Japanese Alzheimer's Disease Neuroimaging Initiative Research Articles

Predicting progression to dementia with "comprehensive visual rating scale" and machine learning algorithms.

Background and ObjectiveIdentifying biomarkers for predicting progression to dementia in patients with mild cognitive impairment (MCI) is crucial. To this end, the comprehensive visual rating scale (CVRS), which is based on magnetic resonance imaging (MRI), was developed for the assessment of structural changes in the brains of patients with MCI. This study aimed to investigate the use of the CVRS score for predicting dementia in patients with MCI over a 2-year follow-up period using various machine learning (ML) algorithms.MethodsWe included 197 patients with MCI who were followed up more than once. The data used for this study were obtained from the Japanese-Alzheimer's Disease Neuroimaging Initiative study. We assessed all the patients using their CVRS scores, cortical thickness data, and clinical data to determine their progression to dementia during a follow-up period of over 2 years. ML algorithms, such as logistic regression, random forest (RF), XGBoost, and LightGBM, were applied to the combination of the dataset. Further, feature importance that contributed to the progression from MCI to dementia was analyzed to confirm the risk predictors among the various variables evaluated.ResultsOf the 197 patients, 108 (54.8%) showed progression from MCI to dementia. Tree-based classifiers, such as XGBoost, LightGBM, and RF, achieved relatively high performance. In addition, the prediction models showed better performance when clinical data and CVRS score (accuracy 0.701–0.711) were used than when clinical data and cortical thickness (accuracy 0.650–0.685) were used. The features related to CVRS helped predict progression to dementia using the tree-based models compared to logistic regression.ConclusionsTree-based ML algorithms can predict progression from MCI to dementia using baseline CVRS scores combined with clinical data.

Dissection of the polygenic architecture of neuronal Aβ production using a large sample of individual iPSC lines derived from Alzheimer's disease patients.

Genome-wide association studies have demonstrated that polygenic risks shape Alzheimer's disease (AD). To elucidate the polygenic architecture of AD phenotypes at a cellular level, we established induced pluripotent stem cells from 102 patients with AD, differentiated them into cortical neurons and conducted a genome-wide analysis of the neuronal production of amyloid β (Aβ). Using such a cellular dissection of polygenicity (CDiP) approach, we identified 24 significant genome-wide loci associated with alterations in Aβ production, including some loci not previously associated with AD, and confirmed the influence of some of the corresponding genes on Aβ levels by the use of small interfering RNA. CDiP genotype sets improved the predictions of amyloid positivity in the brains and cerebrospinal fluid of patients in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Secondary analyses of exome sequencing data from the Japanese ADNI and the ADNI cohorts focused on the 24 CDiP-derived loci associated with alterations in Aβ led to the identification of rare AD variants in KCNMA1.

Molecular Pathogenesis and Disease-modifying Therapies of Alzheimer's Disease and Related Disorders.

The deposition of amyloid β (Aβ) peptides as senile plaques and tau as neurofibrillary changes causes the hallmark neuropathological lesions of Alzheimer’s disease (AD), which are implicated in its pathogenesis and deemed as the prime target for disease-modifying therapies (DMTs). Aβ is produced by sequential proteolytic cleavage by β- and γ-secretases. γ-Secretase, harboring presenilins (PS) as the catalytic center, forms the C-terminus of Aβ that determines its propensity to aggregate; missense mutations in PS genes cause familial AD by altering the preferred γ-secretase cleavage sites to increase the production of pathogenic Aβ42 species. Numerous DMTs for AD have been tested in clinical trials, some of which met the clinical endpoints, whereas others, especially those conducted in dementia stages, have failed, underscoring the needs for early intervention. Notably, positive outcomes of recent trials for anti-Aβ antibody drugs have depended largely on molecular imaging and fluid biomarkers, underscoring the needs of markers that surrogate the clinical and pathophysiological progression of AD. Longitudinal observational studies as represented by the AD Neuroimaging Initiative (ADNI) in North America, as well as the Japanese ADNI (J-ADNI), have contributed greatly toward the goal of very early treatment at the prodromal and preclinical AD stages by delineating the early natural course of AD and facilitating the development of biomarkers. It has been demonstrated that the clinical and biomarker profiles of prodromal AD in J-ADNI were remarkably similar to those in the North American ADNI, supporting the harmonization of global clinical trials. These clinical studies in Japan, accelerated by the development and implementation of biomarkers, will pave the way toward the development of AD therapies targeting its very early stages.

Machine Learning for Diagnosis of AD and Prediction of MCI Progression From Brain MRI Using Brain Anatomical Analysis Using Diffeomorphic Deformation.

Background: With the growing momentum for the adoption of machine learning (ML) in medical field, it is likely that reliance on ML for imaging will become routine over the next few years. We have developed a software named BAAD, which uses ML algorithms for the diagnosis of Alzheimer's disease (AD) and prediction of mild cognitive impairment (MCI) progression.Methods: We constructed an algorithm by combining a support vector machine (SVM) to classify and a voxel-based morphometry (VBM) to reduce concerned variables. We grouped progressive MCI and AD as an AD spectrum and trained SVM according to this classification. We randomly selected half from the total 1,314 subjects of AD neuroimaging Initiative (ADNI) from North America for SVM training, and the remaining half were used for validation to fine-tune the model hyperparameters. We created two types of SVMs, one based solely on the brain structure (SVMst), and the other based on both the brain structure and Mini-Mental State Examination score (SVMcog). We compared the model performance with two expert neuroradiologists, and further evaluated it in test datasets involving 519, 592, 69, and 128 subjects from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Aging (AIBL), Japanese ADNI, the Minimal Interval Resonance Imaging in AD (MIDIAD) and the Open Access Series of Imaging Studies (OASIS), respectively.Results: BAAD's SVMs outperformed radiologists for AD diagnosis in a structural magnetic resonance imaging review. The accuracy of the two radiologists was 57.5 and 70.0%, respectively, whereas, that of the SVMst was 90.5%. The diagnostic accuracy of the SVMst and SVMcog in the test datasets ranged from 88.0 to 97.1% and 92.5 to 100%, respectively. The prediction accuracy for MCI progression was 83.0% in SVMst and 85.0% in SVMcog. In the AD spectrum classified by SVMst, 87.1% of the subjects were Aβ positive according to an AV-45 positron emission tomography. Similarly, among MCI patients classified for the AD spectrum, 89.5% of the subjects progressed to AD.Conclusion: Our ML has shown high performance in AD diagnosis and prediction of MCI progression. It outperformed expert radiologists, and is expected to provide support in clinical practice.

Effect of apolipoprotein E ε4 allele on the progression of cognitive decline in the early stage of Alzheimer's disease.

IntroductionPossession of the apolipoprotein E (APO E) ε4 allele advances amyloid β (Aβ) deposition and symptomatic onset of Alzheimer's disease (AD), whereas its effect on the rate of cognitive decline remained controversial. We examined the effects of APOE ε4 allele on cognition in biomarker‐confirmed late mild cognitive impairment (LMCI) and mild AD subjects in the Japanese Alzheimer's Disease Neuroimaging Initiative (J‐ADNI) and North American ADNI (NA‐ADNI).MethodsThe “early AD” (ie, combined LMCI and mild AD) cohort of 649 subjects from J‐ADNI and NA‐ADNI were selected based on positivity of Aβ confirmed by amyloid positron emission tomography (PET) or cerebrospinal fluid testing. The rates of cognitive decline in the Mini Mental State Examination (MMSE), the Clinical Dementia Rating Sum of Boxes (CDR‐SB), and the Alzheimer's Disease Assessment Scale‐cognitive subscale 13 (ADAS‐Cog) from baseline were examined using mixed‐effects model. The effect of ε4 on time to conversion to dementia was also analyzed in LMCI using the Kaplan‐Meier estimator and log‐rank test.ResultsThe rates of cognitive decline were not significantly different between ε4 carriers and ε4 non‐carriers in the total early AD cohort, which were affected neither by region nor by the number of ε4 alleles. In LMCI, ε4 carriers showed almost the same progression rates as ε4 non‐carriers, except for a significantly faster decline in MMSE (P = .0282). Time to conversion to demenita was not significantly different between ε4 carriers and ε4 non‐carriers. In ε4‐positive mild AD, the rates of decline in MMSE (P = .003) and CDR‐SB (P = .0071) were slower than those in ε4 non‐carriers.DISCUSSIONThe APOE ε4 allele had little effect on the rates of cognitive decline in the overall biomarker‐confirmed early AD, regardless of region and number of ε4 alleles, with a slight variability in different clinical stages, the ε4 allele being slightly accelerative in LMCI, while decelerative in mild AD.

Lower Serum Calcium as a Potentially Associated Factor for Conversion of Mild Cognitive Impairment to Early Alzheimer's Disease in the Japanese Alzheimer's Disease Neuroimaging Initiative.

Effect of serum calcium level to the incidence of mild cognitive impairment (MCI) conversion to early Alzheimer's disease (AD) remains uncertain. To investigate association between baseline serum calcium and the MCI conversion in the Japanese Alzheimer's Disease Neuroimaging Initiative (J-ADNI) study cohort. In this sub-analysis of J-ADNI study, we reviewed data from MCI participants at baseline regarding their conversion to early AD during the 3 years of observation period and assessed the associated factors including serum calcium level. In addition, we compared our results from the J-ADNI study with the corresponding results from the North American (NA)-ADNI. Of 234 eligible MCI participants from the J-ADNI cohort, 121 (51.7%) converted to AD during the first 36 months of observation. Using univariate analysis, being female, having shorter years of education, and lower serum calcium level were correlated with increased risk of MCI-to-AD conversion exclusively in J-ADNI cohort. The lower corrected serum calcium level remained as one of conversion-associated factors in the J-ADNI cohort even after adjustment for multiple confounding variables, although this was not observed in the NA-ADNI cohort. Our findings suggest that lower serum calcium may be associated with an increased risk of MCI conversion to AD in Japanese cohorts. The reason for this correlation remains unclear and further external validation using other Asian cohorts is needed. It would be interesting for future AD studies to obtain serum calcium levels and other related factors, such as vitamin D levels, culture-specific dietary or medication information.

Identification of prognostic factors to predict cognitive decline of patients with early Alzheimer's disease in the Japanese Alzheimer's Disease Neuroimaging Initiative study

IntroductionThe objective of this study was to determine the factors including neuropsychological test performances and cerebrospinal fluid (CSF) biomarkers which can predict disease progression of early Alzheimer's disease (AD) in a Japanese population. MethodsThe group classification on early AD population in both Japanese Alzheimer's Disease Neuroimaging Initiative (J-ADNI) and North American ADNI (NA-ADNI) was performed using the inclusion criteria including brain amyloid positivity on positron emission tomography or CSF. Participants with early AD from each cohort were stratified into two groups based on a cutoff 1.0 of Clinical Dementia Rating Scale Sum of Boxes (CDR-SB) change at month 24 (m24): participants in “progress group” have CDR-SB change ≥ 1.0 and participants in “stable group” have CDR-SB change < 1.0. Then, we performed identification of prognostic factors from baseline items including neuropsychological scores (Assessment Scale-Cognitive Subscale[ADAS-cog 13], Mini-Mental State Examination (MMSE), CDR, FAQ, and Geriatric Depression Scale ), CSF markers (t-tau, p-tau, and beta-amyloid 1-42), vital signs (body weight, pulse rate, etc.,), by using two statistical approaches, Welch's t-test and simple linear regression by ordinary least squares. Comparisons between participants with J-ADNI and participants with NA-ADNI were also performed. ResultsTrends of CDR-SB changes were very similar between J-ADNI and NA-ADNI early AD population enrolled in this study. Baseline levels of CSF t-tau, p-tau, Mini-Mental State Examination, FAQ, and ADAS-cog13 were identified as prognostic factors in both J-ADNI and NA-ADNI. Based on a detailed subscale analysis on ADAS-cog13, four subscales (Q1: word recall, Q3: construction, Q4: delayed word recall, and Q8: word recognition) were identified as prognostic factors in both J-ADNI and NA-ADNI. DiscussionCharacterizing population with early AD can provide benefits for promoting efficiency in conducting AD clinical trials for disease-modifying treatments. Thus, implementing these prognostic factors into clinical trials may be potentially a good method to enrich participants with early AD who are suitable for evaluating treatment effects.

Visualizing modules of coordinated structural brain atrophy during the course of conversion to Alzheimer's disease by applying methodology from gene co-expression analysis.

ObjectiveWe aimed to identify modularized structural atrophy of brain regions with a high degree of connectivity and its longitudinal changes associated with the progression of Alzheimer's disease (AD) using weighted gene co-expression network analysis (WGCNA), which is an unsupervised hierarchical clustering method originally used in genetic analysis.MethodsWe included participants with late mild cognitive impairment (MCI) at baseline from the Japanese Alzheimer's Disease Neuroimaging Initiative (J-ADNI) study. We imputed normalized and Z-transformed structural volume or cortical thickness data of 164 parcellated brain regions/structures based on the calculations of the FreeSurfer software. We applied the WGCNA to extract modules with highly interconnected structural atrophic patterns and examined the correlation between the identified modules and clinical AD progression.ResultsWe included 204 participants from the baseline dataset, and performed a follow-up with 100 in the 36-month dataset of MCI cohort participants from the J-ADNI. In the univariate correlation or variable importance analysis, baseline atrophy in temporal lobe regions/structures significantly predicted clinical AD progression. In the WGCNA consensus analysis, co-atrophy modules associated with MCI conversion were first distributed in the temporal lobe and subsequently extended to adjacent parietal cortical regions in the following 36 months.ConclusionsWe identified coordinated modules of brain atrophy and demonstrated their longitudinal extension along with the clinical course of AD progression using WGCNA, which showed a good correspondence with previous pathological studies of the tau propagation theory. Our results suggest the potential applicability of this methodology, originating from genetic analyses, for the surrogate visualization of the underlying pathological progression in neurodegenerative diseases not limited to AD.

Japanese and North American Alzheimer's Disease Neuroimaging Initiative studies: Harmonization for international trials

IntroductionWe conducted Japanese Alzheimer's Disease Neuroimaging Initiative (J-ADNI) and compared the basic characteristics and progression profiles with those of ADNI in North America. MethodsA total of 537 Japanese subjects with normal cognition, late amnestic mild cognitive impairment (LMCI), or mild Alzheimer's disease (AD) were enrolled using the same criteria as ADNI. Rates of changes in representative cognitive or functional measures were compared for amyloid positron emission tomography- or cerebrospinal fluid amyloid β(1–42)-positive LMCI and mild AD between J-ADNI and ADNI. ResultsAmyloid positivity rates were significantly higher in normal cognition of ADNI but at similar levels in LMCI and mild AD between J-ADNI and ADNI. Profiles of decline in cognitive or functional measures in amyloid-positive LMCI in J-ADNI (n = 75) and ADNI (n = 269) were remarkably similar, whereas those in mild AD were milder in J-ADNI (n = 73) compared with ADNI (n = 230). DiscussionThese results support the feasibility of bridging of clinical trials in the prodromal stage of AD between Asia and western countries.

INCIDENCE AND FACTORS ASSOCIATED WITH THE ONSET OF POST-DURAL PUNCTURE HEADACHE: EXPERIENCE FROM THE JAPANESE ADNI AND REVIEW OF LITERATURE

High diagnostic accuracy of cerebral spinal fluid (CSF) biomarkers, such as Aβ1–42, total tau and phosphorylated tau, has been shown for Alzheimer's disease (AD). As utility of these biomarkers is recognized, collection of CSF by lumbar puncture is increasingly performed in memory clinics. Post-dural puncture headache (PDPH) is the most common adverse event associated with lumbar puncture. We investigated incidence of PDPH in Japanese AD Neuroimaging Initiative (J-ADNI) cohorts, and reviewed literature regarding incidence of PDPH in memory clinic populations to determine factors associated with the onset of PDPH, such as age, cognitive status, history of headache, puncture position, needle type, needle size, collected CSF volume, and rest after LP. Of the 303 LP procedures in J-ADNI cohorts, PDPH occurred in 8 subjects (incidence 2.6%). Of these, two cases were hospitalized, but their symptoms relieved without blood patch treatment. Incidence of PDPH in 9 previous reports ranged from 0.9 to 20.3%. Review of literature revealed that older age (4 of 7 reports) and atraumatic needles (3 of 3 reports) reduced incidence of PDPH in memory clinic populations, whereas rest after LP had no effect (0 of 3 reports). The other factors were inconsistent among the studies. LP appears to be a relatively safe procedure for the differential diagnosis of dementia for the elderly in clinical research and memory clinic setting. Meanwhile, it is recommended to use atraumatic needles to reduce incidence of PDPH when performing LP for younger subjects.

The first results of amyloid imaging in Japanese Alzheimer's Disease Neuroimaging Initiative (J-ADNI) study

The first results of amyloid imaging in Japanese Alzheimer's Disease Neuroimaging Initiative (J-ADNI) study

Geriatric Medicine, Japanese Alzheimer's Disease Neuroimaging Initiative and Biomarker Development

Due to a change in disease spectrum in aged countries, the primary role of geriatricians should be directed to an appropriate management and prevention of 1) cognitive decline and dementia, 2) swallowing and aspiration pneumonia and 3) falls and fractures. Management of dementia constitutes a central part in the practice of geriatric medicine in order to support independence of life in elderly people. The current paradigm of cognitive function-based testing for the diagnosis and treatment of Alzheimer's disease (AD) is going to drastically shift to a biomarker-based test approach, a shift that will correspond to the emergence of disease-modifying drugs. In addition, a new molecular imaging technique that visualizes neuronal protein deposits or pathological features has been developed in Japan and the U.S.A. Based on these achievements, the Alzheimer's Disease Neuroimaging Initiative (ADNI) was proposed and initiated in 2005. The ADNI is a long-term observational study being conducted in the U.S.A., Europe, Australia, and Japan using identical protocols. The objectives of ADNI are: 1) to establish methodology which will allow standard values related to long-term changes in imaging data, such as MRI and PET, in patients with AD and mild cognitive impairment and normal elderly persons; 2) to obtain clinical indices, psychological test data, and blood/cerebrospinal fluid biomarkers to demonstrate the validity of image-based surrogate markers; and 3) to establish optimum methods to monitor the therapeutic effects of disease-modifying drugs for AD. Patient enrollment in the Japanese ADNI has begun in July 2008. Imaging of AD pathology not only acts as a reliable biomarker with which to assay curative drug development by novel pharmaceutical companies, but it also helps health promotion toward AD prevention.