation models in the presence of missing covariates. Although some methods have been developed for the problem, they either apply only to limited situations or may have some computational issues. Corresponding to these, we propose a new and unified two-step inference procedure that can be easily implemented using the existing or standard software. The proposed method makes use of a set of working models to extract partial information from incomplete observations and yields a consistent estimator of regression parameters assuming missing at random. An extensive simulation study is conducted and indicates that it performs well in practical situations. Finally, we apply the proposed approach to an Alzheimer's Disease study that motivated this study.

Mahmoud L, Sadek I. AI-based tool for early detection of Alzheimer's disease

In the context of Alzheimer's disease (AD), timely identification is paramount for effective management, acknowledging its chronic and irreversible nature, where medications can only impede its progression. Our study introduces a holistic solution, leveraging the hippocampus and the VGG16 model with transfer learning for early AD detection. The hippocampus, a pivotal early affected region linked to memory, plays a central role in classifying patients into three categories: cognitively normal (CN), representing individuals without cognitive impairment; mild cognitive impairment (MCI), indicative of a subtle decline in cognitive abilities; and AD, denoting Alzheimer's disease. Employing the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, our model undergoes training enriched by advanced image preprocessing techniques, achieving outstanding accuracy (testing 98.17 %, validation 97.52 %, training 99.62 %). The strategic use of transfer learning fortifies our competitive edge, incorporating the hippocampus approach and, notably, a progressive data augmentation technique. This innovative augmentation strategy gradually introduces augmentation factors during training, significantly elevating accuracy and enhancing the model's generalization ability. The study emphasizes practical application with a user-friendly website, empowering radiologists to predict class probabilities, track disease progression, and visualize patient images in both 2D and 3D formats, contributing significantly to the advancement of early AD detection.

Association between loneliness and cognitive function, and brain volume in community-dwelling elderly

Introduction

We investigated the relationship between loneliness, cognitive impairment, and regional brain volume among elderly individuals residing in the Korean community.

Methods

Data from the ARIRANG aging-cognition sub-cohort, collected between 2020 and 2022, were utilized for the present study. Loneliness was assessed using the UCLA-Loneliness Scale (UCLA-LS) questionnaire and the relevant item from Center for Epidemiologic Studies Depression Scale Korean version (CES-D-K). Cognitive impairment was measured through Mini-Mental State Examination (K-MMSE-2) and Seoul Neuropsychological Screening Battery (SNSB-C), with five sub-categories: attention, memory, visuospatial function, language, and executive function. Logistic regression was employed for prevalence ratios related to cognitive impairment, while linear regression was used for regional brain volume including white matter hyperintensity (WMH) and cortical thickness.

Results

Our analysis involved 785 participants (292 men and 493 women). We observed increased cognitive impairment assessed by K-MMSE-2 [UCLA-LS: odds ratio (OR) 3.133, 95% confidence interval (CI) 1.536-6.393; loneliness from CES-D: OR 2.823, 95% CI 1.426-5.590] and SNSB-C total score (UCLA-LS: OR 2.145, 95% CI 1.304-3.529) in the lonely group compared to the non-lonely group. Specifically, the lonely group identified by UCLA-LS showed an association with declined visuospatial (OR 1.591, 95% CI 1.029-2.460) and executive function (OR 1.971, 95% CI 1.036-3.750). The lonely group identified by CES-D-K was associated with impaired memory (OR 1.577, 95% CI 1.009-2.466) and executive function (OR 1.863, 95% CI 1.036-3.350). In the regional brain volume analysis, loneliness was linked to reduced brain volume in frontal white matter (left: -1.24, 95% CI -2.37 ∼-0.12; right: -1.16, 95% CI -2.31 ∼ -0.00), putamen (left: -0.07, 95% CI -0.12 ∼-0.02; right: -0.06, 95% CI -0.11 ∼-0.01), and globus pallidus (-15.53, 95% CI -30.13 ∼-0.93). There was no observed association in WMH and cortical thickness.

Conclusion

Loneliness is associated with cognitive decline and volumetric reduction in the frontal white matter, putamen, and globus pallidus.

Altered resting-state functional connectivity and dynamic network properties in cognitive impairment: an independent component and dominant-coactivation pattern analyses study

Introduction

Cognitive impairment (CI) due to Alzheimer's disease (AD) encompasses a decline in cognitive abilities and can significantly impact an individual's quality of life. Early detection and intervention are crucial in managing CI, both in the preclinical and prodromal stages of AD prior to dementia.

Methods

In this preliminary study, we investigated differences in resting-state functional connectivity and dynamic network properties between 23 individual with CI due to AD based on clinical assessment and 15 healthy controls (HC) using Independent Component Analysis (ICA) and Dominant-Coactivation Pattern (d-CAP) analysis. The cognitive status of the two groups was also compared, and correlations between cognitive scores and d-CAP switching probability were examined.

Results

Results showed comparable numbers of d-CAPs in the Default Mode Network (DMN), Executive Control Network (ECN), and Frontoparietal Network (FPN) between HC and CI groups. However, the Visual Network (VN) exhibited fewer d-CAPs in the CI group, suggesting altered dynamic properties of this network for the CI group. Additionally, ICA revealed significant connectivity differences for all networks. Spatial maps and effect size analyses indicated increased coactivation and more synchronized activity within the DMN in HC compared to CI. Furthermore, reduced switching probabilities were observed for the CI group in DMN, VN, and FPN networks, indicating less dynamic and flexible functional interactions.

Discussion

The findings highlight altered connectivity patterns within the DMN, VN, ECN, and FPN, suggesting the involvement of multiple functional networks in CI. Understanding these brain processes may contribute to developing targeted diagnostic and therapeutic strategies for CI due to AD.

ADSS: A Composite Score to Detect Disease Progression in Alzheimer's Disease

Background

Composite scores have been increasingly used in trials for Alzheimer's disease (AD) to detect disease progression, such as the AD Composite Score (ADCOMS) in the lecanemab trial.

Objective

To develop a new composite score to improve the prediction of outcome change.

Methods

We proposed to develop a new composite score based on the statistical model in the ADCOMS, by removing duplicated sub-scales and adding the model selection in the partial least squares (PLS) regression.

Results

The new AD composite Score with variable Selection (ADSS) includes 7 cognitive sub-scales. ADSS can increase the sensitivity to detect disease progression as compared to the existing total scores, which leads to smaller sample sizes using the ADSS in trial designs.

Conclusions

ADSS can be utilized in AD trials to improve the success rate of drug development with a high sensitivity to detect disease progression in early stages.

CD163-Mediated Small-Vessel Injury in Alzheimer's Disease: An Exploration from Neuroimaging to Transcriptomics

Patients with Alzheimer's disease (AD) often present with imaging features indicative of small-vessel injury, among which, white-matter hyperintensities (WMHs) are the most prevalent. However, the underlying mechanism of the association between AD and small-vessel injury is still obscure. The aim of this study is to investigate the mechanism of small-vessel injury in AD. Differential gene expression analyses were conducted to identify the genes related to WMHs separately in mild cognitive impairment (MCI) and cognitively normal (CN) subjects from the ADNI database. The WMH-related genes identified in patients with MCI were considered to be associated with small-vessel injury in early AD. Functional enrichment analyses and a protein-protein interaction (PPI) network were performed to explore the pathway and hub genes related to the mechanism of small-vessel injury in MCI. Subsequently, the Boruta algorithm and support vector machine recursive feature elimination (SVM-RFE) algorithm were performed to identify feature-selection genes. Finally, the mechanism of small-vessel injury was analyzed in MCI from the immunological perspectives; the relationship of feature-selection genes with various immune cells and neuroimaging indices were also explored. Furthermore, 5×FAD mice were used to demonstrate the genes related to small-vessel injury. The results of the logistic regression analyses suggested that WMHs significantly contributed to MCI, the early stage of AD. A total of 276 genes were determined as WMH-related genes in patients with MCI, while 203 WMH-related genes were obtained in CN patients. Among them, only 15 genes overlapped and were thus identified as the crosstalk genes. By employing the Boruta and SVM-RFE algorithms, CD163, ALDH3B1, MIR22HG, DTX2, FOLR2, ALDH2, and ZNF23 were recognized as the feature-selection genes linked to small-vessel injury in MCI. After considering the results from the PPI network, CD163 was finally determined as the critical WMH-related gene in MCI. The expression of CD163 was correlated with fractional anisotropy (FA) values in regions that are vulnerable to small-vessel injury in AD. The immunostaining and RT-qPCR results from the verifying experiments demonstrated that the indicators of small-vessel injury presented in the cortical tissue of 5×FAD mice and related to the upregulation of CD163 expression. CD163 may be the most pivotal candidates related to small-vessel injury in early AD.

A Pragmatic, Investigator-Driven Process for Disclosure of Amyloid PET Scan Results to ADNI-4 Research Participants

BACKGROUND

Prior studies of Alzheimer's disease (AD) biomarker disclosure have answered important questions about individuals' safety after learning and comprehending their amyloid PET results; however, these studies have typically employed highly structured disclosure protocols and focused on the psychological impact of disclosure (e.g., anxiety, depression, and suicidality) in homogeneous populations. More work is needed to develop flexible disclosure protocols and study outcomes in ethnoculturally representative samples.

METHODS

The Alzheimer's Disease Neuroimaging Initiative (ADNI) is formally incorporating amyloid PET disclosure into the newest protocol (ADNI-4). Participants across the cognitive spectrum who wish to know their amyloid PET results may learn them. The pragmatic disclosure process spans four timepoints: (1) a pre-disclosure visit, (2) the PET scan and its read, (3) a disclosure visit, and (4) a post-disclosure check-in. This process applies to all participants, with slight modifications to account for their cognitive status. In designing this process, special emphasis was placed on utilizing investigator discretion. Participant measures include perceived risk of dementia, purpose in life, and disclosure satisfaction. Investigator assessment of the disclosure visit (e.g., challenges encountered, topics discussed, etc.) is also included.

RESULTS

Data collection is ongoing. Results will allow for more robust characterization of the impact of learning amyloid PET results on individuals and describe the perspectives of investigators.

CONCLUSION

The pragmatic design of the disclosure process in ADNI-4 coupled with the novel participant and investigator data will inform future disclosure practices. This is especially important as disclosure of biomarker results expands in research and care.

Personalized Computational Causal Modeling of the Alzheimer Disease Biomarker Cascade

BACKGROUND

Mathematical models of complex diseases, such as Alzheimer's disease, have the potential to play a significant role in personalized medicine. Specifically, models can be personalized by fitting parameters with individual data for the purpose of discovering primary underlying disease drivers, predicting natural history, and assessing the effects of theoretical interventions. Previous work in causal/mechanistic modeling of Alzheimer's Disease progression has modeled the disease at the cellular level and on a short time scale, such as minutes to hours. No previous studies have addressed mechanistic modeling on a personalized level using clinically validated biomarkers in individual subjects.

OBJECTIVES

This study aimed to investigate the feasibility of personalizing a causal model of Alzheimer's Disease progression using longitudinal biomarker data.

DESIGN/SETTING/PARTICIPANTS/MEASUREMENTS

We chose the Alzheimer Disease Biomarker Cascade model, a widely-referenced hypothetical model of Alzheimer's Disease based on the amyloid cascade hypothesis, which we had previously implemented mathematically as a mechanistic model. We used available longitudinal demographic and serial biomarker data in over 800 subjects across the cognitive spectrum from the Alzheimer's Disease Neuroimaging Initiative. The data included participants that were cognitively normal, had mild cognitive impairment, or were diagnosed with dementia (probable Alzheimer's Disease). The model consisted of a sparse system of differential equations involving four measurable biomarkers based on cerebrospinal fluid proteins, imaging, and cognitive testing data.

RESULTS

Personalization of the Alzheimer Disease Biomarker Cascade model with individual serial biomarker data yielded fourteen personalized parameters in each subject reflecting physiologically meaningful characteristics. These included growth rates, latency values, and carrying capacities of the various biomarkers, most of which demonstrated significant differences across clinical diagnostic groups. The model fits to training data across the entire cohort had a root mean squared error (RMSE) of 0.09 (SD 0.081) on a variable scale between zero and one, and were robust, with over 90% of subjects showing an RMSE of < 0.2. Similarly, in a subset of subjects with data on all four biomarkers in at least one test set, performance was high on the test sets, with a mean RMSE of 0.15 (SD 0.117), with 80% of subjects demonstrating an RMSE < 0.2 in the estimation of future biomarker points. Cluster analysis of parameters revealed two distinct endophenotypic groups, with distinct biomarker profiles and disease trajectories.

CONCLUSION

Results support the feasibility of personalizing mechanistic models based on individual biomarker trajectories and suggest that this approach may be useful for reclassifying subjects on the Alzheimer's clinical spectrum. This computational modeling approach is not limited to the Alzheimer Disease Biomarker Cascade hypothesis, and can be applied to any mechanistic hypothesis of disease progression in the Alzheimer's field that can be monitored with biomarkers. Thus, it offers a computational platform to compare and validate various disease hypotheses, personalize individual biomarker trajectories and predict individual response to theoretical prevention and therapeutic intervention strategies.

Associations of Frailty with Neuropsychiatric Symptoms of Alzheimer's Disease: A Longitudinal Study

Background

Frailty is a vulnerability state increasing the risk of many adverse health outcomes, but little is known about the effects of frailty on neuropsychiatric health.

Objective

To explore the associations between frailty and the risk of neuropsychiatric symptoms (NPSs) in Alzheimer's disease (AD), especially in its different clinical stages.

Methods

We included 2,155 individuals assessed using modified frailty index-11 (mFI-11), Neuropsychiatric Inventory (NPI) and Neuropsychiatric Inventory Questionnaire (NPI-Q) in the Alzheimer's Disease Neuroimaging Initiative (ADNI). The relationships between frailty and NPSs were explored with logistic regression models and Cox proportional hazard regression models. Causal mediation analyses were conducted to explore the mediation factors between frailty and NPSs.

Results

Among mild cognitive impairment (MCI) participants, frailty was cross-sectionally associated with an increased risk of apathy, and longitudinally associated with increased risk of depression and apathy. Among AD participants, frailty was cross-sectionally associated with increased risk of depression and anxiety, and longitudinally associated with an increased risk of apathy. Among participants with cognitive progression, frailty was associated with increased risk of depression and apathy. In MCI participants, the influence of frailty on NPSs was partially mediated by hippocampus volume, whole brain volume, and monocytes, with mediating proportions ranging from 8.40% to 9.29%.

Conclusions

Frailty was associated with NPSs such as depression, anxiety, and apathy among MCI, AD, and cognitive progression participants. Atrophy of the hippocampus and whole brain, as well as peripheral immunity may be involved in the potential mechanisms underlying the above associations.

A robust class decomposition-based approach for detecting Alzheimer's progression

Computer-aided diagnosis of Alzheimer's disease (AD) is a rapidly growing field with the possibility to be utilized in practice. Deep learning has received much attention in detecting AD from structural magnetic resonance imaging (sMRI). However, training a convolutional neural network from scratch is problematic because it requires a lot of annotated data and additional computational time. Transfer learning can offer a promising and practical solution by transferring information learned from other image recognition tasks to medical image classification. Another issue is the dataset distribution's irregularities. A common classification issue in datasets is a class imbalance, where the distribution of samples among the classes is biased. For example, a dataset may contain more instances of some classes than others. Class imbalance is challenging because most machine learning algorithms assume that each class should have an equal number of samples. Models consequently perform poorly in prediction. Class decomposition can address this problem by making learning a dataset's class boundaries easier. Motivated by these approaches, we propose a class decomposition transfer learning (CDTL) approach that employs VGG19, AlexNet, and an entropy-based technique to detect AD from sMRI. This study aims to assess the robustness of the CDTL approach in detecting the cognitive decline of AD using data from various ADNI cohorts to determine whether comparable classification accuracy for the two or more cohorts would be obtained. Furthermore, the proposed model achieved state-of-the-art performance in predicting mild cognitive impairment (MCI)-to-AD conversion with an accuracy of 91.45%.

Grey matter volume and CSF biomarkers predict neuropsychological subtypes of MCI

There is increasing evidence of different subtypes of individuals with mild cognitive impairment (MCI). An important line of research is whether neuropsychologically-defined subtypes have distinct patterns of neurodegeneration and cerebrospinal fluid (CSF) biomarker composition. In our study, we demonstrated that MCI participants of the ADNI database (N = 640) can be discriminated into 3 coherent neuropsychological subgroups. Our clustering approach revealed amnestic MCI, mixed MCI, and cluster-derived normal subgroups. Furthermore, classification modeling revealed that specific predictive features can be used to differentiate amnestic and mixed MCI from cognitively normal (CN) controls: CSF Aβ142 concentration for the former and CSF Aβ1-42 concentration, tau concentration as well as grey matter atrophy (especially in the temporal and occipital lobes) for the latter. In contrast, participants from the cluster-derived normal subgroup exhibited an identical profile to CN controls in terms of cognitive performance, brain structure, and CSF biomarker levels. Our comprehensive data analytics strategy provides further evidence that multimodal neuropsychological subtyping is both clinically and neurobiologically meaningful.

The impact of quality control on cortical morphometry comparisons in autism

Structural magnetic resonance imaging (MRI) quality is known to impact and bias neuroanatomical estimates and downstream analysis, including case-control comparisons, and a growing body of work has demonstrated the importance of careful quality control (QC) and evaluated the impact of image and image-processing quality. However, the growing size of typical neuroimaging datasets presents an additional challenge to QC, which is typically extremely time and labour intensive. One of the most important aspects of MRI quality is the accuracy of processed outputs, which have been shown to impact estimated neurodevelopmental trajectories. Here, we evaluate whether the quality of surface reconstructions by FreeSurfer (one of the most widely used MRI processing pipelines) interacts with clinical and demographic factors. We present a tool, FSQC, that enables quick and efficient yet thorough assessment of outputs of the FreeSurfer processing pipeline. We validate our method against other existing QC metrics, including the automated FreeSurfer Euler number, two other manual ratings of raw image quality, and two popular automated QC methods. We show strikingly similar spatial patterns in the relationship between each QC measure and cortical thickness; relationships for cortical volume and surface area are largely consistent across metrics, though with some notable differences. We next demonstrate that thresholding by QC score attenuates but does not eliminate the impact of quality on cortical estimates. Finally, we explore different ways of controlling for quality when examining differences between autistic individuals and neurotypical controls in the Autism Brain Imaging Data Exchange (ABIDE) dataset, demonstrating that inadequate control for quality can alter results of case-control comparisons.

Graph neural network based unsupervised influential sample selection for brain multigraph population fusion

Graph neural networks (GNNs) have witnessed remarkable proliferation due to the increasing number of applications where data is represented as graphs. GNN-based multigraph population fusion methods for estimating population representative connectional brain templates (CBT) have recently led to improvements, especially in network neuroscience. However, prior studies do not consider how an individual training brain multigraph influences the quality of GNN training for brain multigraph population fusion. To address this issue, we propose two major sample selection methods to quantify the influence of a training brain multigraph on the brain multigraph population fusion task using GNNs, in a fully unsupervised manner: (1) GraphGradIn, in which we use gradients w.r.t GNN weights to trace changes in the centeredness loss of connectional brain template during the training phase; (2) GraphTestIn, in which we exclude a training brain multigraph of interest during the refinement process in the test phase to infer its influence on the CBT centeredness loss. Next, we select the most influential multigraphs to build the training set for brain multigraph population fusion into a CBT. We conducted extensive experiments on brain multigraph datasets to show that using a dataset of influential training samples improves the learned connectional brain template in terms of centeredness, discriminativeness, and topological soundness. Finally, we demonstrate the use of our methods by discovering the connectional fingerprints of healthy and neurologically disordered brain multigraph populations including Alzheimer's disease and Autism spectrum disorder patients. Our source code is available at https://github.com/basiralab/GraphGradIn.

Interpretable machine learning for dementia: A systematic review

INTRODUCTION

Machine learning research into automated dementia diagnosis is becoming increasingly popular but so far has had limited clinical impact. A key challenge is building robust and generalizable models that generate decisions that can be reliably explained. Some models are designed to be inherently "interpretable," whereas post hoc "explainability" methods can be used for other models.

METHODS

Here we sought to summarize the state-of-the-art of interpretable machine learning for dementia.

RESULTS

We identified 92 studies using PubMed, Web of Science, and Scopus. Studies demonstrate promising classification performance but vary in their validation procedures and reporting standards and rely heavily on popular data sets.

DISCUSSION

Future work should incorporate clinicians to validate explanation methods and make conclusive inferences about dementia-related disease pathology. Critically analyzing model explanations also requires an understanding of the interpretability methods itself. Patient-specific explanations are also required to demonstrate the benefit of interpretable machine learning in clinical practice.

The image and data archive at the laboratory of neuro imaging

The Image and Data Archive (IDA) is a secure online resource for archiving, exploring, and sharing neuroscience data run by the Laboratory of Neuro Imaging (LONI). The laboratory first started managing neuroimaging data for multi-centered research studies in the late 1990's and since has become a nexus for many multi-site collaborations. By providing management and informatics tools and resources for de-identifying, integrating, searching, visualizing, and sharing a diverse range of neuroscience data, study investigators maintain complete control over data stored in the IDA while benefiting from a robust and reliable infrastructure that protects and preserves research data to maximize data collection investment.

Comparative survey of multigraph integration methods for holistic brain connectivity mapping

One of the greatest scientific challenges in network neuroscience is to create a representative map of a population of heterogeneous brain networks, which acts as a connectional fingerprint. The connectional brain template (CBT), also named network atlas, presents a powerful tool for capturing the most representative and discriminative traits of a given population while preserving its topological patterns. The idea of a CBT is to integrate a population of heterogeneous brain connectivity networks, derived from different neuroimaging modalities or brain views (e.g., structural and functional), into a unified holistic representation. Here we review current state-of-the-art methods designed to estimate well-centered and representative CBT for populations of single-view and multi-view brain networks. We start by reviewing each CBT learning method, then we introduce the evaluation measures to compare CBT representativeness of populations generated by single-view and multigraph integration methods, separately, based on the following criteria: Centeredness, biomarker-reproducibility, node-level similarity, global-level similarity, and distance-based similarity. We demonstrate that the deep graph normalizer (DGN) method significantly outperforms other multi-graph and all single-view integration methods for estimating CBTs using a variety of healthy and disordered datasets in terms of centeredness, reproducibility (i.e., graph-derived biomarkers reproducibility that disentangle the typical from the atypical connectivity variability), and preserving the topological traits at both local and global graph-levels.

Group-shrinkage feature selection with a spatial network for mining DNA methylation data

Identifying disease-related biomarkers from high-dimensional DNA methylation data helps in reducing early screening costs and inferring pathogenesis mechanisms. Good discovery results have been achieved through spatial correlation methods of methylation sites, group-based regularization, and network constraints. However, these methods still have some key limitations as they cannot exclude isolated differential sites and only consider adjacent site ordering. Therefore, we propose a group-shrinkage feature selection algorithm to encourage the selection of clustered sites and discourage the selection of isolated differential sites. Specifically, a network-guided group-shrinkage strategy is developed to penalize weakly-correlated isolated methylation sites through a network structure constraint. The spatial network is constructed based on spatial correlation information of DNA methylation sites, where this information accounts for the uneven site distribution. The experimental simulations and applications demonstrated that the proposed method outperforms the advanced regularization methods, especially in rejecting isolated methylation sites; hence this study provides an efficient and clinical-valuable method for biomarker candidate discovery in DNA methylation data. Additionally, the proposed method exhibits enhanced reliability due to introducing biological prior knowledge into a regularization-based feature selection framework and could promote more research in the integration between biological prior knowledge and classical feature selection methods, thus facilitating their clinical application. Our source codes will be released at https://github.com/SJTUBME-QianLab/Group-shrinkage-Spatial-Network once this manuscript is accepted for publication.

Multisite test-retest reliability and compatibility of brain metrics derived from FreeSurfer versions 7.1, 6.0, and 5.3

Automatic neuroimaging processing tools provide convenient and systematic methods for extracting features from brain magnetic resonance imaging scans. One tool, FreeSurfer, provides an easy-to-use pipeline to extract cortical and subcortical morphometric measures. There have been over 25 stable releases of FreeSurfer, with different versions used across published works. The reliability and compatibility of regional morphometric metrics derived from the most recent version releases have yet to be empirically assessed. Here, we used test-retest data from three public data sets to determine within-version reliability and between-version compatibility across 42 regional outputs from FreeSurfer versions 7.1, 6.0, and 5.3. Cortical thickness from v7.1 was less compatible with that of older versions, particularly along the cingulate gyrus, where the lowest version compatibility was observed (intraclass correlation coefficient 0.37-0.61). Surface area of the temporal pole, frontal pole, and medial orbitofrontal cortex, also showed low to moderate version compatibility. We confirm low compatibility between v6.0 and v5.3 of pallidum and putamen volumes, while those from v7.1 were compatible with v6.0. Replication in an independent sample showed largely similar results for measures of surface area and subcortical volumes, but had lower overall regional thickness reliability and compatibility. Batch effect correction may adjust for some inter-version effects when most sites are run with one version, but results vary when more sites are run with different versions. Age associations in a quality controlled independent sample (N = 106) revealed version differences in results of downstream statistical analysis. We provide a reference to highlight the regional metrics that may yield recent version-related inconsistencies in published findings. An interactive viewer is provided at http://data.brainescience.org/Freesurfer_Reliability/.

Survey of Neuroanatomic Sampling and Staining Procedures in Alzheimer Disease Research Center Brain Banks

The collection of post-mortem brain tissue has been a core function of the Alzheimer Disease Research Center's (ADRCs) network located within the United States since its inception. Individual brain banks and centers follow detailed protocols to record, store, and manage complex datasets that include clinical data, demographics, and when post-mortem tissue is available, a detailed neuropathological assessment. Since each institution often has specific research foci, there can be variability in tissue collection and processing workflows. While published guidelines exist for select diseases, such as those put forth by the National Institute on Aging and Alzheimer Association (NIA-AA), it is of importance to denote the current practices across institutions. To this end a survey was developed and sent to United States based brain bank leaders, collecting data on brain region sampling, including anatomic landmarks used, staining (including antibodies used), as well as whole-slide-image scanning hardware. We distributed this survey to 40 brain banks and obtained a response rate of 95% (38 / 40). Most brain banks followed guidelines defined by the NIA-AA, having H&E staining in all recommended regions and targeted region-based amyloid beta, tau, and alpha-synuclein immunohistochemical staining. However, sampling consistency varied related to key anatomic landmarks/locations in select regions, such as the striatum, periventricular white matter, and parietal cortex. This study highlights the diversity and similarities amongst brain banks and discusses considerations when amalgamating data/samples across multiple centers. This survey aids in establishing benchmarks to enhance dialogues on divergent workflows in a feasible way.

APOE ε2 resilience for Alzheimer's disease is mediated by plasma lipid species: Analysis of three independent cohort studies

INTRODUCTION

The apolipoprotein E (APOE) genotype is the strongest genetic risk factor for late-onset Alzheimer's disease. However, its effect on lipid metabolic pathways, and their mediating effect on disease risk, is poorly understood.

METHODS

We performed lipidomic analysis on three independent cohorts (the Australian Imaging, Biomarkers and Lifestyle [AIBL] flagship study, n = 1087; the Alzheimer's Disease Neuroimaging Initiative [ADNI] 1 study, n = 819; and the Busselton Health Study [BHS], n = 4384), and we defined associations between APOE ε2 and ε4 and 569 plasma/serum lipid species. Mediation analysis defined the proportion of the treatment effect of the APOE genotype mediated by plasma/serum lipid species.

RESULTS

A total of 237 and 104 lipid species were associated with APOE ε2 and ε4, respectively. Of these 68 (ε2) and 24 (ε4) were associated with prevalent Alzheimer's disease. Individual lipid species or lipidomic models of APOE genotypes mediated up to 30% and 10% of APOE ε2 and ε4 treatment effect, respectively.

DISCUSSION

Plasma lipid species mediate the treatment effect of APOE genotypes on Alzheimer's disease and as such represent a potential therapeutic target.

Monte Carlo cross-validation for a study with binary outcome and limited sample size

Cross-validation (CV) is a resampling approach to evaluate machine learning models when sample size is limited. The number of all possible combinations of folds for the training data, known as CV rounds, are often very small in leave-one-out CV. Alternatively, Monte Carlo cross-validation (MCCV) can be performed with a flexible number of simulations when computational resources are feasible for a study with limited sample size. We conduct extensive simulation studies to compare accuracy between MCCV and CV with the same number of simulations for a study with binary outcome (e.g., disease progression or not). Accuracy of MCCV is generally higher than CV although the gain is small. They have similar performance when sample size is large. Meanwhile, MCCV is going to provide reliable performance metrics as the number of simulations increases. Two real examples are used to illustrate the comparison between MCCV and CV.

Identifying patterns in amyotrophic lateral sclerosis progression from sparse longitudinal data

The clinical presentation of amyotrophic lateral sclerosis (ALS), a fatal neurodegenerative disease, varies widely across patients, making it challenging to determine if potential therapeutics slow progression. We sought to determine whether there were common patterns of disease progression that could aid in the design and analysis of clinical trials. We developed an approach based on a mixture of Gaussian processes to identify clusters of patients sharing similar disease progression patterns, modeling their average trajectories and the variability in each cluster. We show that ALS progression is frequently nonlinear, with periods of stable disease preceded or followed by rapid decline. We also show that our approach can be extended to Alzheimer's and Parkinson's diseases. Our results advance the characterization of disease progression of ALS and provide a flexible modeling approach that can be applied to other progressive diseases.

Reducing variations in multi-center Alzheimer's disease classification with convolutional adversarial autoencoder

Based on brain magnetic resonance imaging (MRI), multiple variations ranging from MRI scanners to center-specific parameter settings, imaging protocols, and brain region-of-interest (ROI) definitions pose a big challenge for multi-center Alzheimer's disease characterization and classification. Existing approaches to reduce such variations require intricate multi-step, often manual preprocessing pipelines, including skull stripping, segmentation, registration, cortical reconstruction, and ROI outlining. Such procedures are time-consuming, and more importantly, tend to be user biased. Contrasting costly and biased preprocessing pipelines, the question arises whether we can design a deep learning model to automatically reduce these variations from multiple centers for Alzheimer's disease classification? In this study, we used T1 and T2-weighted structural MRI from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset based on three groups with 375 subjects, respectively: patients with Alzheimer's disease (AD) dementia, with mild cognitive impairment (MCI), and healthy controls (HC); to test our approach, we defined AD classification as classifying an individual's structural image to one of the three group labels. We first introduced a convolutional adversarial autoencoder (CAAE) to reduce the variations existing in multi-center raw MRI scans by automatically registering them into a common aligned space. Afterward, a convolutional residual soft attention network (CRAT) was further proposed for AD classification. Canonical classification procedures demonstrated that our model achieved classification accuracies of 91.8%, 90.05%, and 88.10% for the 2-way classification tasks using the RAW aligned MRI scans, including AD vs. HC, AD vs. MCI, and MCI vs. HC, respectively. Thus, our automated approach achieves comparable or even better classification performance by comparing it with many baselines with dedicated conventional preprocessing pipelines. Furthermore, the uncovered brain hotpots, i.e., hippocampus, amygdala, and temporal pole, are consistent with previous studies.

Diagnosing Alzheimer's Disease Specifically and Sensitively With pLG72 and Cystine/Glutamate Antiporter SLC7A11 AS Blood Biomarkers

BACKGROUND

Reliable blood biomarkers for Alzheimer's disease (AD) have been lacking. The D-amino acids oxidase modulator (named pLG72) modulates glutamate N-methyl-D-aspartate receptor activity. The cystine/glutamate antiporter contains a SLC7A11 subunit, which mediates glutamate release. This study aimed to determine the accuracy of pLG72 protein and SLC7A11 mRNA in diagnosing AD.

METHODS

This study enrolled 130 healthy controls and 109 unmatched AD patients; among them, 40 controls and 70 patients were selected to match by age. We measured their pLG72 protein in plasma and SLC7A11 mRNA in white blood cells.

RESULTS

AD patients had markedly higher pLG72 levels and SLC7A11 mRNA ΔCT values than healthy controls (in both unmatched and matched cohorts; all 4 P values <.001). The receiver operating characteristics analysis in the unmatched cohorts demonstrated that the pLG72 level had a high specificity (0.900) at the optimal cutoff value of 2.3285, the ΔCT of SLC7A11 mRNA displayed an excellent sensitivity (0.954) at the cutoff of 12.185, and the combined value of pLG72 and SLC7A11 ΔCT determined a favorable area under the curve (AUC) (0.882) at the cutoff of 21.721. The AUC of the combined value surpassed that of either biomarker. The specificity, sensitivity, and AUC of the matched cohort were like those of the unmatched cohort.

CONCLUSIONS

The findings suggest that pLG72 protein and SLC7A11 mRNA can distinguish AD patients from healthy controls with excellent specificity and sensitivity, respectively. The combination of pLG72 and SLC7A11 yields better AUC than either, suggesting the superiority of simultaneously measuring both biomarkers in identifying AD patients.

A Pragmatic, Data-Driven Method to Determine Cutoffs for CSF Biomarkers of Alzheimer Disease Based on Validation Against PET Imaging

BACKGROUND AND OBJECTIVES

To elaborate a new algorithm to establish a standardized method to define cutoffs for CSF biomarkers of Alzheimer disease (AD) by validating the algorithm against CSF classification derived from PET imaging.

METHODS

Low and high levels of CSF phosphorylated tau were first identified to establish optimal cutoffs for CSF β-amyloid (Aβ) peptide biomarkers. These Aβ cutoffs were then used to determine cutoffs for CSF tau and phosphorylated tau markers. We compared this algorithm to a reference method, based on tau and amyloid PET imaging status (ADNI study), and then applied the algorithm to 10 large clinical cohorts of patients.

RESULTS

A total of 6,922 patients with CSF biomarker data were included (mean [SD] age: 70.6 [8.5] years, 51.0% women). In the ADNI study population (n = 497), the agreement between classification based on our algorithm and the one based on amyloid/tau PET imaging was high, with Cohen's kappa coefficient between 0.87 and 0.99. Applying the algorithm to 10 large cohorts of patients (n = 6,425), the proportion of persons with AD ranged from 25.9% to 43.5%.

DISCUSSION

The proposed novel, pragmatic method to determine CSF biomarker cutoffs for AD does not require assessment of other biomarkers or assumptions concerning the clinical diagnosis of patients. Use of this standardized algorithm is likely to reduce heterogeneity in AD classification.

Proteomic Discovery and Validation of Novel Fluid Biomarkers for Improved Patient Selection and Prediction of Clinical Outcomes in Alzheimer’s Disease Patient Cohorts

Alzheimer’s disease (AD) is an irreversible neurodegenerative disease characterized by progressive cognitive decline. The two cardinal neuropathological hallmarks of AD include the buildup of cerebral β amyloid (Aβ) plaques and neurofibrillary tangles of hyperphosphorylated tau. The current disease-modifying treatments are still not effective enough to lower the rate of cognitive decline. There is an urgent need to identify early detection and disease progression biomarkers that can facilitate AD drug development. The current established readouts based on the expression levels of amyloid beta, tau, and phospho-tau have shown many discrepancies in patient samples when linked to disease progression. There is an urgent need to identify diagnostic and disease progression biomarkers from blood, cerebrospinal fluid (CSF), or other biofluids that can facilitate the early detection of the disease and provide pharmacodynamic readouts for new drugs being tested in clinical trials. Advances in proteomic approaches using state-of-the-art mass spectrometry are now being increasingly applied to study AD disease mechanisms and identify drug targets and novel disease biomarkers. In this report, we describe the application of quantitative proteomic approaches for understanding AD pathophysiology, summarize the current knowledge gained from proteomic investigations of AD, and discuss the development and validation of new predictive and diagnostic disease biomarkers.

ADataViewer: exploring semantically harmonized Alzheimer's disease cohort datasets

BACKGROUND

Currently, Alzheimer's disease (AD) cohort datasets are difficult to find and lack across-cohort interoperability, and the actual content of publicly available datasets often only becomes clear to third-party researchers once data access has been granted. These aspects severely hinder the advancement of AD research through emerging data-driven approaches such as machine learning and artificial intelligence and bias current data-driven findings towards the few commonly used, well-explored AD cohorts. To achieve robust and generalizable results, validation across multiple datasets is crucial.

METHODS

We accessed and systematically investigated the content of 20 major AD cohort datasets at the data level. Both, a medical professional and a data specialist, manually curated and semantically harmonized the acquired datasets. Finally, we developed a platform that displays vital information about the available datasets.

RESULTS

Here, we present ADataViewer, an interactive platform that facilitates the exploration of 20 cohort datasets with respect to longitudinal follow-up, demographics, ethnoracial diversity, measured modalities, and statistical properties of individual variables. It allows researchers to quickly identify AD cohorts that meet user-specified requirements for discovery and validation studies regarding available variables, sample sizes, and longitudinal follow-up. Additionally, we publish the underlying variable mapping catalog that harmonizes 1196 unique variables across the 20 cohorts and paves the way for interoperable AD datasets.

CONCLUSIONS

In conclusion, ADataViewer facilitates fast, robust data-driven research by transparently displaying cohort dataset content and supporting researchers in selecting datasets that are suited for their envisioned study. The platform is available at https://adata.scai.fraunhofer.de/ .

Development of a mobile low-field MRI scanner

Magnetic resonance imaging (MRI) allows important visualization of the brain and central nervous system anatomy and organization. However, unlike electroencephalography (EEG) or functional near infrared spectroscopy, which can be brought to a patient or study participant, MRI remains a hospital or center-based modality. Low magnetic field strength MRI systems, however, offer the potential to extend beyond these traditional hospital and imaging center boundaries. Here we describe the development of a modified cargo van that incorporates a removable low-field permanent magnet MRI system and demonstrate its proof-of-concept. Using phantom scans and in vivo T₂-weighted neuroimaging data, we show no significant differences with respect to geometric distortion, signal-to-noise ratio, or tissue segmentation outcomes in data acquired in the mobile system compared to a similar static system in a laboratory setting. These encouraging results show, for the first time, MRI that can be performed at a participant’s home, community center, school, etc. Breaking traditional barriers of access, this mobile approach may enable imaging of patients and participants who have mobility challenges, live long distances from imaging centers, or are otherwise unable to travel to an imaging center or hospital.

Using the Alzheimer's Disease Neuroimaging Initiative to improve early detection, diagnosis, and treatment of Alzheimer's disease

INTRODUCTION

The Alzheimer's Disease Neuroimaging Initiative (ADNI) has accumulated 15 years of clinical, neuroimaging, cognitive, biofluid biomarker and genetic data, and biofluid samples available to researchers, resulting in more than 3500 publications. This review covers studies from 2018 to 2020.

METHODS

We identified 1442 publications using ADNI data by conventional search methods and selected impactful studies for inclusion.

RESULTS

Disease progression studies supported pivotal roles for regional amyloid beta (Aβ) and tau deposition, and identified underlying genetic contributions to Alzheimer's disease (AD). Vascular disease, immune response, inflammation, resilience, and sex modulated disease course. Biologically coherent subgroups were identified at all clinical stages. Practical algorithms and methodological changes improved determination of Aβ status. Plasma Aβ, phosphorylated tau181, and neurofilament light were promising noninvasive biomarkers. Prognostic and diagnostic models were externally validated in ADNI but studies are limited by lack of ethnocultural cohort diversity.

DISCUSSION

ADNI has had a profound impact in improving clinical trials for AD.

Graph-guided Bayesian SVM with Adaptive Structured Shrinkage Prior for High-dimensional Data

Support vector machine (SVM) is a popular classification method for the analysis of a wide range of data including big biomedical data. Many SVM methods with feature selection have been developed under the frequentist regularization or Bayesian shrinkage frameworks. On the other hand, the value of incorporating a priori known biological knowledge, such as those from functional genomics and functional proteomics, into statistical analysis of -omic data has been recognized in recent years. Such biological information is often represented by graphs. We propose a novel method that assigns Laplace priors to the regression coefficients and incorporates the underlying graph information via a hyper-prior for the shrinkage parameters in the Laplace priors. This enables smoothing of shrinkage parameters for connected variables in the graph and conditional independence between shrinkage parameters for disconnected variables. Extensive simulations demonstrate that our proposed methods achieve the best performance compared to the other existing SVM methods in terms of prediction accuracy. The proposed method are also illustrated in analysis of genomic data from cancer studies, demonstrating its advantage in generating biologically meaningful results and identifying potentially important features.

Large, open datasets for human connectomics research: Considerations for reproducible and responsible data use

Large, open datasets have emerged as important resources in the field of human connectomics. In this review, the evolution of data sharing involving magnetic resonance imaging is described. A summary of the challenges and progress in conducting reproducible data analyses is provided, including description of recent progress made in the development of community guidelines and recommendations, software and data management tools, and initiatives to enhance training and education. Finally, this review concludes with a discussion of ethical conduct relevant to analyses of large, open datasets and a researcher's responsibility to prevent further stigmatization of historically marginalized racial and ethnic groups. Moving forward, future work should include an enhanced emphasis on the social determinants of health, which may further contextualize findings among diverse population-based samples. Leveraging the progress to date and guided by interdisciplinary collaborations, the future of connectomics promises to be an impressive era of innovative research, yielding a more inclusive understanding of brain structure and function.

Recommendations to Optimize the Use of Volumetric MRI in Huntington's Disease Clinical Trials

Volumetric magnetic resonance imaging (vMRI) has been widely studied in Huntington's disease (HD) and is commonly used to assess treatment effects on brain atrophy in interventional trials. Global and regional trajectories of brain atrophy in HD, with early involvement of striatal regions, are becoming increasingly understood. However, there remains heterogeneity in the methods used and a lack of widely-accessible multisite, longitudinal, normative datasets in HD. Consensus for standardized practices for data acquisition, analysis, sharing, and reporting will strengthen the interpretation of vMRI results and facilitate their adoption as part of a pathobiological disease staging system. The Huntington's Disease Regulatory Science Consortium (HD-RSC) currently comprises 37 member organizations and is dedicated to building a regulatory science strategy to expedite the approval of HD therapeutics. Here, we propose four recommendations to address vMRI standardization in HD research: (1) a checklist of standardized practices for the use of vMRI in clinical research and for reporting results; (2) targeted research projects to evaluate advanced vMRI methodologies in HD; (3) the definition of standard MRI-based anatomical boundaries for key brain structures in HD, plus the creation of a standard reference dataset to benchmark vMRI data analysis methods; and (4) broad access to raw images and derived data from both observational studies and interventional trials, coded to protect participant identity. In concert, these recommendations will enable a better understanding of disease progression and increase confidence in the use of vMRI for drug development.

Alzheimer's Disease Classification Accuracy is Improved by MRI Harmonization based on Attention-Guided Generative Adversarial Networks

Alzheimer's disease (AD) accounts for 60% of dementia cases worldwide; patients with the disease typically suffer from irreversible memory loss and progressive decline in multiple cognitive domains. With brain imaging techniques such as magnetic resonance imaging (MRI), microscopic brain changes are detectable even before abnormal memory loss is detected clinically. Patterns of brain atrophy can be measured using MRI, which gives us an opportunity to facilitate AD detection using image classification techniques. Even so, MRI scanning protocols and scanners differ across studies. The resulting differences in image contrast and signal to noise make it important to train and test classification models on multiple datasets, and to handle shifts in image characteristics across protocols (also known as domain transfer or domain adaptation). Here, we examined whether adversarial domain adaptation can boost the performance of a Convolutional Neural Network (CNN) model designed to classify AD. To test this, we used an Attention-Guided Generative Adversarial Network (GAN) to harmonize images from three publicly available brain MRI datasets - ADNI, AIBL and OASIS - adjusting for scanner-dependent effects. Our AG-GAN optimized a joint objective function that included attention loss, pixel loss, cycle-consistency loss and adversarial loss; the model was trained bidirectionally in an end-to-end fashion. For AD classification, we adapted the popular 2D AlexNet CNN to handle 3D images. Classification based on harmonized MR images significantly outperformed classification based on the three datasets in non-harmonized form, motivating further work on image harmonization using adversarial techniques.

Brain atrophy trajectories predict differential functional performance in Alzheimer's disease: Moderations with apolipoprotein E and sex

INTRODUCTION

We examine whether distinct brain atrophy patterns (using brain parenchymal fraction [BPF]) differentially predict functional performance and decline in Alzheimer's disease (AD), and are independently moderated by (1) a key AD genetic risk marker (apolipoprotein E [APOE]), (2) sex, and (3) high-risk group (women APOE ɛ4 carriers).

METHODS

We used a 2-year longitudinal sample of AD patients (baseline N = 170; mean age = 71.3 [9.1] years) from the Sunnybrook Dementia Study. We applied latent class analysis, latent growth modeling, and path analysis. We aimed to replicate our findings (N = 184) in the Alzheimer's Disease Neuroimaging Initiative.

RESULTS

We observed that high brain atrophy class predicted lower functional performance and steeper decline. This association was moderated by APOE, sex, and high-risk group. Baseline findings as moderated by APOE and high-risk group were replicated.

DISCUSSION

Women APOE ɛ4 carriers may selectively be at a greater risk of functional impairment with higher brain atrophy.

Robust Discovery of Mild Cognitive Impairment Subtypes and Their Risk of Alzheimer's Disease Conversion Using Unsupervised Machine Learning and Gaussian Mixture Modeling

BACKGROUND

Alzheimer's Disease (AD) is an irreversible, progressive brain disorder that slowly destroys memory and thinking skills. The ability to correctly predict the diagnosis of Alzheimer's disease in its earliest stages can help physicians make more informed clinical decisions on therapy plans.

OBJECTIVE

This study aimed to determine whether the unsupervised discovering of latent classes of subjects with Mild Cognitive Impairment (MCI) may be useful in finding different prodromal AD stages and/or subjects with a low MCI to AD conversion risk.

METHODS

Total 18 features relevant to the MCI to AD conversion process led to the identification of 681 subjects with early MCI. Subjects were divided into training (70%) and validation (30%) sets. Subjects from the training set were analyzed using consensus clustering, and Gaussian Mixture Models (GMM) were used to describe the latent classes. The discovered GMM predicted the latent class of the validation set. Finally, descriptive statistics, rates of conversion, and Odds Ratios (OR) were computed for each discovered class.

RESULTS

Through consensus clustering, we discovered three different clusters among MCI subjects. The three clusters were associated with low-risk (OR = 0.12, 95%CI = 0.04 to 0.3|), medium-risk (OR = 1.33, 95%CI = 0.75 to 2.37), and high-risk (OR = 3.02, 95%CI = 1.64 to 5.57) of converting from MCI to AD, with the high-risk and low-risk groups highly contrasting. Hence, prodromal AD subjects were present in only two clusters.

CONCLUSION

We successfully discovered three different latent classes among MCI subjects with varied risks of MCI-to-AD conversion through consensus clustering. Two of the discovered classes may represent two different prodromal presentations of Alzheimer´s disease.

Targeting autonomic flexibility to enhance cognitive training outcomes in older adults with mild cognitive impairment: study protocol for a randomized controlled trial

Importance

Cognitive training with components that can further enhance the transferred and long-term effects and slow the progress of dementia is needed for preventing dementia.

Objective

The goal of the study is to test whether improving autonomic nervous system (ANS) flexibility via a resonance frequency breathing (RFB) training will strengthen the effects of a visual speed of processing (VSOP) cognitive training on cognitive and brain function, and slow the progress of dementia in older adults with mild cognitive impairment (MCI).

Design

Stage II double-blinded randomized controlled trial. The study was prospectively registered at ClinicalTrials.gov, with registration approved on 21 August 2020 (No. NCT04522791).

Setting

Study-related appointments will be conducted on-site at University of Rochester Medical Center locations. Data collection will be conducted from August 2020 to February 2025.

Participants

Older adults with MCI (n = 114) will be randomly assigned to an 8-week combined intervention (RFB+VSOP), VSOP with guided imagery relaxation (IR) control, and a IR-only control, with periodical booster training sessions at follow-ups. Mechanistic and distal outcomes include ANS flexibility, measured by heart rate variability, and multiple markers of dementia progress. Data will be collected across a 14-month period.

Discussion

This will be among the first RCTs to examine in older persons with MCI a novel, combined intervention targeting ANS flexibility, an important contributor to overall environmental adaptation, with an ultimate goal for slowing neurodegeneration.

Trial registration

ClinicalTrials.gov NCT04522791. Registered on 21 August 2020

Protocol version: STUDY00004727; IRB protocol version 2, approved on 30 July 2020.

Development and evaluation of [18F]Flotaza for Aβ plaque imaging in postmortem human Alzheimer's disease brain

Positron emission tomographic (PET) studies of amyloid β (Aβ) accumulation in Alzheimer's disease (AD) have shown clinical utility. The aim of this study was to develop and evaluate the effectiveness of a new fluorine-18 radiotracer [18F]Flotaza (2-{2-[2-[18F]fluoroethoxy]ethoxy}ethoxy)-4'-N,N-dimethylaminoazobenzene), for Aβ plaque imaging. Nucleophilic [18F]fluoride was used in a one-step radiosynthesis for [18F]flotaza. Using post mortem human AD brain tissues consisting of anterior cingulate (AC) and corpus callosum (CC), binding affinity of Flotaza, Ki = 1.68 nM for human Aβ plaques and weak (>10-5 M) for Tau protein. Radiosynthesis of [18F]Flotaza was very efficient in high radiochemical yields (>25%) with specific activities >74 GBq/μmol. Brain slices from all AD subjects were positively immunostained with anti-Aβ. Ratio of [18F]Flotaza in gray matter AC to white matter CC was >100 in all the 6 subjects. Very little white matter binding was seen. [18F]Flotaza binding in AC strongly correlated with anti-Aβ immunostains. [18F]Flotaza is therefore a suitable fluorine-18 PET radiotracer for PET imaging studies of human Aβ plaques.

Unsupervised Machine Learning to Identify Separable Clinical Alzheimer's Disease Sub-Populations

Heterogeneity among Alzheimer's disease (AD) patients confounds clinical trial patient selection and therapeutic efficacy evaluation. This work defines separable AD clinical sub-populations using unsupervised machine learning. Clustering (t-SNE followed by k-means) of patient features and association rule mining (ARM) was performed on the ADNIMERGE dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Patient sociodemographics, brain imaging, biomarkers, cognitive tests, and medication usage were included for analysis. Four AD clinical sub-populations were identified using between-cluster mean fold changes [cognitive performance, brain volume]: cluster-1 represented least severe disease [+17.3, +13.3]; cluster-0 [-4.6, +3.8] and cluster-3 [+10.8, -4.9] represented mid-severity sub-populations; cluster-2 represented most severe disease [-18.4, -8.4]. ARM assessed frequently occurring pharmacologic substances within the 4 sub-populations. No drug class was associated with the least severe AD (cluster-1), likely due to lesser antecedent disease. Anti-hyperlipidemia drugs associated with cluster-0 (mid-severity, higher volume). Interestingly, antioxidants vitamin C and E associated with cluster-3 (mid-severity, higher cognition). Anti-depressants like Zoloft associated with most severe disease (cluster-2). Vitamin D is protective for AD, but ARM identified significant underutilization across all AD sub-populations. Identification and feature characterization of four distinct AD sub-population "clusters" using standard clinical features enhances future clinical trial selection criteria and cross-study comparative analysis.

Association between Alzheimer's disease genes and trajectories of cognitive function decline in Han Chinese in Taiwan

Genetic background has been considered one of the important contributors to the rate of cognitive decline among patients with Alzheimer’s disease (AD). We conducted a 4-year longitudinal follow-up study, recruited 255 AD and 44 mild cognitive impairment (MCI) patients, and used a data-driven trajectory analysis to examine the influence of selected AD risk genes on the age for and the rate of cognitive decline in Han Chinese population. Genotyping of selected single-nucleotide polymorphisms in the APOE, ABCA7, SORL1, BIN1, GAB2, and CD33 genes was conducted, and a Bayesian hierarchical model was fitted to analyze the trajectories of cognitive decline among different genotypes. After adjusting for sex and education years, the APOE ε4 allele was associated with an earlier mean change of −2.39 years in the age at midpoint of cognitive decline, the G allele in ABCA7 rs3764650 was associated with an earlier mean change of −1.75 years, and the T allele in SORL1 rs3737529 was associated with a later mean change of 2.6 years. Additionally, the rate of cognitive decline was associated with the APOE ε4 allele and SORL1 rs3737529. In summary, APOE and SORL1 might be the most important genetic factors related to cognitive decline in Han Chinese population.

Interplay between stress-related genes may influence Alzheimer's disease development: The results of genetic interaction analyses of human data

Emerging evidence from experimental and clinical research suggests that stress-related genes may play key roles in AD development. The fact that genome-wide association studies were not able to detect a contribution of such genes to AD indicates the possibility that these genes may influence AD non-linearly, through interactions of their products. In this paper, we selected two stress-related genes (GCN2/EIF2AK4 and APP) based on recent findings from experimental studies which suggest that the interplay between these genes might influence AD in humans. To test this hypothesis, we evaluated the effects of interactions between SNPs in these two genes on AD occurrence, using the Health and Retirement Study data on white indidividuals. We found several interacting SNP-pairs whose associations with AD remained statistically significant after correction for multiple testing. These findings emphasize the importance of nonlinear mechanisms of polygenic AD regulation that cannot be detected in traditional association studies. To estimate collective effects of multiple interacting SNP-pairs on AD, we constructed a new composite index, called Interaction Polygenic Risk Score, and showed that its association with AD is highly statistically significant. These results open a new avenue in the analyses of mechanisms of complex multigenic AD regulation.

Neuroimaging Biomarkers in Schizophrenia

Schizophrenia is a complex neuropsychiatric syndrome with a heterogeneous genetic, neurobiological, and phenotypic profile. Currently, no objective biological measures-that is, biomarkers-are available to inform diagnostic or treatment decisions. Neuroimaging is well positioned for biomarker development in schizophrenia, as it may capture phenotypic variations in molecular and cellular disease targets, or in brain circuits. These mechanistically based biomarkers may represent a direct measure of the pathophysiological underpinnings of the disease process and thus could serve as true intermediate or surrogate endpoints. Effective biomarkers could validate new treatment targets or pathways, predict response, aid in selection of patients for therapy, determine treatment regimens, and provide a rationale for personalized treatments. In this review, the authors discuss a range of mechanistically plausible neuroimaging biomarker candidates, including dopamine hyperactivity, N-methyl-d-aspartate receptor hypofunction, hippocampal hyperactivity, immune dysregulation, dysconnectivity, and cortical gray matter volume loss. They then focus on the putative neuroimaging biomarkers for disease risk, diagnosis, target engagement, and treatment response in schizophrenia. Finally, they highlight areas of unmet need and discuss strategies to advance biomarker development.

Multi-scale modeling for systematically understanding the key roles of microglia in AD development

Alzheimer's disease (AD) is the leading cause of age-related dementia, affecting over 5 million people in the United States. Unfortunately, current therapies are largely palliative and several potential drug candidates have failed in late-stage clinical trials. Studies suggest that microglia-mediated neuroinflammation might be responsible for the failures of various therapies. Microglia contribute to Aβ clearance in the early stage of neurodegeneration and may contribute to AD development at the late stage by releasing pro-inflammatory cytokines. However, the activation profile and phenotypic changes of microglia during the development of AD are poorly understood. To systematically understand the key role of microglia in AD progression and predict the optimal therapeutic strategy in silico, we developed a 3D multi-scale model of AD (MSMAD) by integrating multi-level experimental data, to manipulate the neurodegeneration in a simulated system. Based on our analysis, we revealed that how TREM2-related signal transduction leads to an imbalance in the activation of different microglia phenotypes, thereby promoting AD development. Our MSMAD model also provides an optimal therapeutic strategy for improving the outcome of AD treatment.

Evolution of the Research Literature and the Scientific Community of Alzheimer's Disease from 1983-2017: A 35-Year Survey

This study surveys the development of Alzheimer's disease (AD) in the research literature, the scientific community, and the journals containing AD papers over a 35-year period. Research papers on AD published from 1983 to 2017 in journals indexed in the Web of Science were analyzed in seven five-year periods. The number of AD papers increased from 1,095 in 1983-1987 to 50,532 by 2013-2017 and in the same time period, the number of participating countries went from 27 to 152. The US was the most prolific country throughout, followed by several European countries, Canada, Australia, and Japan. Asian countries have emerged and by 2013-2017, China surpassed all but the US in productivity. Countries in Latin America and Africa have also contributed to AD research. Additionally, several new non-governmental institutions (e.g., ADNI, ADI) have emerged and now play a key role in the fight against AD. Likewise the AD scientific publishing universe evolved in various aspects: an increase in number of journals containing AD papers (227 journals in 1983-1987 to 3,257 in 2013-2017); appearance of several AD-focused journals, e.g., Alzheimer's & Dementia, Journal of Alzheimer's Disease; and the development of special issues dedicated to AD. Our paper complements the numerous extant papers on theoretical and clinical aspects of AD and provides a description of the research landscape of the countries and journals contributing papers related to AD.

Coordinating Global Multi-Site Studies of Military-Relevant Traumatic Brain Injury: Opportunities, Challenges, and Harmonization Guidelines

Traumatic brain injury (TBI) is common among military personnel and the civilian population and is often followed by a heterogeneous array of clinical, cognitive, behavioral, mood, and neuroimaging changes. Unlike many neurological disorders that have a characteristic abnormal central neurologic area(s) of abnormality pathognomonic to the disorder, a sufficient head impact may cause focal, multifocal, diffuse or combination of injury to the brain. This inconsistent presentation makes it difficult to establish or validate biological and imaging markers that could help improve diagnostic and prognostic accuracy in this patient population. The purpose of this manuscript is to describe both the challenges and opportunities when conducting military-relevant TBI research and introduce the Enhancing NeuroImaging Genetics through Meta-Analysis (ENIGMA) Military Brain Injury working group. ENIGMA is a worldwide consortium focused on improving replicability and analytical power through data sharing and collaboration. In this paper, we discuss challenges affecting efforts to aggregate data in this patient group. In addition, we highlight how "big data" approaches might be used to understand better the role that each of these variables might play in the imaging and functional phenotypes of TBI in Service member and Veteran populations, and how data may be used to examine important military specific issues such as return to duty, the late effects of combat-related injury, and alteration of the natural aging processes.