Alzheimer's Disease Neuroimaging Initiative Data Research Articles

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 =<12 years of education. In contrast, the 2019 US Census American Community Survey for adults 60+ reports 25% non‐White, and 44 % =< 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 =<12 years of education failed screening at a significantly higher rate (p=.01) and rolled‐over significantly less to subsequent ADNI phases (p<.001) compared to individuals with an education >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.

A Bayesian group lasso classification for ADNI volumetrics data.

The primary objective of this paper is to develop a statistically valid classification procedure for analyzing brain image volumetrics data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) in elderly subjects with cognitive impairments. The Bayesian group lasso method thereby proposed for logistic regression efficiently selects an optimal model with the use of a spike and slab type prior. This method selects groups of attributes of a brain subregion encouraged by the group lasso penalty. We conduct simulation studies for high- and low-dimensional scenarios where our method is always able to select the true parameters that are truly predictive among a large number of parameters. The method is then applied on dichotomous response ADNI data which selects predictive atrophied brain regions and classifies Alzheimer's disease patients from healthy controls. Our analysis is able to give an accuracy rate of 80% for classifying Alzheimer's disease. The suggested method selects 29 brain subregions. The medical literature indicates that all these regions are associated with Alzheimer's patients. The Bayesian method of model selection further helps selecting only the subregions that are statistically significant, thus obtaining an optimal model.

Robust hybrid deep learning models for Alzheimer’s progression detection

The prevalence of Alzheimer’s disease (AD) in the growing elderly population makes accurately predicting AD progression crucial. Due to AD’s complex etiology and pathogenesis, an effective and medically practical solution is a challenging task. In this paper, we developed and evaluated two novel hybrid deep learning architectures for AD progression detection. These models are based on the fusion of multiple deep bidirectional long short-term memory (BiLSTM) models. The first architecture is an interpretable multitask regression model that predicts seven crucial cognitive scores for the patient 2.5 years after their last observations. The predicted scores are used to build an interpretable clinical decision support system based on a glass-box model. This architecture aims to explore the role of multitasking models in producing more stable, robust, and accurate results. The second architecture is a hybrid model where the deep features extracted from the BiLSTM model are used to train multiple machine learning classifiers. The two architectures were comprehensively evaluated using different time series modalities of 1371 subjects participated in the study of the Alzheimer’s disease neuroimaging initiative (ADNI). The extensive, real-world experimental results over ADNI data help establish the effectiveness and practicality of the proposed deep learning models.

The association between low social support and risk of cognitive impairment is partially mediated by neuroanatomic biomarkers of Alzheimer’s disease

AbstractBackgroundSocial relationships with less support are linked to greater risk of developing Alzheimer’s disease (AD) and other dementias. Despite growing evidence of this link, to our knowledge, no studies have examined neuropathological processes through which low social support may affect risk of cognitive impairment. We used data from the Women’s Health Initiative Memory Study (WHIMS)‐MRI Study to examine whether neuroanatomical characteristics indicative of AD risk and cerebrovascular diseases underlie the greater risk of cognitive impairment or dementia over time in those with less supportive social relationships.MethodParticipants included 989 women (aged 73‐87 years) from the WHIMS‐MRI study who completed the Medical Outcomes Study Social Support Scale, assessing perceived emotional, tangible, and affectionate support, in 2004‐05. Structural brain scans were performed in 2005‐06 to assess small‐vessel ischemic disease (SVID) volume and determine AD pattern similarity scores (AD‐PS), a brain‐MRI measured neuroanatomical biomarker reflecting diffuse gray matter atrophy in brain regions vulnerable to AD neuropathologies, developed by supervised machine learning and validated with AD Neuroimaging Initiative data. Annual WHIMS follow‐ups included extensive neuropsychological assessments to ascertain centrally‐adjudicated incident cases of mild cognitive impairment (MCI) or all‐cause dementia. Structural equation models were used to assess the association between social support and risk of MCI/dementia (diagnosis data available through June 2018), and whether the association was mediated by global SVID volumes or AD‐PS scores. Models were adjusted for depressive symptoms, demographic, lifestyle, and clinical covariates.ResultLow social support was associated with higher MCI/dementia risk (hazard ratio= 1.23 per 1‐SD; 95% CI: 1.07, 1.44) and also with higher AD‐PS scores (β=.067; 95% CI: .01, .12), but not SVID volume. Higher AD‐PS score accounted for 18.6% (95% CI: 4%, 43%) of the total effect of low social support on risk of MCI/dementia (Figure 1). Higher SVID only accounted for 1.9% (95% CI: ‐1.5%, 8.8%) of the total effect.ConclusionOur study illustrates an association between low social support and higher MCI/dementia risk among older women, which was partly mediated by gray matter atrophy indicative of higher AD risk. Findings also suggest less of a role of cerebrovascular disease in mediating these associations.

Association of Alzheimer’s disease progression with baseline clinical and genetic characteristics

AbstractBackgroundMitochondrial genetics are important in the etiology of Alzheimer’s disease (AD). Based on the polymorphisms in mitochondrial DNA (mtDNA) the population can be classified into subgroups called the haplogroups. Previous studies have explored the association of haplogroups and genetic variants in APOE ε4 with AD but the results are inconsistent. Also, patients with mild cognitive impairment (MCI) at baseline often progress differently over several years of follow up.MethodWe carried out a cross‐sectional study to examine the association of the rate of incidence of AD with APOE ε4 genotype and haplogroups. The data collected at the University of Kansas AD Center (KU ADC) consisting of 146 AD and 265 normal subjects, and the data collected by AD Neuroimaging Initiative (ADNI) consisting of 244 AD and 242 normal subjects were used for these analyses. Logistic regression and Fisher Exact tests were used to explore the associations. We also carried out the association analyses of the differences in the disease progression rates from MCI to AD among the haplogroups using both datasets.ResultRates of incidence of AD were statistically significantly different among the haplogroups (2.2 × 10−8), with differing strengths of association across haplogroups. APOE ε4 was significantly associated with AD overall (p‐value = 1.9 × 10−11) and the association further varied by haplogroups. The results of the KU ADC population were consistent with those of the ADNI data. Out of 112 MCI subjects at baseline in KU ADC, 26 progressed to AD and 20 reverted back to normal at the last clinical visit. In ADNI, 172 progressed to AD and 42 reverted back out of 482 MCI at baseline. For both datasets, the proportion of subjects who progressed to AD differed by haplogroups. APOE ε4 genotype was significantly associated with increased risk of progression from MCI to AD (p‐value = 8.6 × 10−7 KUADC and p‐value = 1.33 × 10−9 ADNI).ConclusionThe rate of incidence of AD differed by mtDNA haplogroup and the strength of association further differed by APOE ε4 genotype. The rates of progression of MCI subjects to AD also differed by haplogroups and APOE ε4 genotype.

Zero Echo Time MRAC on FDG-PET/MR Maintains Diagnostic Accuracy for Alzheimer's Disease; A Simulation Study Combining ADNI-Data.

AimAttenuation correction using zero-echo time (ZTE) – magnetic resonance imaging (MRI) (ZTE-MRAC) has become one of the standard methods for brain-positron emission tomography (PET) on commercial PET/MR scanners. Although the accuracy of the net tracer-uptake quantification based on ZTE-MRAC has been validated, that of the diagnosis for dementia has not yet been clarified, especially in terms of automated statistical analysis. The aim of this study was to clarify the impact of ZTE-MRAC on the diagnosis of Alzheimer’s disease (AD) by performing simulation study.MethodsWe recruited 27 subjects, who underwent both PET/computed tomography (CT) and PET/MR (GE SIGNA) examinations. Additionally, we extracted 107 subjects from the Alzheimer Disease Neuroimaging Initiative (ADNI) dataset. From the PET raw data acquired on PET/MR, three FDG-PET series were generated, using two vendor-provided MRAC methods (ZTE and Atlas) and CT-based AC. Following spatial normalization to Montreal Neurological Institute (MNI) space, we calculated each patient’s specific error maps, which correspond to the difference between the PET image corrected using the CTAC method and the PET images corrected using the MRAC methods. To simulate PET maps as if ADNI data had been corrected using MRAC methods, we multiplied each of these 27 error maps with each of the 107 ADNI cases in MNI space. To evaluate the probability of AD in each resulting image, we calculated a cumulative t-value using a fully automated method which had been validated not only in the original ADNI dataset but several multi-center studies. In the method, PET score = 1 is the 95% prediction limit of AD. PET score and diagnostic accuracy for the discrimination of AD were evaluated in simulated images using the original ADNI dataset as reference.ResultsPositron emission tomography score was slightly underestimated both in ZTE and Atlas group compared with reference CTAC (−0.0796 ± 0.0938 vs. −0.0784 ± 0.1724). The absolute error of PET score was lower in ZTE than Atlas group (0.098 ± 0.075 vs. 0.145 ± 0.122, p < 0.001). A higher correlation to the original PET score was observed in ZTE vs. Atlas group (R2: 0.982 vs. 0.961). The accuracy for the discrimination of AD patients from normal control was maintained in ZTE and Atlas compared to CTAC (ZTE vs. Atlas. vs. original; 82.5% vs. 82.1% vs. 83.2% (CI 81.8–84.5%), respectively).ConclusionFor FDG-PET images on PET/MR, attenuation correction using ZTE-MRI had superior accuracy to an atlas-based method in classification for dementia. ZTE maintains the diagnostic accuracy for AD.

Increased Neuroanatomic Risk for Alzheimer’s Disease: Exploring the Interaction of Fine Particle Exposure and Long-Chain Omega-3 Polyunsaturated Fatty Acids

Background/Aim: Ambient fine particulate matter (PM2.5) may increase Alzheimer’s disease (AD) risk. Although epidemiologic and experimental studies have shown neurotrophic effects of long-chain omega-3 polyunsaturated fatty acids (LCn3FAs), no studies have investigated whether LCn3FAs modify the neurotoxic effect of PM2.5 on neuroanatomic risk for AD. Methods: Community-dwelling older women (aged 71-89) from the Women’s Health Initiative Memory Study of MRI completed two structural brain scans (MRI-1: 2005-6; MRI-2: 2010-11). The AD pattern similarity (AD-PS) score, developed by supervised machine learning and validated with AD Neuroimaging Initiative data, was used to measure neuroanatomic risk determined by the degree of high-dimensional gray matter atrophy in brain areas vulnerable to AD. Residential three-year average PM2.5 exposure preceding MRI-1 was aggregated from daily estimates, based on nationwide spatiotemporal modeling. Red blood cell fatty acid composition was analyzed using gas chromatography, with the omega-3 index defined as the sum of eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA). We examined whether omega-3 index, EPA, and DHA modified the association between PM2.5 and AD-PS scores (5-year standardized difference) using generalized linear models, adjusting for geographic region, sociodemographics, lifestyle factors, clinical characteristics, intracranial volume, and total energy intake. Results: Among 627 women, PM2.5 (per 2.82-µg/m3) was significantly associated with increased AD-PS scores (β=0.026; p=0.003; equivalent to a 24% increase in AD risk) over 5 years. This association with PM2.5 was greater among women with lower (β=0.042; p=0.001) vs. higher (β=0.006; p=0.660) omega-3 index (median=0.050-g/1,000-kcal; pinteraction=0.056) and among women with lower (β=0.042; p=0.001) vs. higher (β=0.007; p=0.577) DHA (median=0.044-g/1,000-kcal; pinteraction=0.064). There was no evidence that EPA modified the association (pinteraction=0.340). Conclusions: Our findings support potential interactions between PM2.5 neurotoxicity and neurotrophic effects of LCn3FAs, though tests of interactions did not reach statistical significance. Higher LCn3FAs, achievable by dietary intervention, may reduce the AD risk associated with long-term PM2.5 exposure.

Robust parametric modeling of Alzheimer’s disease progression

Quantitative characterization of disease progression using longitudinal data can provide long-term predictions for the pathological stages of individuals. This work studies the robust modeling of Alzheimer’s disease progression using parametric methods. The proposed method linearly maps the individual’s age to a disease progression score (DPS) and jointly fits constrained generalized logistic functions to the longitudinal dynamics of biomarkers as functions of the DPS using M-estimation. Robustness of the estimates is quantified using bootstrapping via Monte Carlo resampling, and the estimated inflection points of the fitted functions are used to temporally order the modeled biomarkers in the disease course. Kernel density estimation is applied to the obtained DPSs for clinical status classification using a Bayesian classifier. Different M-estimators and logistic functions, including a novel type proposed in this study, called modified Stannard, are evaluated on the data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) for robust modeling of volumetric magnetic resonance imaging (MRI) and positron emission tomography (PET) biomarkers, cerebrospinal fluid (CSF) measurements, as well as cognitive tests. The results show that the modified Stannard function fitted using the logistic loss achieves the best modeling performance with an average normalized mean absolute error (NMAE) of 0.991 across all biomarkers and bootstraps. Applied to the ADNI test set, this model achieves a multiclass area under the ROC curve (AUC) of 0.934 in clinical status classification. The obtained results for the proposed model outperform almost all state-of-the-art results in predicting biomarker values and classifying clinical status. Finally, the experiments show that the proposed model, trained using abundant ADNI data, generalizes well to data from the National Alzheimer’s Coordinating Center (NACC) with an average NMAE of 1.182 and a multiclass AUC of 0.929.

Predicting Mental Decline Rates in Mild Cognitive Impairment From Baseline MRI Volumetric Data.

In mild cognitive impairment (MCI), identifying individuals at high risk for progressive cognitive deterioration can be useful for prognostication and intervention. This study quantitatively characterizes cognitive decline rates in MCI and tests whether volumetric data from baseline magnetic resonance imaging (MRI) can predict accelerated cognitive decline. The authors retrospectively examined Alzheimer Disease Neuroimaging Initiative data to obtain serial Mini-Mental Status Exam (MMSE) scores, diagnoses, and the following baseline MRI volumes: total intracranial volume, whole-brain and ventricular volumes, and volumes of the hippocampus, entorhinal cortex, fusiform gyrus, and medial temporal lobe. Subjects with <24 months or <4 measurements of MMSE data were excluded. Predictive modeling of fast cognitive decline (defined as >0.6/year) from baseline volumetric data was performed on subjects with MCI using a single hidden layer neural network. Among 698 baseline MCI subjects, the median annual decline in the MMSE score was 1.3 for converters to dementia versus 0.11 for stable MCI (P<0.001). A 0.6/year threshold captured dementia conversion with 82% accuracy (sensitivity 79%, specificity 85%, area under the receiver operating characteristic curve 0.88). Regional volumes on baseline MRI predicted fast cognitive decline with a test accuracy of 71%. An MMSE score decrease of >0.6/year is associated with MCI-to-dementia conversion and can be predicted from baseline MRI.

Longitudinal ComBat: A method for harmonizing longitudinal multi-scanner imaging data

While aggregation of neuroimaging datasets from multiple sites and scanners can yield increased statistical power, it also presents challenges due to systematic scanner effects. This unwanted technical variability can introduce noise and bias into estimation of biological variability of interest. We propose a method for harmonizing longitudinal multi-scanner imaging data based on ComBat, a method originally developed for genomics and later adapted to cross-sectional neuroimaging data. Using longitudinal cortical thickness measurements from 663 participants in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study, we demonstrate the presence of additive and multiplicative scanner effects in various brain regions. We compare estimates of the association between diagnosis and change in cortical thickness over time using three versions of the ADNI data: unharmonized data, data harmonized using cross-sectional ComBat, and data harmonized using longitudinal ComBat. In simulation studies, we show that longitudinal ComBat is more powerful for detecting longitudinal change than cross-sectional ComBat and controls the type I error rate better than unharmonized data with scanner included as a covariate. The proposed method would be useful for other types of longitudinal data requiring harmonization, such as genomic data, or neuroimaging studies of neurodevelopment, psychiatric disorders, or other neurological diseases.

Genome-Wide Gene-Based Multi-Trait Analysis.

Genome-wide association studies focusing on a single phenotype have been broadly conducted to identify genetic variants associated with a complex disease. The commonly applied single variant analysis is limited by failing to consider the complex interactions between variants, which motivated the development of association analyses focusing on genes or gene sets. Moreover, when multiple correlated phenotypes are available, methods based on a multi-trait analysis can improve the association power. However, most currently available multi-trait analyses are single variant-based analyses; thus have limited power when disease variants function as a group in a gene or a gene set. In this work, we propose a genome-wide gene-based multi-trait analysis method by considering genes as testing units. For a given phenotype, we adopt a rapid and powerful kernel-based testing method which can evaluate the joint effect of multiple variants within a gene. The joint effect, either linear or nonlinear, is captured through kernel functions. Given a series of candidate kernel functions, we propose an omnibus test strategy to integrate the test results based on different candidate kernels. A p-value combination method is then applied to integrate dependent p-values to assess the association between a gene and multiple correlated phenotypes. Simulation studies show a reasonable type I error control and an excellent power of the proposed method compared to its counterparts. We further show the utility of the method by applying it to two data sets: the Human Liver Cohort and the Alzheimer Disease Neuroimaging Initiative data set, and novel genes are identified. Our method has broad applications in other fields in which the interest is to evaluate the joint effect (linear or nonlinear) of a set of variants.

Some statistical consideration in transcriptome-wide association studies.

The methodology of transcriptome-wide association studies (TWAS) has become popular in integrating a reference expression quantitative trait (eQTL) data set with an independent main GWAS data set to identify (putatively) causal genes, shedding mechanistic insights to biological pathways from genetic variants to a GWAS trait mediated by gene expression. Statistically TWAS is a (two-sample) 2-stage least squares (2SLS) method in the framework of instrumental variables analysis for causal inference: in Stage 1 it uses the reference eQTL data to impute a genes expression for the main GWAS data, then in Stage 2 it tests for association between the imputed gene expression and the GWAS trait; if an association is detected in Stage 2, a (putatively) causal relationship between the gene and the GWAS trait is claimed. If a nonlinear model or a generalized linear model (GLM) is fitted in Stage 2 (e.g., for a binary GWAS trait), it is known that using only imputed gene expression, as in standard TWAS, in general does not lead to a consistent (i.e., asymptotically unbiased) estimate for the causal effect; accordingly, a variation of 2SLS, called two-stage residual inclusion (2SRI), has been proposed to yield better estimates (e.g., being consistent under suitable conditions). Our main goal is to investigate whether it is necessary or even better to apply 2SRI, instead of the standard 2SLS. In addition, due to the use of imputed gene expression (i.e., with measurement errors), it is known that in general some correction to the standard error estimate of the causal effect estimate has to be applied, while in the standard TWAS no correction is applied. Is this an issue? We also compare one-sample 2SLS with two-sample 2SLS (i.e., the standard TWAS). We used the Alzheimer's Disease Neuroimaging Initiative (ADNI) data and simulated data mimicking the ADNI data to address the above questions. At the end, we conclude that, in practice with the large sample sizes and small effect sizes of genetic variants, the standard TWAS performs well and is recommended.

ASSOCIATION BETWEEN NEUROPSYCHIATRIC SYMPTOM TRAJECTORY AND PROGRESSION TO ALZHEIMER'S DISEASE

Introduction Objective: Neuropsychiatric symptoms (NPS) are a key characteristic and known biomarker of Alzheimer's disease (AD). Our study investigates the potential of NPS as measured by the Neuropsychiatric Inventory score (NPI) to predict progression from Mild Cognitive Impairment (MCI) to AD. In addition, we have analyzed the trajectory of NPS in comparison to global cognitive scores. Introduction NPS are common in MCI and based on prior studies they are a significant risk factor for progression to AD. Working memory and episodic memory are also known to decline with progression of AD. Cognitive tests such as MMSE have been utilized to track patients’ level of cognition and the decline in these cognitive tests is a well-known predictor of dementia. However, how NPI scores relate to cognitive test scores in predicting progression to AD is still unknown. We propose to analyze NPI (total score and sub scores) longitudinally for 6 years and to compare scores between MCI- converters (MCI-C) and MCI- non converters (MCI-NC). We hypothesize that converters may have higher scores compared to non-converters. In addition, we expect that MMSE score should correlate inversely with NPI score. Symptoms associated with progression to AD that are prevalent in our study should match those that are shown in previous studies (depression, delusion, agitation, and apathy.) Methods We selected 150 subjects from Alzheimer's Disease Neuroimaging Initiative phase 3 (36 MCI-C and 114 MCI-NC). The only inclusion criteria were that subjects must have NPI scores at two or more time points. Gender, age, and education were matched across all subjects. To measure NPI scores longitudinally, subjects were divided into two groups, MCI-C and MCI-NC. We also grouped subjects according to their NPI scores to measure their cognition using MMSE: healthy (N=55), mild (NPI score= 1-9, N=65), and severe (NPI score= 10 and above, N=30). The NPI total score and MMSE were measured across 6 years and compared at 12-month intervals. All statistical analyses were performed using SPSS 25. Analyses of variance (ANOVA) were used to compare MCI-C and MCI-NC group differences. If the assumption of homogeneity was violated, Brown-Forsythe Test p-value was reported instead. Post-hoc analyses was done by using Gabriel and Dunnett's T3 test. The 12 NPI sub scores were also counted as percentage to analyse the progression of NPS. Results The NPI total scores at all time points for the duration of 6 years were significantly different between MCI-C and MCI-NC (p Conclusions Our study has confirmed previous findings that NPI scores increased with progression of clinical symptoms from MCI to AD in MCI-C relative to MCI-NC. In addition, MMSE scores varied between NPI groups at all time points after baseline. Both of the scores showed a deteriorating trend in their respective scale in MCI-C relative to MCI-NC. This research was funded by Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer's Association; Alzheimer's Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health ( www.fnih.org ). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer's Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California.

Independent and Reproducible Hippocampal Radiomic Biomarkers for Multisite Alzheimer's Disease: Diagnosis, Longitudinal Progress and Biological Basis

Hippocampal morphological change is one of the main hallmarks of Alzheimer's disease (AD). However, whether hippocampal radiomic features are reproducible and robust as predictors of progression from mild cognitive impairment (MCI) to AD dementia and provide a neurobiological foundation remains unclear. The primary aim of this study was to verify whether hippocampal radiomic features are robust MRI markers for AD. Multivariate classifier-based SVM analysis provided individual-level predictions for distinguishing AD patients (N=261) from normal controls (NCs; N=231) with accuracy=88.21% with inter-site cross-validation. Further analyses of a large, independent ADNI dataset (N=1228) reinforced these findings. In mild cognitive impairment (MCI) groups, a systemic analysis demonstrated that the identified features were significantly associated with clinical features (e.g., apolipoprotein E (APOE) genotype, polygenic risk scores, cerebrospinal fluid (CSF) Aβ, CSF Tau), and longitudinal changes in cognition ability; more importantly, the radiomic features have a consistently altered pattern with changes in the MMSE scores over 5 years of follow-up. These comprehensive results suggest that hippocampal radiomic features can serve as a robust biomarker for clinical applications in AD/MCI, further provide evidence for predicting whether MCI subject would convert to AD or not based on hippocampus, without doubt has significantly meaning for early diagnosis of AD/MCI. Funding Statement: This work was partially supported by the National Key Research and Development Program of China (grant no. 2016YFC1305904), the Strategic Priority Research Program (B) of the Chinese Academy of Sciences (grant no. XDB32020200), the National Natural Science Foundation of China (grant nos. 81871438, 81901101, 61633018, 81571062, 81400890, 61431012), and the Primary Research & Development Plan of Shandong Province (grant no. 2017GGX10112). Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH 12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and generous contributions from AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research provide funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer’s Therapeutic Research Institute at the University of Southern California. The ADNI data are disseminated by the Laboratory for Neuro-Imaging at the University of Southern California. Declaration of Interests: This study includes the databases which were approved by the Medical Ethics Committee of local Hospitals.

Disease progression timeline estimation for Alzheimer's disease using discriminative event based modeling

Alzheimer's Disease (AD) is characterized by a cascade of biomarkers becoming abnormal, the pathophysiology of which is very complex and largely unknown. Event-based modeling (EBM) is a data-driven technique to estimate the sequence in which biomarkers for a disease become abnormal based on cross-sectional data. It can help in understanding the dynamics of disease progression and facilitate early diagnosis and prognosis by staging patients. In this work we propose a novel discriminative approach to EBM, which is shown to be more accurate than existing state-of-the-art EBM methods. The method first estimates for each subject an approximate ordering of events. Subsequently, the central ordering over all subjects is estimated by fitting a generalized Mallows model to these approximate subject-specific orderings based on a novel probabilistic Kendall's Tau distance. We also introduce the concept of relative distance between events which helps in creating a disease progression timeline. Subsequently, we propose a method to stage subjects by placing them on the estimated disease progression timeline. We evaluated the proposed method on Alzheimer's Disease Neuroimaging Initiative (ADNI) data and compared the results with existing state-of-the-art EBM methods. We also performed extensive experiments on synthetic data simulating the progression of Alzheimer's disease. The event orderings obtained on ADNI data seem plausible and are in agreement with the current understanding of progression of AD. The proposed patient staging algorithm performed consistently better than that of state-of-the-art EBM methods. Event orderings obtained in simulation experiments were more accurate than those of other EBM methods and the estimated disease progression timeline was observed to correlate with the timeline of actual disease progression. The results of these experiments are encouraging and suggest that discriminative EBM is a promising approach to disease progression modeling.

A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain.

Purpose To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 (18F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers. Materials and Methods Prospective 18F-FDG PET brain images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding. Results The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P < .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain. Conclusion By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Larvie in this issue.

Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer's disease across imaging databases

IntroductionThe main goal of this work is to investigate the feasibility of estimating an anatomical index that can be used as an Alzheimer's disease (AD) risk factor in the Women's Health Initiative Magnetic Resonance Imaging Study (WHIMS-MRI) using MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), a well-characterized imaging database of AD patients and cognitively normal subjects. We called this index AD Pattern Similarity (AD-PS) scores. To demonstrate the construct validity of the scores, we investigated their associations with several AD risk factors. The ADNI and WHIMS imaging databases were collected with different goals, populations and data acquisition protocols: it is important to demonstrate that the approach to estimating AD-PS scores can bridge these differences. MethodsMRI data from both studies were processed using high-dimensional warping methods. High-dimensional classifiers were then estimated using the ADNI MRI data. Next, the classifiers were applied to baseline and follow-up WHIMS-MRI GM data to generate the GM AD-PS scores. To study the validity of the scores we investigated associations between GM AD-PS scores at baseline (Scan 1) and their longitudinal changes (Scan 2 –Scan 1) with: 1) age, cognitive scores, white matter small vessel ischemic disease (WM SVID) volume at baseline and 2) age, cognitive scores, WM SVID volume longitudinal changes respectively. In addition, we investigated their associations with time until classification of independently adjudicated status in WHIMS-MRI. ResultsHigher GM AD-PS scores from WHIMS-MRI baseline data were associated with older age, lower cognitive scores, and higher WM SVID volume. Longitudinal changes in GM AD-PS scores (Scan 2 – Scan 1) were also associated with age and changes in WM SVID volumes and cognitive test scores. Increases in the GM AD-PS scores predicted decreases in cognitive scores and increases in WM SVID volume. GM AD-PS scores and their longitudinal changes also were associated with time until classification of cognitive impairment. Finally, receiver operating characteristic curves showed that baseline GM AD-PS scores of cognitively normal participants carried information about future cognitive status determined during follow-up. DiscussionWe applied a high-dimensional machine learning approach to estimate a novel AD risk factor for WHIMS-MRI study participants using ADNI data. The GM AD-PS scores showed strong associations with incident cognitive impairment and cross-sectional and longitudinal associations with age, cognitive function, cognitive status and WM SVID volume lending support to the ongoing validation of the GM AD-PS score.

Associations of Pulse and Blood Pressure with Hippocampal Volume by APOE and Cognitive Phenotype: The Alzheimer’s Disease Neuroimaging Initiative (ADNI)

Background: It is increasingly evident that high blood pressure can promote reduction in global and regional brain volumes. While these effects may preferentially affect the hippocampus, reports are inconsistent. Methods: Using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), we examined the relationships of hippocampal volume to pulse pressure (PPR) and systolic (SBP) and diastolic (DBP) blood pressure according to apolipoprotein (APOE) ɛ4 positivity and cognitive status. The ADNI data included 1,308 participants: Alzheimer disease (AD = 237), late mild cognitive impairment (LMCI = 454), early mild cognitive impairment (EMCI = 254), and cognitively normal (CN = 365), with up to 24 months of follow-up. Results: Higher quartiles of PPR were significantly associated with lower hippocampal volumes (Q1 vs. Q4, p = 0.034) in the CN and AD groups, but with increasing hippocampal volume (Q1, p = 0.008; Q2, p = 0.020; Q3, p = 0.017; Q4 = reference) in the MCI groups. In adjusted stratified analyses among non-APOE ɛ4 carriers, the effects in the CN (Q1 vs. Q4, p = 0.006) and EMCI groups (Q1, p = 0.002; Q2, p = 0.013; Q3, p = 0.002; Q4 = reference) remained statistically significant. Also, higher DBP was significantly associated with higher hippocampal volume (p = 0.002) while higher SBP was significantly associated with decreasing hippocampal volume in the EMCI group (p = 0.015). Conclusion: Changes in PPR, SBP, and DBP differentially influenced hippocampal volumes depending on the cognitive and APOE genotypic categories.

APOE allele frequencies in suspected non-amyloid pathophysiology (SNAP) and the prodromal stages of Alzheimer's Disease.

Biomarker definitions for preclinical Alzheimer’s disease (AD) have identified individuals with neurodegeneration (ND+) without β-amyloidosis (Aβ-) and labeled them with suspected non-AD pathophysiology (SNAP). We evaluated Apolipoprotein E (APOE) ε2 and ε4 allele frequencies across biomarker definitions—Aβ-/ND- (n = 268), Aβ+/ND- (n = 236), Aβ-/ND+ or SNAP (n = 78), Aβ+/ND+ (n = 204)—hypothesizing that SNAP would have an APOE profile comparable to Aβ-/ND-. Using AD Neuroimaging Initiative data (n = 786, 72±7 years, 48% female), amyloid status (Aβ+ or Aβ-) was defined by cerebrospinal fluid (CSF) Aβ-42 levels, and neurodegeneration status (ND+ or ND-) was defined by hippocampal volume from MRI. Binary logistic regression related biomarker status to APOE ε2 and ε4 allele carrier status, adjusting for age, sex, education, and cognitive diagnosis. Compared to the biomarker negative (Aβ-/ND-) participants, higher proportions of ε4 and lower proportions of ε2 carriers were observed among Aβ+/ND- (ε4: OR = 6.23, p<0.001; ε2: OR = 0.53, p = 0.03) and Aβ+/ND+ participants (ε4: OR = 12.07, p<0.001; ε2: OR = 0.29, p = 0.004). SNAP participants were statistically comparable to biomarker negative participants (p-values>0.30). In supplemental analyses, comparable results were observed when coding SNAP using amyloid imaging and when using CSF tau levels. In contrast to APOE, a polygenic risk score for AD that excluded APOE did not show an association with amyloidosis or neurodegeneration (p-values>0.15), but did show an association with SNAP defined using CSF tau (β = 0.004, p = 0.02). Thus, in a population with low levels of cerebrovascular disease and a lower prevalence of SNAP than the general population, APOE and known genetic drivers of AD do not appear to contribute to the neurodegeneration observed in SNAP. Additional work in population based samples is needed to better elucidate the genetic contributors to various etiological drivers of SNAP.