Predicting Progression from Mild Cognitive Impairment to Alzheimer's Dementia Using Clinical, MRI, and Plasma Biomarkers via Probabilistic Pattern Classification

Vascular biomarkers and ApoE4 expression in mild cognitive impairment and Alzheimer's disease

Vascular pathology and genetic markers such as apolipoprotein E allele ε4 (ApoE ε4) are risk factors for the progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD). In Panama, a high prevalence of vascular risk factors and an increase in the aging population, generate the need to investigate biomarkers using specific, sensitive, non-invasive and cost-efficient methods that could be used in primary care. The main objective of this study was to explore the association between vascular biomarkers such as intima-media thickness (IMT) and stenosis, ApoΕ ε4 and cognitive function in a sample of older adults, including healthy controls (n = 41), MCI (n = 33), and AD (n = 12). A descriptive and cross-sectional study was conducted. Participants were part of the Panama Aging Research Initiative (PARI), the first prospective study in aging in Panama. Assessments included a neuropsychological battery, ApoΕ ε4 genotyping and a Doppler ultrasound of the left carotid artery to examine the presence of vascular risk factors. Neuropsychological tests were combined to form six cognitive domains: Global cognition, language, visuospatial abilities, learning and memory, attention and executive functions. Multivariable analyses (using age, education, and ApoE ε4 expression as covariates) were conducted. Participants with increased IMT showed poorer performance in memory and those with carotid stenosis showed poorer performance in language, visuospatial abilities and attention, independent of age, education or ApoΕ ε4 expression. The results support the use of vascular markers in cognitive assessments of aged individuals.

How random is the random forest? Random forest algorithm on the service of structural imaging biomarkers for Alzheimer's disease: from Alzheimer's disease neuroimaging initiative (ADNI) database

Neuroinformatics is a fascinating research field that applies computational models and analytical tools to high dimensional experimental neuroscience data for a better understanding of how the brain functions or dysfunctions in brain diseases. Neuroinformaticians work in the intersection of neuroscience and informatics supporting the integration of various sub-disciplines (behavioural neuroscience, genetics, cognitive psychology, etc.) working on brain research. Neuroinformaticians are the pathway of information exchange between informaticians and clinicians for a better understanding of the outcome of computational models and the clinical interpretation of the analysis. Machine learning is one of the most significant computational developments in the last decade giving tools to neuroinformaticians and finally to radiologists and clinicians for an automatic and early diagnosis-prognosis of a brain disease. Random forest (RF) algorithm has been successfully applied to high-dimensional neuroimaging data for feature reduction and also has been applied to classify the clinical label of a subject using single or multi-modal neuroimaging datasets. Our aim was to review the studies where RF was applied to correctly predict the Alzheimer's disease (AD), the conversion from mild cognitive impairment (MCI) and its robustness to overfitting, outliers and handling of non-linear data. Finally, we described our RF-based model that gave us the 1st position in an international challenge for automated prediction of MCI from MRI data.

Neuronal levels and sequence of tau modulate the power of brain rhythms

Neural network dysfunction may contribute to functional decline and disease progression in neurodegenerative disorders. Diverse lines of evidence suggest that neuronal accumulation of tau promotes network dysfunction and cognitive decline. The A152T-variant of human tau (hTau-A152T) increases the risk of Alzheimer's disease (AD) and several other tauopathies. When overexpressed in neurons of transgenic mice, it causes age-dependent neuronal loss and cognitive decline, as well as non-convulsive epileptic activity, which is also seen in patients with AD. Using intracranial EEG recordings with electrodes implanted over the parietal cortex, we demonstrate that hTau-A152T increases the power of brain oscillations in the 0.5-6 Hz range more than wildtype human tau in transgenic lines with comparable levels of human tau protein in brain, and that genetic ablation of endogenous tau in Mapt^-/- mice decreases the power of these oscillations as compared to wildtype controls. Suppression of hTau-A152T production in doxycycline-regulatable transgenic mice reversed their abnormal network activity. Treatment of hTau-A152T mice with the antiepileptic drug levetiracetam also rapidly and persistently reversed their brain dysrhythmia and network hypersynchrony. These findings suggest that both the level and the sequence of tau modulate the power of specific brain oscillations. The potential of EEG spectral changes as a biomarker deserves to be explored in clinical trials of tau-lowering therapeutics. Our results also suggest that levetiracetam treatment is able to counteract tau-dependent neural network dysfunction. Tau reduction and levetiracetam treatment may be of benefit in AD and other conditions associated with brain dysrhythmias and network hypersynchrony.

Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer's Disease using structural MR and FDG-PET images

Alzheimer's Disease (AD) is a progressive neurodegenerative disease where biomarkers for disease based on pathophysiology may be able to provide objective measures for disease diagnosis and staging. Neuroimaging scans acquired from MRI and metabolism images obtained by FDG-PET provide in-vivo measurements of structure and function (glucose metabolism) in a living brain. It is hypothesized that combining multiple different image modalities providing complementary information could help improve early diagnosis of AD. In this paper, we propose a novel deep-learning-based framework to discriminate individuals with AD utilizing a multimodal and multiscale deep neural network. Our method delivers 82.4% accuracy in identifying the individuals with mild cognitive impairment (MCI) who will convert to AD at 3 years prior to conversion (86.4% combined accuracy for conversion within 1-3 years), a 94.23% sensitivity in classifying individuals with clinical diagnosis of probable AD, and a 86.3% specificity in classifying non-demented controls improving upon results in published literature.

Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion

In this paper, we aim to predict conversion and time-to-conversion of mild cognitive impairment (MCI) patients using multi-modal neuroimaging data and clinical data, via cross-sectional and longitudinal studies. However, such data are often heterogeneous, high-dimensional, noisy, and incomplete. We thus propose a framework that includes sparse feature selection, low-rank affinity pursuit denoising (LRAD), and low-rank matrix completion (LRMC) in this study. Specifically, we first use sparse linear regressions to remove unrelated features. Then, considering the heterogeneity of the MCI data, which can be assumed as a union of multiple subspaces, we propose to use a low rank subspace method (i.e., LRAD) to denoise the data. Finally, we employ LRMC algorithm with three data fitting terms and one inequality constraint for joint conversion and time-to-conversion predictions. Our framework aims to answer a very important but yet rarely explored question in AD study, i.e., when will the MCI convert to AD? This is different from survival analysis, which provides the probabilities of conversion at different time points that are mainly used for global analysis, while our time-to-conversion prediction is for each individual subject. Evaluations using the ADNI dataset indicate that our method outperforms conventional LRMC and other state-of-the-art methods. Our method achieves a maximal pMCI classification accuracy of 84% and time prediction correlation of 0.665.

Machine Learning-based Individual Assessment of Cortical Atrophy Pattern in Alzheimer's Disease Spectrum: Development of the Classifier and Longitudinal Evaluation

To develop a new method for measuring Alzheimer's disease (AD)-specific similarity of cortical atrophy patterns at the individual-level, we employed an individual-level machine learning algorithm. A total of 869 cognitively normal (CN) individuals and 473 patients with probable AD dementia who underwent high-resolution 3T brain MRI were included. We propose a machine learning-based method for measuring the similarity of an individual subject's cortical atrophy pattern with that of a representative AD patient cohort. In addition, we validated this similarity measure in two longitudinal cohorts consisting of 79 patients with amnestic-mild cognitive impairment (aMCI) and 27 patients with probable AD dementia. Surface-based morphometry classifier for discriminating AD from CN showed sensitivity and specificity values of 87.1% and 93.3%, respectively. In the longitudinal validation study, aMCI-converts had higher atrophy similarity at both baseline (p < 0.001) and first year visits (p < 0.001) relative to non-converters. Similarly, AD patients with faster decline had higher atrophy similarity than slower decliners at baseline (p = 0.042), first year (p = 0.028), and third year visits (p = 0.027). The AD-specific atrophy similarity measure is a novel approach for the prediction of dementia risk and for the evaluation of AD trajectories on an individual subject level.

Increased Serum miR-206 Level Predicts Conversion from Amnestic Mild Cognitive Impairment to Alzheimer's Disease: A 5-Year Follow-up Study

Evidence suggests that individuals with amnestic mild cognitive impairment (aMCI) tend to progress to probable Alzheimer's disease (AD) with aging. This study was performed to examine whether circulating miRNAs could be potential predictors for the progression of aMCI to AD. A total of 458 patients with aMCI were included in this study, and the clinical data were collected at two time points: the baseline and the follow-up assessment. These aMCI patients were classified into two groups after 5 years: aMCI-stable group (n = 330) and AD-conversion group (n = 128). The expression of miR-206 and miR-132 and the levels of BDNF and SIRT1 in serum were detected using a quantitative real-time RT-PCR (qPCR) and the ELISA method, respectively. Kaplan-Meier method (Log-rank test) was used for univariate survival analysis. Cox proportional hazard model was used to estimate the prognostic value of miRNAs in conversion from aMCI to AD. At the baseline, serum levels of miR-206 in aMCI-AD group were significantly elevated compared to aMCI-aMCI group and the same trend was found at 5-year follow-up time point as well. There were no significant differences in serum levels of miR-132 between the conversion and non-conversion group at both time points. Kaplan-Meier analysis showed significant correlation between AD conversion and higher serum levels of miR-206 for aMCI patients (HR = 3.60, 95% CI: 2.51- 5.36, p < 0.001). Multivariate Cox regression analysis revealed that serum miR-206 and its target BDNF were significant independent predictors for AD conversion (HR = 4.22, p < 0.001). These results suggested that increased serum miR-206 level might be a potential predictor of conversion from aMCI to AD.

Association of Peripheral Interleukin-6 with Global Cognitive Decline in Non-demented Adults: A Meta-Analysis of Prospective Studies

Background: Elevated biomarkers of systemic inflammation have been reported in individuals with cognitive decline, however, most of the literature concerns cross-sectional analyses that have produced mixed results. This study investigates the etiology of this association by performing meta-analyses on prospective studies investigating the relationship between baseline interleukin-6 (IL-6), an established marker of peripheral inflammation, with cognitive decline risk in non-demented adults at follow-up.

Methods: We reviewed studies reporting peripheral IL-6 with future cognitive decline, up to February 2017 by searching the PubMed, Science Direct, Scopus and Google Scholar databases. Studies which contained odds ratios (ORs) for the association between circulating baseline IL-6 and longitudinal cognitive performance in non-demented community dwelling older adults were pooled in random-effects models.

Results: The literature search retrieved 5,642 potential articles, of which 7 articles containing 8 independent aging cohorts were eligible for review. Collectively, these studies included 15,828 participants at baseline. Those with high circulating IL-6 were 1.42 times more likely to experience global cognitive decline at follow-up, over a 2–7-year period, compared to those with low IL-6 (OR 1.42, 95% CI 1.18–1.70; p < 0.001). Subgroup and sensitivity analyses suggests that this association is independent of the study sample size, duration of follow-up and cognitive assessments used.

Conclusions: These results add further evidence for the association between high peripheral inflammation, as measured by blood IL-6, and global cognitive decline. Measuring circulating IL-6 may be a useful indication for future cognitive health.

Gait in Mild Alzheimer's Disease: Feasibility of Multi-Center Measurement in the Clinic and Home with Body-Worn Sensors: A Pilot Study

Gait is emerging as a potential diagnostic tool for cognitive decline. The 'Deep and Frequent Phenotyping for Experimental Medicine in Dementia Study' (D&FP) is a multicenter feasibility study embedded in the United Kingdom Dementia Platform designed to determine participant acceptability and feasibility of extensive and repeated phenotyping to determine the optimal combination of biomarkers to detect disease progression and identify early risk of Alzheimer's disease (AD). Gait is included as a clinical biomarker. The tools to quantify gait in the clinic and home, and suitability for multi-center application have not been examined. Six centers from the National Institute for Health Research Translational Research Collaboration in Dementia initiative recruited 20 individuals with early onset AD. Participants wore a single wearable (tri-axial accelerometer) and completed both clinic-based and free-living gait assessment. A series of macro (behavioral) and micro (spatiotemporal) characteristics were derived from the resultant data using previously validated algorithms. Results indicate good participant acceptability, and potential for use of body-worn sensors in both the clinic and the home. Recommendations for future studies have been provided. Gait has been demonstrated to be a feasible and suitable measure, and future research should examine its suitability as a biomarker in AD.

Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and alzheimer's disease patients: From the alzheimer's disease neuroimaging initiative (ADNI) database

BACKGROUND

In the era of computer-assisted diagnostic tools for various brain diseases, Alzheimer's disease (AD) covers a large percentage of neuroimaging research, with the main scope being its use in daily practice. However, there has been no study attempting to simultaneously discriminate among Healthy Controls (HC), early mild cognitive impairment (MCI), late MCI (cMCI) and stable AD, using features derived from a single modality, namely MRI.

NEW METHOD

Based on preprocessed MRI images from the organizers of a neuroimaging challenge,³ we attempted to quantify the prediction accuracy of multiple morphological MRI features to simultaneously discriminate among HC, MCI, cMCI and AD. We explored the efficacy of a novel scheme that includes multiple feature selections via Random Forest from subsets of the whole set of features (e.g. whole set, left/right hemisphere etc.), Random Forest classification using a fusion approach and ensemble classification via majority voting. From the ADNI database, 60 HC, 60 MCI, 60 cMCI and 60 CE were used as a training set with known labels. An extra dataset of 160 subjects (HC: 40, MCI: 40, cMCI: 40 and AD: 40) was used as an external blind validation dataset to evaluate the proposed machine learning scheme.

RESULTS

In the second blind dataset, we succeeded in a four-class classification of 61.9% by combining MRI-based features with a Random Forest-based Ensemble Strategy. We achieved the best classification accuracy of all teams that participated in this neuroimaging competition.

COMPARISON WITH EXISTING METHOD(S)

The results demonstrate the effectiveness of the proposed scheme to simultaneously discriminate among four groups using morphological MRI features for the very first time in the literature.

CONCLUSIONS

Hence, the proposed machine learning scheme can be used to define single and multi-modal biomarkers for AD.

A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages

Neuroimaging has made it possible to measure pathological brain changes associated with Alzheimer's disease (AD) in vivo. Over the past decade, these measures have been increasingly integrated into imaging signatures of AD by means of classification frameworks, offering promising tools for individualized diagnosis and prognosis. We reviewed neuroimaging-based studies for AD and mild cognitive impairment classification, selected after online database searches in Google Scholar and PubMed (January, 1985-June, 2016). We categorized these studies based on the following neuroimaging modalities (and sub-categorized based on features extracted as a post-processing step from these modalities): i) structural magnetic resonance imaging [MRI] (tissue density, cortical surface, and hippocampal measurements), ii) functional MRI (functional coherence of different brain regions, and the strength of the functional connectivity), iii) diffusion tensor imaging (patterns along the white matter fibers), iv) fluorodeoxyglucose positron emission tomography (FDG-PET) (metabolic rate of cerebral glucose), and v) amyloid-PET (amyloid burden). The studies reviewed indicate that the classification frameworks formulated on the basis of these features show promise for individualized diagnosis and prediction of clinical progression. Finally, we provided a detailed account of AD classification challenges and addressed some future research directions.

Longitudinal measurement and hierarchical classification framework for the prediction of Alzheimer's disease

Accurate prediction of Alzheimer’s disease (AD) is important for the early diagnosis and treatment of this condition. Mild cognitive impairment (MCI) is an early stage of AD. Therefore, patients with MCI who are at high risk of fully developing AD should be identified to accurately predict AD. However, the relationship between brain images and AD is difficult to construct because of the complex characteristics of neuroimaging data. To address this problem, we present a longitudinal measurement of MCI brain images and a hierarchical classification method for AD prediction. Longitudinal images obtained from individuals with MCI were investigated to acquire important information on the longitudinal changes, which can be used to classify MCI subjects as either MCI conversion (MCIc) or MCI non-conversion (MCInc) individuals. Moreover, a hierarchical framework was introduced to the classifier to manage high feature dimensionality issues and incorporate spatial information for improving the prediction accuracy. The proposed method was evaluated using 131 patients with MCI (70 MCIc and 61 MCInc) based on MRI scans taken at different time points. Results showed that the proposed method achieved 79.4% accuracy for the classification of MCIc versus MCInc, thereby demonstrating very promising performance for AD prediction.

A Nonparametric Approach for Mild Cognitive Impairment to AD Conversion Prediction: Results on Longitudinal Data

The goal of this study is to introduce a nonparametric technique for predicting conversion from Mild Cognitive impairment (MCI)-to-Alzheimer's disease (AD). Progression of a slowly progressing disease such as AD benefits from the use of longitudinal data; however, research till now is limited due to the insufficient patient data and short follow-up time. A small dataset size invalidates the estimation of underlying disease progression model; hence, a supervised nonparametric method is proposed. While depicting a real-world setting, longitudinal data of three years are employed for training, whereas only the baseline visit's data is used for validation. The train set is preprocessed for extraction of two dense clusters representing the subjects who remain stable at MCI or progress to AD after three years of the baseline visit. Similarity between these clusters and the test point is calculated in Euclidean space. Multiple features from two modalities of biomarkers, i.e., neuropsychological measures (NM) and structural magnetic resonance imaging (MRI) morphometry are also analyzed. Due to the limited MCI dataset size (NM: 145, MRI: 52, NM+MRI: 29), leave-one-out cross validation setup is employed for performance evaluation. The algorithm performance is noted for both unimodal case and bimodal cases. Superior performance (accuracy: 89.66%, sensitivity: 87.50%, specificity: 92.31%, precision: 93.33%) is delivered by multivariate predictors. Three notable conclusions of this study are: 1) Longitudinal data are more powerful than the temporal data, 2) MRI is a better predictor of MCI-to-AD conversion than NM, and 3) multivariate predictors outperform single predictor models.

Type 2 diabetes mellitus might be a risk factor for mild cognitive impairment progressing to Alzheimer's disease

BACKGROUND

Mild cognitive impairment (MCI) is the prodromal stage of Alzheimer's disease (AD), so identification of the related risk factors can be helpful. Although the association between type 2 diabetes mellitus (T2DM) and these modest changes in cognition is well established, whether T2DM will promote the transformation of MCI into AD is not a unified conclusion.

OBJECTIVE

This study aims to explore the relationship between T2DM and MCI in the elderly population living in the community in Shanghai, People's Republic of China.

METHODS

A total of 197 participants were included in the study. They were screened for T2DM, hyperlipidemia, traumatic brain injury, and family history of dementia. The Mini-Mental State Examination and the Montreal Cognitive Assessment were used to assess cognitive function. The diagnosis of AD was made according to Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition, whereas the diagnosis of MCI was made according to Petersen's criteria. Then, we investigated the relation between T2DM and MCI.

RESULTS

A total of 82 (41.6%) participants had no cognitive impairment, 82 (41.6%) participants had MCI, and 33 (16.8%) participants had AD. Multivariate logistic regression models demonstrated that T2DM was a risk factor for AD (odds ratio =49.723, 95% CI =21.173-111.987).

CONCLUSION

T2DM might be a risk factor for MCI progressing into AD.