Alzheimer's Disease Neuroimaging Initiative Data Research Articles

Brain magnetic resonance imaging image classification for Alzheimer's disease and its hardware acceleration

<span lang="EN-US">Alzheimer's is a progressive neurodegenerative disorder and is considered the sixth leading cause of death after cancer and heart attack. Early detection and diagnosis provide individuals to go through a wider variety of clinical trials and get multiple medical benefits. Research on the application of deep learning and machine learning to the early detection of Alzheimer's disease has recently gained considerable attention. In this paper, we propose a deep learning classification framework to classify the individual with different progression stages of Alzheimer's disease such as mild cognitive impairment (MCI) and cognitive normal (CN). The dataset from Alzheimer’s disease neuroimaging initiative (ADNI) is considered in this paper which is a multisite having collection of Neuroimaging data for researchers. Structural magnetic resonance imaging (MRI) images are considered from the ADNI data set and feature extraction is done using a 2D discrete wavelet transform. 97% of data reduction is achieved during data pre-processing. The algorithm is trained and validated. The algorithm is accelerated in Nvidia Tx2 graphics processing unit (GPU) to get the better throughput. The result shows our algorithm outperforms the other deep learning algorithms with 91.56% accuracy. </span>

Mapping of Alzheimer’s disease related data elements and the NIH Common Data Elements

BackgroundAlzheimer’s Disease (AD) is a devastating disease that destroys memory and other cognitive functions. There has been an increasing research effort to prevent and treat AD. In the US, two major data sharing resources for AD research are the National Alzheimer’s Coordinating Center (NACC) and the Alzheimer’s Disease Neuroimaging Initiative (ADNI); Additionally, the National Institutes of Health (NIH) Common Data Elements (CDE) Repository has been developed to facilitate data sharing and improve the interoperability among data sets in various disease research areas.MethodTo better understand how AD-related data elements in these resources are interoperable with each other, we leverage different representation models to map data elements from different resources: NACC to ADNI, NACC to NIH CDE, and ADNI to NIH CDE. We explore bag-of-words based and word embeddings based models (Word2Vec and BioWordVec) to perform the data element mappings in these resources.ResultsThe data dictionaries downloaded on November 23, 2021 contain 1,195 data elements in NACC, 13,918 in ADNI, and 27,213 in NIH CDE Repository. Data element preprocessing reduced the numbers of NACC and ADNI data elements for mapping to 1,099 and 7,584 respectively. Manual evaluation of the mapping results showed that the bag-of-words based approach achieved the best precision, while the BioWordVec based approach attained the best recall. In total, the three approaches mapped 175 out of 1,099 (15.92%) NACC data elements to ADNI; 107 out of 1,099 (9.74%) NACC data elements to NIH CDE; and 171 out of 7,584 (2.25%) ADNI data elements to NIH CDE.ConclusionsThe bag-of-words based and word embeddings based approaches showed promise in mapping AD-related data elements between different resources. Although the mapping approaches need further improvement, our result indicates that there is a critical need to standardize CDEs across these valuable AD research resources in order to maximize the discoveries regarding AD pathophysiology, diagnosis, and treatment that can be gleaned from them.

Genetic heterogeneity of Alzheimer’s disease: Evidence for disease‐relevant and disease‐specific clustering

AbstractBackgroundAlzheimer’s disease (AD) demonstrates heterogeneity across domains of cognitive impairment, atrophy, and pathological accumulation. This has led to speculations that AD may comprise several disease subtypes. AD is under substantial genetic influence, thus searching for genetic clustering may provide insight towards the origins of this phenotypic variability.MethodGenotyping data from 2,739 AD cases and 5,478 age and sex‐matched controls from the UK Biobank were used as the discovery data. A principal components analysis (PCA) was applied to AD‐associated variants (p<0.05 in the IGAPS2 GWAS of AD) to assess disease‐relevant structure. A novel biclustering algorithm was then applied to find disease‐specific genetic signatures of AD. This algorithm searches for subsets of subjects and variants that are present in cases, but importantly, not in controls. Pathway analysis was used to characterize the biological pathways implicated by disease‐relevant and specific clustering. Data from 476 AD cases and 591 controls from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) were used to test replication of clusters.ResultPCA revealed 3 distinct clusters. Each cluster contained a mix of cases and controls but these clusters only became apparent when restricting to AD‐associated variants, suggesting disease‐relevant structure. Examining clusters separately, we found 2 significant disease‐specific biclusters comprising sets of variants found more frequently in a subset of AD cases than in controls. When projecting ADNI data on UK Biobank principal components, there was almost perfect overlap of disease‐relevant clusters. Disease‐specific biclusters significantly replicated (p<0.05) across a range of parameter choices.ConclusionThese findings demonstrate a hierarchy of heterogeneity for AD genetic risk. At the first level, the three disease‐relevant clusters may indicate that different pathways are more vulnerable for different groups of individuals, but additional risk factors or insults are required to substantially increase risk for AD. At the next level, individuals assigned to the biclusters may represent subtypes of AD with different genetic signatures that significantly increase risk for AD. Replication in ADNI demonstrates that this hierarchical structure is a generalizable aspect of AD genetic risk. More broadly, this study illustrates an approach that can be extended to investigate genetic heterogeneity of other complex diseases.

An ontology-based approach for modelling and querying Alzheimer’s disease data

BackgroundThe recent advances in biotechnology and computer science have led to an ever-increasing availability of public biomedical data distributed in large databases worldwide. However, these data collections are far from being “standardized” so to be harmonized or even integrated, making it impossible to fully exploit the latest machine learning technologies for the analysis of data themselves. Hence, facing this huge flow of biomedical data is a challenging task for researchers and clinicians due to their complexity and high heterogeneity. This is the case of neurodegenerative diseases and the Alzheimer’s Disease (AD) in whose context specialized data collections such as the one by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) are maintained.MethodsOntologies are controlled vocabularies that allow the semantics of data and their relationships in a given domain to be represented. They are often exploited to aid knowledge and data management in healthcare research. Computational Ontologies are the result of the combination of data management systems and traditional ontologies. Our approach is i) to define a computational ontology representing a logic-based formal conceptual model of the ADNI data collection and ii) to provide a means for populating the ontology with the actual data in the Alzheimer Disease Neuroimaging Initiative (ADNI). These two components make it possible to semantically query the ADNI database in order to support data extraction in a more intuitive manner.ResultsWe developed: i) a detailed computational ontology for clinical multimodal datasets from the ADNI repository in order to simplify the access to these data; ii) a means for populating this ontology with the actual ADNI data. Such computational ontology immediately makes it possible to facilitate complex queries to the ADNI files, obtaining new diagnostic knowledge about Alzheimer’s disease.ConclusionsThe proposed ontology will improve the access to the ADNI dataset, allowing queries to extract multivariate datasets to perform multidimensional and longitudinal statistical analyses. Moreover, the proposed ontology can be a candidate for supporting the design and implementation of new information systems for the collection and management of AD data and metadata, and for being a reference point for harmonizing or integrating data residing in different sources.

An ontology-based approach for harmonization and cross-cohort query of Alzheimer’s disease data resources

BackgroundIn the United States, the National Alzheimer’s Coordinating Center (NACC) and the Alzheimer’s Disease Neuroimaging Initiative (ADNI) are two major data sharing resources for Alzheimer’s Disease (AD) research. NACC and ADNI strive to make their data more FAIR (findable, interoperable, accessible and reusable) for the broader research community. However, there is limited work harmonizing and supporting cross-cohort interoperability of the two resources.MethodIn this paper, we leverage an ontology-based approach to harmonize data elements in the two resources and develop a web-based query system to search patient cohorts across the two resources. We first mapped data elements across NACC and ADNI, and performed value harmonization for the mapped data elements with inconsistent permissible values. Then we built an Alzheimer’s Disease Data Element Ontology (ADEO) to model the mapped data elements in NACC and ADNI. We further developed a prototype cross-cohort query system to search patient cohorts across NACC and ADNI.ResultsAfter manual review, we found 172 mappings between NACC and ADNI. These 172 mappings were further used to construct common concepts in ADEO. Our data element mapping and harmonization resulted in five files storing common concepts, variables in NACC and ADNI, mappings between variables and common concepts, permissible values of categorical type data elements, and coding inconsistency harmonization, respectively. Our cross-cohort query system consists of three core architectural elements: a web-based interface, an advanced query engine, and a backend MongoDB database.ConclusionsIn this work, ADEO has been specifically designed to facilitate data harmonization and cross-cohort query of NACC and ADNI data resources. Although our prototype cross-cohort query system was developed for exploring NACC and ADNI, its backend and frontend framework has been designed and implemented to be generally applicable to other domains for querying patient cohorts from multiple heterogeneous data sources.

Federated Deep Learning for Detecting Alzheimer’s Disease in Multi‐Cohort Brain MRI

AbstractBackgroundDeep learning shows promise in detecting Alzheimer’s Disease (AD) based on brain MRI1. Models trained on limited samples may fail when applied to new datasets (other cohorts, scanners), but privacy concerns make it difficult to centralize large amounts of data2. To address this, we developed a general federated learning architecture3, which we applied to train a 3D convolutional neural network (CNN) to detect AD from T1‐weighted brain MRI data from the three independently collected phases of the Alzheimer’s Disease Neuroimaging Initiative (ADNI).MethodWe trained a 3D‐CNN over a federated learning environment of 3 sites corresponding to each ADNI phases (ADNI1, ADNI2/GO, ADNI3). No subject data are shared across sites, only model parameters, thus satisfying privacy/regulatory requirements. Each site trains the model on its own local dataset for several epochs and shares only the locally‐trained parameters with a central server. The server aggregates the parameters and computes the global model, which is sent back to each learner, and the process repeats.We trained each learner for 4 local epochs in between federation rounds for a total number of 25 rounds. We divided each ADNI dataset into training, validation and test sets with distribution 70/20/10% (Figure 1). We also compared the performance of training our CNN models with random initialization versus using pre‐trained weights from a UK Biobank MRI sex classification task.ResultTable 2 shows the accuracy, precision, recall and F1 scores for our federated CNN, compared to a centralized model that was trained over all ADNI data. All models achieved excellent performance for classifying AD (96‐98%). Overall, the federated model with pretrained weights performed best. Pre‐training boosted accuracy for the federated, but not the centralized, case.ConclusionFederated learning achieves high performance in AD prediction from MRI and promises new applications in neuroimaging.[1] Lu et al. A Practical Alzheimer Disease Classifier via Brain Imaging‐Based Deep Learning on 85,721 Samples. bioRxiv 2020_08_18_256594. 2021[2] Ming et al. COINSTAC: Decentralizing the future of brain imaging analysis. F1000Research 6:1512, 2017.[3] Stripelis et al. Scaling Neuroscience Research using Federated Learning. ISBI 2021.

E.4 Hippocampal subfield thickness measurements evaluated using HippUnfold in patients with mild cognitive impairment and Alzheimer’s disease

Background: Alzheimer’s disease (AD) is an emerging public health crisis and biomarkers are playing a large role in AD research. Magnetic Resonance Imaging (MRI) holds advantages over existing biomarkers for AD. This project aims to measure subfield thickness throughout the hippocampal long axis using HippUnfold, a novel open-source automated hippocampal segmentation software. Methods: High resolution (0.39×0.39×2mm) Hippocampal MR Images [control, n= 16, mild cognitive impairment (MCI, n =16), and AD, (n = 16)] acquired by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) were analyzed with an automated segmentation software (HippUnfold) to compute thickness measurements. ADNI data such as Positron Emission Tomography (PET) biomarkers, Cerebrospinal Fluid biomarkers, and cognitive scores such as Mini-Mental State Exam (MMSE), Montreal Cognitive Assessment (MoCA), Alzheimer’s Disease Assessment Scale (ADAS13), and Rey Auditory Verbal Learning Test (RAVLT), were correlated to thickness along the hippocampal long axis using linear regression models. Results: We found significant cluster correlations (p < 0.05) throughout the long axis between hippocampal subfield thickness to MoCA scores, ADAS13 scores, PET phosphorylated tau levels, and PET beta-amyloid levels. Conclusions: Subfield atrophy throughout the hippocampal long axis is associated with disease severity (as measured with existing biomarkers and cognitive testing) in patients with MCI and AD.

Problems using structural MRIs from the oldest‐old, and some solutions: Lessons learned from The 90+ Study and ADNI

AbstractBackgroundThe oldest‐old (≥85 years) have the highest rates of dementia. However, because of pronounced brain atrophy, standard neuroimaging programs face unique challenges in this cohort. Here, using data from both The 90+ Study and Alzheimer’s Disease Neuroimaging Initiative (ADNI), we report the prevalence of errors when processing brain MRIs from oldest‐old participants using standard approaches and present some strategies for ameliorating these issues.MethodFirst, we analyzed image quality issues and segmentation errors (FreeSurfer) for the last available scans by age‐groups (oldest‐old, ≥85 years, vs younger‐old, <85 years) in ADNI. Second, we evaluated the utility of an age‐specific template (the 90+ T1w Template) for realigning MRIs from the oldest‐old compared to a standard template (Montreal Neurological Institute T1w template, MNI) using linear and nonlinear registration (FSL) and evaluating alignment quality using visual and deformation (Jacobian) measures for oldest‐old participants in both The 90+ Study and ADNI. Lastly, we evaluated whether stringent preprocessing (bias field removal, denoising, brain extraction, intensity normalization using Computational Anatomy Toolbox (CAT12)) helped reduce FreeSurfer segmentation errors in frontal, parietal, and temporal regions in MRIs from the oldest‐old. Comparisons were performed using Chi‐square tests.ResultIn ADNI data (Table‐1), MRIs from oldest‐old participants (∼10% of cohort) were around twice as likely to have image quality issues (20% vs 13%, P<0.001) and brain segmentation errors (45% vs 29%, P<0.001) compared to younger‐old participants. Figure‐1 shows a histogram of image quality issues and segmentation errors, which become more common with greater age. Compared to the MNI template, MRIs from participants aged 90 and older from both The 90+ Study (N=163, Table‐2) and ADNI (N=75) had fewer registration errors (∼5% vs ∼23%, P<0.001 for all) and less severe deformation when using the 90+ T1w Template (Figure‐2). Our proposed preprocessing pipeline (see Figure‐3 for example) roughly halved segmentation errors in the oldest‐old (P<0.001 for all regions, Figure‐4).ConclusionOur results show that adapting pipelines specifically for processing brain MRIs of oldest‐old participants minimizes errors, enabling more effective use of neuroimaging to study neural correlates of neurodegeneration and dementia in this important portion of our aging population.

Problems using structural MRIs from the oldest‐old, and some solutions: Lessons learned from The 90+ Study and ADNI

AbstractBackgroundThe oldest‐old (≥85 years) have the highest rates of dementia. However, because of pronounced brain atrophy, standard neuroimaging programs face unique challenges in this cohort. Here, using data from both The 90+ Study and Alzheimer’s Disease Neuroimaging Initiative (ADNI), we report the prevalence of errors when processing brain MRIs from oldest‐old participants using standard approaches and present some strategies for ameliorating these issues.MethodFirst, we analyzed image quality issues and segmentation errors (FreeSurfer) for the last available scans by age‐groups (oldest‐old, ≥85 years, vs younger‐old, 55 to 85 years) in ADNI. Second, we evaluated the utility of an age‐specific template (the 90+ T1w Template) for realigning MRIs from the oldest‐old compared to a standard template (Montreal Neurological Institute T1w template, MNI) using linear and nonlinear registration (FSL) and evaluating alignment quality using visual and deformation (Jacobian) measures for oldest‐old participants (≥90 years) in both The 90+ Study and ADNI. Lastly, we evaluated whether stringent preprocessing (bias field removal, denoising, brain extraction, intensity normalization using Computational Anatomy Toolbox (CAT12)) helped reduce FreeSurfer segmentation errors in frontal, parietal, and temporal regions in MRIs from the oldest‐old. Comparisons were performed using Chi‐square tests.ResultIn ADNI data (Table‐1), MRIs from oldest‐old participants (∼10% of cohort) were around twice as likely to have image quality issues (20% vs 13%, P<0.001) and brain segmentation errors (45% vs 29%, P<0.001) compared to younger‐old participants. Figure‐1 shows a histogram of image quality issues and segmentation errors, which become more common with greater age. Compared to the MNI template, MRIs from participants aged 90 and older from both The 90+ Study (N=163, Table‐2) and ADNI (N=75) had fewer registration errors (∼5% vs ∼23%, P<0.001 for all) and less severe deformation when using the 90+ T1w Template (Figure‐2). Our proposed preprocessing pipeline (see Figure‐3 for example) roughly halved segmentation errors in the oldest‐old (P<0.001 for all regions, Figure‐4).ConclusionOur results show that adapting pipelines specifically for processing brain MRIs of oldest‐old participants minimizes errors, enabling more effective use of neuroimaging to study neural correlates of neurodegeneration and dementia in this important portion of our aging population.

Crop Filling: artefact removal for real‐world clinical neuroimaging data

AbstractBackgroundThe use of standard clinical neuroimaging data for quantitative research is often precluded by imaging artefacts caused by real‐world limitations. For example, partial coverage (cropping) of T1‐weighted MRI scans can occur when a memory clinic prioritises visual ratings on T2‐weighted MRI, and so the T1 scan field‐of‐view is reduced to minimise the overall acquisition time. This study investigated cropping‐induced biases in T1‐MRI volumetric measurements and proposed and validated a solution.MethodThis study involved 1.5T T1‐weighted and T2‐weighted MRI data from 577 participants in the Alzheimer’s Disease Neuroimaging Initiative (ADNI): 173 cognitively normal (CN); 262 mild cognitive impairment (MCI); 114 probable Alzheimer’s disease dementia (AD). The ADNI data was preprocessed to resemble clinical data seen in the CODEC dataset from the Essex Memory Clinic in the UK. The T1w scans were artificially cropped to a field of view of 120mm laterally. The T2w scans were down‐sampled to have axial slice thickness of 5mm. FreeSurfer’s synthSR tool was used to synthesize a super‐resolved T1wSR from the down‐sampled T2w. The T1wSR image was registered to the cropped T1w using mri_robust_registration, with the data from the T1wSR used to fill the missing voxels in the cropped image. FreeSurfer’s recon‐all tool was used to estimate regional brain volumes in cropped , crop‐filled and original T1w images, with results compared using Bland‐Altman analysis, R2 correlation metric, and T‐test between original and cropped/crop‐filled values.ResultFigure 1 shows an example T1w from ADNI (coronal/axial view, AD patient): original (top); artificially cropped (centre); crop‐filled (bottom). Table 1 shows groupwise demographics of the ADNI participants and overall experimental results. Figure 2‐5 shows Bland‐Altman plots and R2 correlation metric for the volumes of three AD‐relevant brain regions: hippocampus, middle temporal gyrus, and ventricles. Results suggest that the proposed crop‐filling solution works well: low percentage bias (<1% crop‐filled; ∼2% cropped), high correlation (R2∼0.9 crop‐filled; ∼0.85 cropped).ConclusionThe new crop‐filling methodology was effective at removing this specific artefact seen in clinical neuroimaging data. This is an important step towards making real‐world neuroimaging data amenable to quantitative analyses.

Topographical differences in white matter hyperintensity burden and cognition in aging, MCI, and AD

AbstractBackgroundWhite matter hyperintensities (WMHs) are pathological changes that develop with increased age and are associated with cognitive decline. Most research on WMHs has neglected to examine regional differences and instead focuses on using a whole‐brain approach. This study examined regional WMH differences and their association with different cognition domains in normal controls (NCs), people with mild cognitive impairment (MCI), and Alzheimer’s disease (AD).Methods We included participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Few studies using ADNI data have examined the most recent cohort, ADNI‐3. Our study included datapoints from this recently released cohort. Participants were selected from ADNI and were included if they had at least one WMH measurement and cognitive scores examining global cognition (Alzheimer’s Disease Assessment Scale‐13), executive functioning (Trail Making Test‐Part B, and memory (Rey Auditory Verbal Learning Test). MCI and AD participants were included only if they were amyloid positive. A total of 1573 participants with 7381 follow‐ups met inclusion criteria. Linear mixed‐effects models were completed to examine group differences in WMH burden and the association between WMH burden and cognition in aging, MCI, and AD.ResultsPeople with MCI and AD had increased total and regional WMH burden compared to cognitively healthy older adults. An association between WMH and cognition was observed for global cognition, executive functioning, and memory in NCs in all regions of interest. A steeper decline (stronger association between WMH and cognition) was observed in MCI compared to NCs for all cognitive domains in all regions. A steeper decline was observed in AD compared to NCs for global cognition in only the temporal region.Conclusion Including ADNI‐3 data in this study is a novel strength to this study. These results suggest WMH burden increases from aging to AD. A strong association is observed between all cognitive domains of interest and WMH burden in healthy aging and MCI, while those with AD only had a few associations between and WMH and global cognition. These findings indicate that WMH burden is associated with changes in cognition in healthy aging and prodromal AD but not AD.

Neural network on interval-censored data with application to the prediction of Alzheimer's disease.

Alzheimer's disease (AD) is a progressive and polygenic disorder that affects millions of individuals each year. Given that there have been few effective treatments yet for AD, it is highly desirable to develop an accurate model to predict the full disease progression profile based on an individual's genetic characteristics for early prevention and clinical management. This work uses data composed of all four phases of the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, including 1740 individuals with 8 million genetic variants. We tackle several challenges in this data, characterized by large-scale genetic data, interval-censored outcome due to intermittent assessments, and left truncation in one study phase (ADNIGO). Specifically, we first develop a semiparametric transformation model on interval-censored and left-truncated data and estimate parameters through a sieve approach. Then we propose a computationally efficient generalized score test to identify variants associated with AD progression. Next, we implement a novel neural network on interval-censored data (NN-IC) to construct a prediction model using top variants identified from the genome-wide test. Comprehensive simulation studies show that the NN-IC outperforms several existing methods in terms of prediction accuracy. Finally, we apply the NN-IC to the full ADNI data and successfully identify subgroups with differential progression risk profiles. Data used in the preparation of this article were obtained from the ADNIdatabase.

Development of a three tiered cognitive hybrid machine learning algorithm for effective diagnosis of Alzheimer’s disease

Alzheimer's disease (AD) is one of the most frequent neurodegenerative disorders in the elderly subjects. Since early detection can prevent or delay cognitive decline in the older subjects, it is desirable to develop effectual protocols for the diagnosis of the disease. Most of the existing diagnostic tools fail to improvise timely disease prognosis in susceptible patients. Keeping this fact into consideration, we developed a cognitive-based 3-tiered machine learning (ML) algorithm employing baseline characteristics to predict AD or mild cognitive impairment (MCI) to construct psychometric test results. Earlier machine learning based AD diagnosis methods used a binary or multinomial classification technique. We relied on the development of a sophisticated hybrid cognitive ML algorithm that provides an accurate and precise prediction of the disease. We built an ML model using cognitive and demographic data. The prediction method consisted of a three-step process. Alzheimer’s Disease Neuroimaging Initiative (ADNI) database was used to develop a novel prediction algorithm. Considering the fact that nineteen ML and deep learning classifiers could not adequately classify ADNI data, we created a 2-layer model stacking procedure. Model stacking outperformed six ML classifier combinations, including Logistic Regression, Naïve Bayes, Support Vector Machine, Decision Trees, Random Forest, and eXtreme Gradient Boosting. The performance of the as-proposed model was evaluated employing seven performance assessment measures and four classification error indicators. Each model was evaluated in three separate strategical assessment modules. In the first experiment, XGB, Random Forest, and SVM achieved 89.63% accuracy, while Random Forest achieved 93.90% accuracy in the second experiment. Experiment 2 improved the classification and performance of overall prediction. In the third experiment, hybrid modeling, the accuracy increased significantly, with experiment 1 giving 90.24% accuracy and experiment 2 yielding 95.12% accuracy. The as-proposed model successfully predicted early AD and MCI in an effective manner. We were able to reduce nineteen classifiers into four classifiers (from experiment-1) and six classifiers (from experiment-2) and subsequently into one meta-learner (19 → 4 → 1 and 19 → 6 → 1), with high predictive power. Finally, we performed a thorough comparative analysis of different ADNI datasets to validate our findings.

Identifying Alzheimer’s genes via brain transcriptome mapping

BackgroundAlzheimer’s disease (AD) is one of the most common neurodegenerative disorders characterized by progressive decline in cognitive function. Targeted genetic analyses, genome-wide association studies, and imaging genetic analyses have been performed to detect AD risk and protective genes and have successfully identified dozens of AD susceptibility loci. Recently, brain imaging transcriptomics analyses have also been conducted to investigate the relationship between neuroimaging traits and gene expression measures to identify interesting gene-traits associations. These imaging transcriptomic studies typically do not involve the disease outcome in the analysis, and thus the identified brain or transcriptomic markers may not be related or specific to the disease outcome.ResultsWe propose an innovative two-stage approach to identify genes whose expression profiles are related to diagnosis phenotype via brain transcriptome mapping. Specifically, we first map the effects of a diagnosis phenotype onto imaging traits across the brain using a linear regression model. Then, the gene-diagnosis association is assessed by spatially correlating the brain transcriptome map with the diagnostic effect map on the brain-wide imaging traits. To demonstrate the promise of our approach, we apply it to the integrative analysis of the brain transcriptome data from the Allen Human Brain Atlas (AHBA) and the amyloid imaging data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. Our method identifies 12 genes whose brain-wide transcriptome patterns are highly correlated with six different diagnostic effect maps on the amyloid imaging traits. These 12 genes include four confirmatory findings (i.e., AD genes reported in DisGeNET) and eight novel genes that have not be associated with AD in DisGeNET.ConclusionWe have proposed a novel disease-related brain transcriptomic mapping method to identify genes whose expression profiles spatially correlated with regional diagnostic effects on a studied brain trait. Our empirical study on the AHBA and ADNI data shows the promise of the approach, and the resulting AD gene discoveries provide valuable information for better understanding biological pathways from transcriptomic signatures to intermediate brain traits and to phenotypic disease outcomes.

Screening and enrollment of underrepresented ethnocultural and educational populations in the Alzheimer's Disease Neuroimaging Initiative (ADNI).

An analysis of the ethnocultural and socioeconomic composition of Alzheimer's Disease Neuroimaging Initiative (ADNI) participants is needed to assess the generalizability of ADNI data to diverse populations. ADNI data collected between October 2004 and November 2020 were used to determine ethnocultural and educational composition of the sample and differences in the following metrics: screening, screen fails, enrollment, biomarkers. Of 3739 screened individuals, 11% identified as being from ethnoculturally underrepresented populations (e.g., Black, Latinx) and 16% had <12 years of education. Of 2286 enrolled participants, 11% identified as ethnoculturally underrepresented individuals and 15% had <12 years of education. This participation is considerably lower than US Census data for adults 60+ (ethnoculturally underrepresented populations: 25%; <12 years of education: 4%). Individuals with <12 years of education failed screening at a higher rate. Our findings suggest that ADNI results may not be entirely generalizable to ethnoculturally diverse and low education populations.

Profile and Non-Profile MM Modeling of Cluster Failure Time and Analysis of ADNI Data

Motivated by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) data, the objective of integration of important biomarkers for the early detection of Mild Cognitive Impairment (MCI) to Alzheimer’s disease (AD) as a therapeutic intervention is most likely to be beneficial in the early stages of disease progression. Developing predictors for MCI to AD comes down to genotype variables such that the dimension of predictors increases as the sample becomes large. Thus, we consider the sparsity concept of coefficients in a high-dimensional regression model with clustered failure time data such as ADNI, which enables enhancing predictive performances and facilitates the model’s interpretability. In this study, we propose two MM algorithms (profile and non-profile) for the shared frailty survival model firstly and then extend the two proposed MM algorithms to regularized estimation in sparse high-dimensional regression model. The convergence properties of our proposed estimators are also established. Furthermore simulation studies and analysis of ADNI data are illustrated by our proposed methods.

Functional MRI and ApoE4 genotype for predicting cognitive decline in amyloid-positive individuals.

In light of advancements in machine learning techniques, many studies have implemented machine learning approaches combined with data measures to predict and classify Alzheimer's disease. Studies that predicted cognitive status with longitudinal follow-up of amyloid-positive individuals remain scarce, however. We developed models based on voxel-wise functional connectivity (FC) density mapping and the presence of the ApoE4 genotype to predict whether amyloid-positive individuals would experience cognitive decline after 1 year. We divided 122 participants into cognitive decline and stable cognition groups based on the participants' change rates in Mini-Mental State Examination scores. In addition, we included 68 participants from Alzheimer's Disease Neuroimaging Initiative (ADNI) database as an external validation data set. Subsequently, we developed two classification models: the first model included 99 voxels, and the second model included 99 voxels and the ApoE4 genotype as features to train the models by Wide Neural Network algorithm with fivefold cross-validation and to predict the classes in the hold-out test and ADNI data sets. The results revealed that both models demonstrated high accuracy in classifying the two groups in the hold-out test data set. The model for FC demonstrated good performance, with a mean F 1-score of 0.86. The model for FC combined with the ApoE4 genotype achieved superior performance, with a mean F 1-score of 0.90. In the ADNI data set, the two models demonstrated stable performances, with mean F 1-scores of 0.77 in the first and second models. Our findings suggest that the proposed models exhibited promising accuracy for predicting cognitive status after 1 year in amyloid-positive individuals. Notably, the combination of FC and the ApoE4 genotype increased prediction accuracy. These findings can assist clinicians in predicting changes in cognitive status in individuals with a high risk of Alzheimer's disease and can assist future studies in developing precise treatment and prevention strategies.

Comparison of plasma neurofilament light and total tau as neurodegeneration markers: associations with cognitive and neuroimaging outcomes

BackgroundTotal tau protein (T-Tau) and neurofilament light chain (NfL) have emerged as candidate plasma biomarkers of neurodegeneration, but studies have not compared how these biomarkers cross-sectionally or longitudinally associate with cognitive and neuroimaging measures. We therefore compared plasma T-Tau and NfL as cross-sectional and longitudinal markers of (1) global and domain-specific cognitive decline and (2) neuroimaging markers of cortical thickness, hippocampal volume, white matter integrity, and white matter hyperintensity volume.MethodsWe included 995 participants without dementia who were enrolled in the Mayo Clinic Study of Aging cohort. All had concurrent plasma NfL and T-tau, cognitive status, and neuroimaging data. Follow-up was repeated approximately every 15 months for a median of 6.2 years. Plasma NfL and T-tau were measured on the Simoa-HD1 Platform. Linear mixed effects models adjusted for age, sex, and education examined associations between baseline z-scored plasma NfL or T-tau and cognitive or neuroimaging outcomes. Analyses were replicated in Alzheimer’s Disease Neuroimaging Initiative (ADNI) among 387 participants without dementia followed for a median of 3.0 years.ResultsAt baseline, plasma NfL was more strongly associated with all cognitive and neuroimaging outcomes. The combination of having both elevated NfL and T-tau at baseline, compared to elevated levels of either alone, was more strongly associated at cross-section with worse global cognition and memory, and with neuroimaging measures including temporal cortex thickness and increased number of infarcts. In longitudinal analyses, baseline plasma T-tau did not add to the prognostic value of baseline plasma NfL. Results using ADNI data were similar.ConclusionsOur results indicate plasma NfL had better utility as a prognostic marker of cognitive decline and neuroimaging changes. Plasma T-tau added cross-sectional value to NfL in specific contexts.Trial registrationNot applicable

The screening and enrollment of underrepresented ethnoracial and educational populations in the Alzheimer's Disease Neuroimaging Initiative

AbstractBackgroundAn analysis of the ethnoracial and educational composition of Alzheimer's Disease Neuroimaging Initiative (ADNI) participants, and the relationship between ethnoracial/education and screening, enrollment, dropout, and biomarkers is needed to assess the generalizability of ADNI data to diverse populations, and to inform efforts to increase diversity.MethodData from all 4 ADNI phases were used to determine ethnoracial and educational breakdown and differences of the following ADNI participation metrics: screening, screen fails, enrollment, as well as drop‐out within and between ADNI phases. Multivariable logistic regression was used to analyze the association between ethnoracial and educational group and either amyloid positivity or ApoE e4 status, adjusting for age, gender, and diagnostic group.ResultAcross the 4 ADNI phases (screened: n=3,739; enrolled: n=2,286), 11% of screened and enrolled participants identified as Latinx, non‐Latinx Black, or non‐Latinx‐Asian and 16% of the screened and 15% of the enrolled participants reported having =&lt;12 years of education. In contrast, the 2019 US Census American Community Survey for adults 60+ reports 25% non‐White, and 44 % =&lt; 12 years of education. There were no observed differences between participants from historically underrepresented ethnoracial groups and NLW participants in screen fail and dropout rates. We found that individuals with =&lt;12 years of education failed screening at a significantly higher rate (p=.01) and rolled‐over significantly less to subsequent ADNI phases (p&lt;.001) compared to individuals with an education &gt;12 years. Identifying as non‐Latinx Asian was associated with lower odds of being amyloid positive (OR=0.36; p=.014) and an ApoE4 carrier (OR=0.36; p=.008) compared to NLW. Identifying as Latinx was associated with being less likely to be amyloid positive than NLW participants (OR=0.54; p=.031).ConclusionCompared to the US Census, ADNI underrepresents enrollment of Latinx, non‐Latinx Black, and non‐Latinx Asian participants and those with low educational attainment. Hence, ADNI reflects the on‐going challenges with recruiting and enrolling underrepresented populations into most AD research. Our findings highlight the need for ADNI to increase enrollment and engagement of underrepresented ethnoracial and educational populations. ADNI is actively undertaking steps to implement improved recruitment approaches aimed at increasing ethnoracial and socioeconomical representation in multi‐center cohort studies.

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

IntroductionThe 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.MethodsWe identified 1442 publications using ADNI data by conventional search methods and selected impactful studies for inclusion.ResultsDisease 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.DiscussionADNI has had a profound impact in improving clinical trials for AD.