In this Seminar, we highlight the main developments in the field of Alzheimer's disease. The most recent data indicate that, by 2050, the prevalence of dementia will double in Europe and triple worldwide, and that estimate is 3 times higher when based on a biological (rather than clinical) definition of Alzheimer's disease. The earliest phase of Alzheimer's disease (cellular phase) happens in parallel with accumulating amyloid β, inducing the spread of tau pathology. The risk of Alzheimer's disease is 60-80% dependent on heritable factors, with more than 40 Alzheimer's disease-associated genetic risk loci already identified, of which the APOE alleles have the strongest association with the disease. Novel biomarkers include PET scans and plasma assays for amyloid β and phosphorylated tau, which show great promise for clinical and research use. Multidomain lifestyle-based prevention trials suggest cognitive benefits in participants with increased risk of dementia. Lifestyle factors do not directly affect Alzheimer's disease pathology, but can still contribute to a positive outcome in individuals with Alzheimer's disease. Promising pharmacological treatments are poised at advanced stages of clinical trials and include anti-amyloid β, anti-tau, and anti-inflammatory strategies.Copyright © 2021 Elsevier Ltd. All rights reserved.

As individuals age, the quality of cognitive function becomes an increasingly important topic. The concept of mild cognitive impairment (MCI) has evolved over the past 2 decades to represent a state of cognitive function between that seen in normal aging and dementia. As such, it is important for health care providers to be aware of the condition and place it in the appropriate clinical context.Numerous international population-based studies have been conducted to document the frequency of MCI, estimating its prevalence to be between 15% and 20% in persons 60 years and older, making it a common condition encountered by clinicians. The annual rate in which MCI progresses to dementia varies between 8% and 15% per year, implying that it is an important condition to identify and treat. In those MCI cases destined to develop Alzheimer disease, biomarkers are emerging to help identify etiology and predict progression. However, not all MCI is due to Alzheimer disease, and identifying subtypes is important for possible treatment and counseling. If treatable causes are identified, the person with MCI might improve.MCI is an important clinical entity to identify, and while uncertainties persist, clinicians need to be aware of its diagnostic features to enable them to counsel patients. MCI remains an active area of research as numerous randomized controlled trials are being conducted to develop effective treatments.

An MRI time course of 512 echo-planar images (EPI) in resting human brain obtained every 250 ms reveals fluctuations in signal intensity in each pixel that have a physiologic origin. Regions of the sensorimotor cortex that were activated secondary to hand movement were identified using functional MRI methodology (FMRI). Time courses of low frequency (< 0.1 Hz) fluctuations in resting brain were observed to have a high degree of temporal correlation (P < 10(-3)) within these regions and also with time courses in several other regions that can be associated with motor function. It is concluded that correlation of low frequency fluctuations, which may arise from fluctuations in blood oxygenation or flow, is a manifestation of functional connectivity of the brain.

Amyloid deposition is present in 20-50% of nondemented older adults yet the functional consequences remain unclear. The current study found that amyloid accumulation is correlated with functional disruption of the default network as measured by intrinsic activity correlations. Clinically normal participants (n = 38, aged 60-88 years) were characterized using (11)C-labeled Pittsburgh Compound B positron emission tomography imaging to estimate fibrillar amyloid burden and, separately, underwent functional magnetic resonance imaging (fMRI). The integrity of the default network was estimated by correlating rest-state fMRI time courses extracted from a priori regions including the posterior cingulate, lateral parietal, and medial prefrontal cortices. Clinically normal participants with high amyloid burden displayed significantly reduced functional correlations within the default network relative to participants with low amyloid burden. These reductions were also observed when amyloid burden was treated as a continuous, rather than a dichotomous, measure and when controlling for age and structural atrophy. Whole-brain analyses initiated by seeding the posterior cingulate cortex, a region of high amyloid burden in Alzheimer's disease, revealed significant disruption in the default network including functional disconnection of the hippocampal formation.

Deep learning (DL) is a family of machine learning methods that has gained considerable attention in the scientific community, breaking benchmark records in areas such as speech and visual recognition. DL differs from conventional machine learning methods by virtue of its ability to learn the optimal representation from the raw data through consecutive nonlinear transformations, achieving increasingly higher levels of abstraction and complexity. Given its ability to detect abstract and complex patterns, DL has been applied in neuroimaging studies of psychiatric and neurological disorders, which are characterised by subtle and diffuse alterations. Here we introduce the underlying concepts of DL and review studies that have used this approach to classify brain-based disorders. The results of these studies indicate that DL could be a powerful tool in the current search for biomarkers of psychiatric and neurologic disease. We conclude our review by discussing the main promises and challenges of using DL to elucidate brain-based disorders, as well as possible directions for future research.Copyright © 2017 The Authors. Published by Elsevier Ltd.. All rights reserved.

We used resting-state functional MRI to investigate spatial patterns of spontaneous brain activity in 22 healthy elderly subjects, as well as 16 mild cognitive impairment (MCI) and 16 Alzheimer's disease (AD) patients. The pattern of intrinsic brain activity was measured by examining the amplitude of low-frequency fluctuations (ALFF) of blood oxygen level dependent signal during rest. There were widespread ALFF differences among the three groups throughout the frontal, temporal, and parietal cortices. Both AD and MCI patients showed decreased activity mainly in the medial parietal lobe region and lentiform nucleus, while there was increased activity in the lateral temporal regions and superior frontal and parietal regions as compared with controls. Compared with MCI, the AD patients showed decreased activity in the medial prefrontal cortex and increased activity in the superior frontal gyrus and inferior and superior temporal gyri. Specifically, the most significant ALFF differences among the groups appeared in the posterior cingulate cortex, with a reduced pattern of activity when comparing healthy controls, MCI, and AD patients. Additionally, we also showed that the regions with ALFF changes had significant correlations with the cognitive performance of patients as measured by mini-mental state examination scores. Finally, while taking gray matter volume as covariates, the ALFF results were approximately consistent with those without gray matter correction, implying that the functional analysis could not be explained by regional atrophy. Together, our results demonstrate that there is a specific pattern of ALFF in AD and MCI, thus providing insights into biological mechanisms of the diseases.Copyright © 2010 Wiley-Liss, Inc.

Here we utilized resting-state functional magnetic resonance imaging (R-fMRI) to measure the amplitude of low-frequency fluctuations (ALFF) and fractional ALFF (fALFF) in 24 patients with amnestic mild cognitive impairment (aMCI) and 24 age- and sex-matched healthy controls. Two different frequency bands (slow-5: 0.01-0.027 Hz; slow-4: 0.027-0.073 Hz) were analyzed. We showed that there were widespread differences in ALFF/fALFF between the two bands in many brain regions, predominantly including the medial prefrontal cortex (MPFC), posterior cingulate cortex/precuneus (PCC/PCu), basal ganglia, and hippocampus/parahippocampal gyrus (PHG). Compared to controls, the aMCI patients had decreased ALFF/fALFF values in the PCC/PCu, MPFC, hippocampus/PHG, basal ganglia, and prefrontal regions, and increased ALFF/fALFF values mainly in several occipital and temporal regions. Specifically, we observed that the ALFF/fALFF abnormalities in the PCC/PCu, PHG, and several occipital regions were greater in the slow-5 band than in the slow-4 band. Finally, our results of functional analysis were not significantly influenced by the gray matter loss in the MCI patients, suggesting that the results reflect functional differences between groups. Together, our data suggest that aMCI patients have widespread abnormalities in intrinsic brain activity, and the abnormalities depend on the studied frequency bands of R-fMRI data.Copyright © 2010 Elsevier Inc. All rights reserved.

Alzheimer's disease (AD), the most prevalent cause of dementia in the elderly, is characterized by progressive cognitive and intellectual deficits. Most patients with mild cognitive impairment (MCI) are thought to be in a very early stage of AD. Resting-state functional magnetic resonance imaging reflects spontaneous brain activities and/or the endogenous/background neurophysiological process of the human brain. Regional Homogeneity (ReHo) can provide a fast method for mapping regional activity across the whole brain. Little has been previously published about where or how spontaneous activity differs between MCI and AD, although many previous fMRI studies have shown that the activity pattern is altered in MCI/AD. In the present study, we first used the ReHo method to explore differences in regional spontaneous activities throughout the whole brain between normal controls (NC) and people with MCI and with AD. A one-way ANOVA was performed to determine the regions in which the ReHo differs between the three groups, and then a post hoc analysis was performed to evaluate differences in the pattern among the three groups. Finally a correlation analysis was done between the ReHo index of these regions and clinical variables in order to evaluate the relationship between ReHo and cognitive measures in the AD and MCI groups. An exploratory classification analysis also demonstrated that ReHo measures were able to correctly separate subjects in 71.4% of the cases. Altered brain spontaneous activations were found in the medial prefrontal cortex, the bilateral posterior cingulate gyrus/precuneus and the left inferior parietal lobule (IPL) in both MCI and AD. In MCI, the ReHo index in the left IPL was higher than that of the NC, which could indicate the presence of a compensatory mechanism in MCI. More obviously, the correlation analysis indicated that the lower the memory and other cognitive abilities, the lower the ReHo in patients with MCI and AD. Combining our findings with the results in earlier studies, we propose that the spontaneous activity pattern in the resting state could potentially be used as a clinical marker for MCI/AD.Copyright © 2011 Elsevier Inc. All rights reserved.

Recent functional imaging studies have revealed coactivation in a distributed network of cortical regions that characterizes the resting state, or default mode, of the human brain. Among the brain regions implicated in this network, several, including the posterior cingulate cortex and inferior parietal lobes, have also shown decreased metabolism early in the course of Alzheimer's disease (AD). We reasoned that default-mode network activity might therefore be abnormal in AD. To test this hypothesis, we used independent component analysis to isolate the network in a group of 13 subjects with mild AD and in a group of 13 age-matched elderly controls as they performed a simple sensory-motor processing task. Three important findings are reported. Prominent coactivation of the hippocampus, detected in all groups, suggests that the default-mode network is closely involved with episodic memory processing. The AD group showed decreased resting-state activity in the posterior cingulate and hippocampus, suggesting that disrupted connectivity between these two regions accounts for the posterior cingulate hypometabolism commonly detected in positron emission tomography studies of early AD. Finally, a goodness-of-fit analysis applied at the individual subject level suggests that activity in the default-mode network may ultimately prove a sensitive and specific biomarker for incipient AD.

With the increase in large multimodal cohorts and high-throughput technologies, the potential for discovering novel biomarkers is no longer limited by data set size. Artificial intelligence (AI) and machine learning approaches have been developed to detect novel biomarkers and interactions in complex data sets. We discuss exemplar uses and evaluate current applications and limitations of AI to discover novel biomarkers. Remaining challenges include a lack of diversity in the data sets available, the sheer complexity of investigating interactions, the invasiveness and cost of some biomarkers, and poor reporting in some studies. Overcoming these challenges will involve collecting data from underrepresented populations, developing more powerful AI approaches, validating the use of noninvasive biomarkers, and adhering to reporting guidelines. By harnessing rich multimodal data through AI approaches and international collaborative innovation, we are well positioned to identify clinically useful biomarkers that are accurate, generalizable, unbiased, and acceptable in clinical practice. HIGHLIGHTS: Artificial intelligence and machine learning approaches may accelerate dementia biomarker discovery. Remaining challenges include data set suitability due to size and bias in cohort selection. Multimodal data, diverse data sets, improved machine learning approaches, real-world validation, and interdisciplinary collaboration are required.© 2023 The Authors. Alzheimer's & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer's Association.

Much effort in recent years has focused on understanding the effects of Alzheimer's disease (AD) on neural function. This effort has resulted in an enormous number of papers describing different facets of the functional derangement seen in AD. A particularly important tool for these investigations has been resting-state functional connectivity. Attempts to comprehensively synthesize resting-state functional connectivity results have focused on the potential utility of functional connectivity as a biomarker for disease risk, disease staging, or prognosis. While these are all appropriate uses of this technique, the purpose of this review is to examine how functional connectivity disruptions inform our understanding of AD pathophysiology. Here, we examine the rationale and methodological considerations behind functional connectivity studies and then provide a critical review of the existing literature. In conclusion, we propose a hypothesis regarding the development and spread of functional connectivity deficits seen in AD.

We performed a systematic review and meta-analysis of the Alzheimer's disease (AD) literature to examine consistency of functional connectivity alterations in AD dementia and mild cognitive impairment, using resting-state functional magnetic resonance imaging.Studies were screened using a standardized procedure. Multiresolution statistics were performed to assess the spatial consistency of findings across studies.Thirty-four studies were included (1363 participants, average 40 per study). Consistent alterations in connectivity were found in the default mode, salience, and limbic networks in patients with AD dementia, mild cognitive impairment, or in both groups. We also identified a strong tendency in the literature toward specific examination of the default mode network.Convergent evidence across the literature supports the use of resting-state connectivity as a biomarker of AD. The locations of consistent alterations suggest that highly connected hub regions in the brain might be an early target of AD.

Spontaneous fluctuations are a hallmark of recordings of neural signals, emergent over time scales spanning milliseconds and tens of minutes. However, investigations of intrinsic brain organization based on resting-state functional magnetic resonance imaging have largely not taken into account the presence and potential of temporal variability, as most current approaches to examine functional connectivity (FC) implicitly assume that relationships are constant throughout the length of the recording. In this work, we describe an approach to assess whole-brain FC dynamics based on spatial independent component analysis, sliding time window correlation, and k-means clustering of windowed correlation matrices. The method is applied to resting-state data from a large sample (n = 405) of young adults. Our analysis of FC variability highlights particularly flexible connections between regions in lateral parietal and cingulate cortex, and argues against a labeling scheme where such regions are treated as separate and antagonistic entities. Additionally, clustering analysis reveals unanticipated FC states that in part diverge strongly from stationary connectivity patterns and challenge current descriptions of interactions between large-scale networks. Temporal trends in the occurrence of different FC states motivate theories regarding their functional roles and relationships with vigilance/arousal. Overall, we suggest that the study of time-varying aspects of FC can unveil flexibility in the functional coordination between different neural systems, and that the exploitation of these dynamics in further investigations may improve our understanding of behavioral shifts and adaptive processes.

The brain must dynamically integrate, coordinate, and respond to internal and external stimuli across multiple time scales. Non-invasive measurements of brain activity with fMRI have greatly advanced our understanding of the large-scale functional organization supporting these fundamental features of brain function. Conclusions from previous resting-state fMRI investigations were based upon static descriptions of functional connectivity (FC), and only recently studies have begun to capitalize on the wealth of information contained within the temporal features of spontaneous BOLD FC. Emerging evidence suggests that dynamic FC metrics may index changes in macroscopic neural activity patterns underlying critical aspects of cognition and behavior, though limitations with regard to analysis and interpretation remain. Here, we review recent findings, methodological considerations, neural and behavioral correlates, and future directions in the emerging field of dynamic FC investigations. Copyright © 2013 Elsevier Inc. All rights reserved.

Alzheimer's disease (AD) patients show altered patterns of functional connectivity (FC) on resting state functional magnetic resonance imaging (RSfMRI) scans. It is yet unclear which RSfMRI measures are most informative for the individual classification of AD patients. We investigated this using RSfMRI scans from 77 AD patients (MMSE = 20.4 ± 4.5) and 173 controls (MMSE = 27.5 ± 1.8). We calculated i) FC matrices between resting state components as obtained with independent component analysis (ICA), ii) the dynamics of these FC matrices using a sliding window approach, iii) the graph properties (e.g., connection degree, and clustering coefficient) of the FC matrices, and iv) we distinguished five FC states and administered how long each subject resided in each of these five states. Furthermore, for each voxel we calculated v) FC with 10 resting state networks using dual regression, vi) FC with the hippocampus, vii) eigenvector centrality, and viii) the amplitude of low frequency fluctuations (ALFF). These eight measures were used separately as predictors in an elastic net logistic regression, and combined in a group lasso logistic regression model. We calculated the area under the receiver operating characteristic curve plots (AUC) to determine classification performance. The AUC values ranged between 0.51 and 0.84 and the highest were found for the FC matrices (0.82), FC dynamics (0.84) and ALFF (0.82). The combination of all measures resulted in an AUC of 0.85. We show that it is possible to obtain moderate to good AD classification using RSfMRI scans. FC matrices, FC dynamics and ALFF are most discriminative and the combination of all the resting state measures improves classification accuracy slightly.Copyright © 2017 Elsevier Inc. All rights reserved.

The resting-state functional MRI (rs-fMRI) has been demonstrated as a valuable neuroimaging tool to identify mild cognitive impairment (MCI) patients. Previous studies showed network breakdown in MCI patients with thresholded rs-fMRI connectivity networks. Recently, machine learning techniques have assisted MCI diagnosis by integrating information from multiple networks constructed with a range of thresholds. However, due to the difficulty of searching optimal thresholds, they are often predetermined and uniformly applied to the entire network. Here, we propose an element-wise thresholding strategy to dynamically construct multiple functional networks, i.e., using possibly different thresholds for different elements in the connectivity matrix. These dynamically generated networks are then integrated with a network fusion scheme to capture their common and complementary information. Finally, the features extracted from the fused network are fed into support vector machine (SVM) for MCI diagnosis. Compared to the previous methods, our proposed framework can greatly improve MCI classification performance.

Dynamic functional connectivity captures temporal variations of functional connectivity during MRI acquisition and it may be a suitable method to detect cognitive changes in Parkinson's disease. In this study, we evaluated 118 patients with Parkinson's disease matched for age, sex and education with 35 healthy control subjects. Patients with Parkinson's disease were classified with normal cognition (n = 52), mild cognitive impairment (n = 46), and dementia (n = 20) based on an extensive neuropsychological evaluation. Resting state functional MRI and a sliding-window approach were used to study the dynamic functional connectivity. Dynamic analysis suggested two distinct connectivity 'States' across the entire group: a more frequent, segregated brain state characterized by the predominance of within-network connections, State I, and a less frequent, integrated state with strongly connected functional internetwork components, State II. In Parkinson's disease, State I occurred 13.89% more often than in healthy control subjects, paralleled by a proportional reduction of State II. Parkinson's disease subgroups analyses showed the segregated state occurred more frequently in Parkinson's disease dementia than in mild cognitive impairment and normal cognition groups. Further, patients with Parkinson's disease dementia dwelled significantly longer in the segregated State I, and showed a significant lower number of transitions to the strongly interconnected State II compared to the other subgroups. Our study indicates that dementia in Parkinson's disease is characterized by altered temporal properties in dynamic connectivity. In addition, our results show that increased dwell time in the segregated state and reduced number of transitions between states are associated with presence of dementia in Parkinson's disease. Further studies on dynamic functional connectivity changes could help to better understand the progressive dysfunction of networks between Parkinson's disease cognitive states.© The Author(s) (2019). Published by Oxford University Press on behalf of the Guarantors of Brain. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

The interrelationships between pathological processes and emerging clinical phenotypes in Alzheimer's disease (AD) are important yet complicated to study, because the brain is a complex network where local disruptions can have widespread effects. Recently, properties in brain networks obtained with neuroimaging techniques have been studied in AD with tools from graph theory. However, the interpretation of graph alterations remains unclear, because the definition of connectivity depends on the imaging modality used. Here we examined which graph properties have been consistently reported to be disturbed in AD studies, using a heuristically defined "graph space" to investigate which theoretical models can best explain graph alterations in AD. Findings from structural and functional graphs point to a loss of highly connected areas in AD. However, studies showed considerable variability in reported group differences of most graph properties. This suggests that brain graphs might not be isometric, which complicates the interpretation of graph measurements. We highlight confounding factors such as differences in graph construction methods and provide recommendations for future research.Copyright © 2013 Elsevier Inc. All rights reserved.

Recent evidence suggests that some brain areas act as hubs interconnecting distinct, functionally specialized systems. These nexuses are intriguing because of their potential role in integration and also because they may augment metabolic cascades relevant to brain disease. To identify regions of high connectivity in the human cerebral cortex, we applied a computationally efficient approach to map the degree of intrinsic functional connectivity across the brain. Analysis of two separate functional magnetic resonance imaging datasets (each n = 24) demonstrated hubs throughout heteromodal areas of association cortex. Prominent hubs were located within posterior cingulate, lateral temporal, lateral parietal, and medial/lateral prefrontal cortices. Network analysis revealed that many, but not all, hubs were located within regions previously implicated as components of the default network. A third dataset (n = 12) demonstrated that the locations of hubs were present across passive and active task states, suggesting that they reflect a stable property of cortical network architecture. To obtain an accurate reference map, data were combined across 127 participants to yield a consensus estimate of cortical hubs. Using this consensus estimate, we explored whether the topography of hubs could explain the pattern of vulnerability in Alzheimer's disease (AD) because some models suggest that regions of high activity and metabolism accelerate pathology. Positron emission tomography amyloid imaging in AD (n = 10) compared with older controls (n = 29) showed high amyloid-beta deposition in the locations of cortical hubs consistent with the possibility that hubs, while acting as critical way stations for information processing, may also augment the underlying pathological cascade in AD.

Brain networks or 'connectomes' include a minority of highly connected hub nodes that are functionally valuable, because their topological centrality supports integrative processing and adaptive behaviours. Recent studies also suggest that hubs have higher metabolic demands and longer-distance connections than other brain regions, and therefore could be considered biologically costly. Assuming that hubs thus normally combine both high topological value and high biological cost, we predicted that pathological brain lesions would be concentrated in hub regions. To test this general hypothesis, we first identified the hubs of brain anatomical networks estimated from diffusion tensor imaging data on healthy volunteers (n = 56), and showed that computational attacks targeted on hubs disproportionally degraded the efficiency of brain networks compared to random attacks. We then prepared grey matter lesion maps, based on meta-analyses of published magnetic resonance imaging data on more than 20 000 subjects and 26 different brain disorders. Magnetic resonance imaging lesions that were common across all brain disorders were more likely to be located in hubs of the normal brain connectome (P < 10(-4), permutation test). Specifically, nine brain disorders had lesions that were significantly more likely to be located in hubs (P < 0.05, permutation test), including schizophrenia and Alzheimer's disease. Both these disorders had significantly hub-concentrated lesion distributions, although (almost completely) distinct subsets of cortical hubs were lesioned in each disorder: temporal lobe hubs specifically were associated with higher lesion probability in Alzheimer's disease, whereas in schizophrenia lesions were concentrated in both frontal and temporal cortical hubs. These results linking pathological lesions to the topological centrality of nodes in the normal diffusion tensor imaging connectome were generally replicated when hubs were defined instead by the meta-analysis of more than 1500 task-related functional neuroimaging studies of healthy volunteers to create a normative functional co-activation network. We conclude that the high cost/high value hubs of human brain networks are more likely to be anatomically abnormal than non-hubs in many (if not all) brain disorders. © The Author (2014). Published by Oxford University Press on behalf of the Guarantors of Brain.

\n Cognitive and behavioral deficits in Alzheimer’s disease (AD) and frontotemporal dementia (FTD) arise alongside gray matter atrophy and altered functional connectivity, yet the structure-function relationship across the dementia spectrum remains unclear. Here we combine structural and functional MRI from 221 patients—AD (\n n\n  = 82), behavioral variant FTD (\n n\n  = 41), corticobasal syndrome (\n n\n  = 27), and nonfluent (\n n\n  = 34) or semantic (\n n\n  = 37) variant primary progressive aphasia—and 100 cognitively normal individuals. Partial least-squares regression reveals three structure–function components. Component 1 links cumulative atrophy to sensorimotor hypo-connectivity and hyper-connectivity in association cortical and subcortical brain regions. Components 2 and 3 tie focal, syndrome-specific atrophy to peri-lesional hypo-connectivity and distal hyper-connectivity. Structural and functional component scores explain 34% of the variance in global and domain-specific cognitive deficits on average. The functional connectivity changes reflect alterations of intrinsic activity gradients. Eigenmode analysis shows that atrophy relates to reduced gradient amplitudes and narrowed phase angles between gradients, offering a mechanistic account of network collapse in neurodegeneration.\n

Mild cognitive impairment (MCI) is often a transitional state between normal aging and Alzheimer's disease (AD). When observed longitudinally, some MCI patients convert to AD, while a considerable portion either remains MCI or revert to a normal functioning state. This divergence has provided some enlightenment on a potential biomarker to be represented in the resting state brain activities of MCI patients with different post-hoc labels. Recent studies have shown impaired executive functions, other than typically explicated memory impairment with AD/MCI patients. This observation raises the question that whether or not the executive control network (ECN) was impaired, which pivotally supports the central executive functions. Given the fact that effective connectivity is a sufficient index in detecting resting brain abnormalities in AD/MCI, the current study specifically asks a question whether the effective connectivity patterns are differentiated in MCI patients with different post-hoc labels.We divided the MCI subjects into three groups depending on their progressive state obtained longitudinally: 1) 15 MCI-R subjects: MCI reverted to the normal functioning state and stabilized to the normal state in 24 months; 2) 35 MCI-S subjects: MCI patients maintained this disease in a stable state for 24 months; 3) 22 MCI-P subjects: MCI progressed to AD and stabilized to AD in 24 months, and 4) 39 age-matched normal control subjects (NC). We conducted a Granger causality analysis after identifying the core nodes of ECN in all of the subjects using Independent Component Analysis. Our findings revealed that different MCI groups presented different effective connectivity patterns within the ECN compared to the NC group. Specifically, (1) dorsolateral prefrontal cortex (dLPFC) and medial prefrontal cortex (mPFC) were the core nodes in the ECN network that exhibited different connecting patterns; (2) an effective connection circuit "R.dLPFC→ right caudate→ left thalamus→R.dLPFC" in the ECN showed different levels of damage; and (3) there were four pathways between the R.dLPFC and L.LP, and these four pathways were also different.Our results would help to understand the potential central mechanism of MCI patients. The differentiated effective connectivity of ECN may serve as a potential biomarker for early detection of AD, which may also provide a reference for clinical researchers to manipulate active but distinctive interventions for MCI patients who have different risks.Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Machine learning techniques are increasingly being used in making relevant predictions and inferences on individual subjects neuroimaging scan data. Previous studies have mostly focused on categorical discrimination of patients and matched healthy controls and more recently, on prediction of individual continuous variables such as clinical scores or age. However, these studies are greatly hampered by the large number of predictor variables (voxels) and low observations (subjects) also known as the curse-of-dimensionality or small-n-large-p problem. As a result, feature reduction techniques such as feature subset selection and dimensionality reduction are used to remove redundant predictor variables and experimental noise, a process which mitigates the curse-of-dimensionality and small-n-large-p effects. Feature reduction is an essential step before training a machine learning model to avoid overfitting and therefore improving model prediction accuracy and generalization ability. In this review, we discuss feature reduction techniques used with machine learning in neuroimaging studies.

Using the Pearson correlation coefficient to constructing functional brain network has been evidenced to be an effective means to diagnose different stages of mild cognitive impairment (MCI) disease. In this study, we investigated the efficacy of a classification framework to distinguish early mild cognitive impairment (EMCI) from late mild cognitive impairment (LMCI) by using the effective features derived from functional brain network of three frequency bands (full-band: 0.01-0.08 Hz; slow-4: 0.027-0.08 Hz; slow-5: 0.01-0.027 Hz) at Rest. Graphic theory was performed to calculate and analyze the relationship between changes in network connectivity. Subsequently, three different algorithms [minimal redundancy maximal relevance (mRMR), sparse linear regression feature selection algorithm based on stationary selection (SS-LR), and Fisher Score (FS)] were applied to select the features of network attributes, respectively. Finally, we used the support vector machine (SVM) with nested cross validation to classify the samples into two categories to obtain unbiased results. Our results showed that the global efficiency, the local efficiency, and the average clustering coefficient were significantly higher in the slow-5 band for the LMCI-EMCI comparison, while the characteristic path length was significantly longer under most threshold values. The classification results showed that the features selected by the mRMR algorithm have higher classification performance than those selected by the SS-LR and FS algorithms. The classification results obtained by using mRMR algorithm in slow-5 band are the best, with 83.87% accuracy (ACC), 86.21% sensitivity (SEN), 81.21% specificity (SPE), and the area under receiver operating characteristic curve (AUC) of 0.905. The present results suggest that the method we proposed could effectively help diagnose MCI disease in clinic and predict its conversion to Alzheimer's disease at an early stage.

Resting-state fMRI (rs-fMRI) detects functional connectivity (FC) abnormalities that occur in the brains of patients with Alzheimer's disease (AD) and mild cognitive impairment (MCI). FC of the default mode network (DMN) is commonly impaired in AD and MCI. We conducted a systematic review aimed at determining the diagnostic power of rs-fMRI to identify FC abnormalities in the DMN of patients with AD or MCI compared with healthy controls (HCs) using machine learning (ML) methods. Multimodal support vector machine (SVM) algorithm was the commonest form of ML method utilized. Multiple kernel approach can be utilized to aid in the classification by incorporating various discriminating features, such as FC graphs based on "nodes" and "edges" together with structural MRI-based regional cortical thickness and gray matter volume. Other multimodal features include neuropsychiatric testing scores, DTI features, and regional cerebral blood flow. Among AD patients, the posterior cingulate cortex (PCC)/Precuneus was noted to be a highly affected hub of the DMN that demonstrated overall reduced FC. Whereas reduced DMN FC between the PCC and anterior cingulate cortex (ACC) was observed in MCI patients. Evidence indicates that the nodes of the DMN can offer moderate to high diagnostic power to distinguish AD and MCI patients. Nevertheless, various concerns over the homogeneity of data based on patient selection, scanner effects, and the variable usage of classifiers and algorithms pose a challenge for ML-based image interpretation of rs-fMRI datasets to become a mainstream option for diagnosing AD and predicting the conversion of HC/MCI to AD.© 2021 The Authors. Human Brain Mapping published by Wiley Periodicals LLC.

Objective : Machine learning classification has been the most important computational development in the last years to satisfy the primary need of clinicians for automatic early diagnosis and prognosis. Nowadays, Random Forest (RF) algorithm has been successfully applied for reducing high dimensional and multi-source data in many scientific realms. Our aim was to explore the state of the art of the application of RF on single and multi-modal neuroimaging data for the prediction of Alzheimer's disease.Methods : A systematic review following PRISMA guidelines was conducted on this field of study. In particular, we constructed an advanced query using boolean operators as follows: ("random forest" OR "random forests") AND neuroimaging AND ("alzheimer's disease" OR alzheimer's OR alzheimer) AND ( prediction OR classification). The query was then searched in four well-known scientific databases: Pubmed, Scopus, Google Scholar and Web of Science.Results : Twelve articles-published between the 2007 and 2017-have been included in this systematic review after a quantitative and qualitative selection. The lesson learnt from these works suggest that when RF was applied on multi-modal data for prediction of Alzheimer's disease (AD) conversion from the Mild Cognitive Impairment (MCI), it produces one of the best accuracies to date. Moreover, the RF has important advantages in terms of robustness to overfitting, ability to handle highly non-linear data, stability in the presence of outliers and opportunity for efficient parallel processing mainly when applied on multi-modality neuroimaging data, such as, MRI morphometric, diffusion tensor imaging, and PET images.Conclusions : We discussed the strengths of RF, considering also possible limitations and by encouraging further studies on the comparisons of this algorithm with other commonly used classification approaches, particularly in the early prediction of the progression from MCI to AD.

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.

Graphs are widely used as a natural framework that captures interactions between individual elements represented as nodes in a graph. In medical applications, specifically, nodes can represent individuals within a potentially large population (patients or healthy controls) accompanied by a set of features, while the graph edges incorporate associations between subjects in an intuitive manner. This representation allows to incorporate the wealth of imaging and non-imaging information as well as individual subject features simultaneously in disease classification tasks. Previous graph-based approaches for supervised or unsupervised learning in the context of disease prediction solely focus on pairwise similarities between subjects, disregarding individual characteristics and features, or rather rely on subject-specific imaging feature vectors and fail to model interactions between them. In this paper, we present a thorough evaluation of a generic framework that leverages both imaging and non-imaging information and can be used for brain analysis in large populations. This framework exploits Graph Convolutional Networks (GCNs) and involves representing populations as a sparse graph, where its nodes are associated with imaging-based feature vectors, while phenotypic information is integrated as edge weights. The extensive evaluation explores the effect of each individual component of this framework on disease prediction performance and further compares it to different baselines. The framework performance is tested on two large datasets with diverse underlying data, ABIDE and ADNI, for the prediction of Autism Spectrum Disorder and conversion to Alzheimer's disease, respectively. Our analysis shows that our novel framework can improve over state-of-the-art results on both databases, with 70.4% classification accuracy for ABIDE and 80.0% for ADNI.Copyright © 2018 Elsevier B.V. All rights reserved.

To enhance sleep quality in hospitalized patients, we developed a conversational agent that streamlines the collection and analysis of sleep data. The system employs the Richards-Campbell Sleep Questionnaire, supplemented by additional questions about environmental factors such as room temperature and lighting, to comprehensively evaluate sleep disturbances experienced by patients. By processing patients' spoken responses, the agent identifies environmental and care-related factors impacting sleep, which may allow for non-pharmacological interventions to enhance sleep quality. The integration of advanced conversational AI technologies, including GPT-4 and large language models, is a key feature of this system, enabling nuanced interpretation and structuring of patient feedback. This approach not only streamlines sleep assessment in hospital settings but also aligns with the shift towards patient-centric healthcare. By offering detailed insights into factors affecting sleep, the system showcases its potential with a high recognition accuracy, underscoring its potentially valuable role in advancing healthcare sleep quality management.

Brain functional connectivity (FC) extracted from resting-state fMRI (RS-fMRI) has become a popular approach for disease diagnosis, where discriminating subjects with mild cognitive impairment (MCI) from normal controls (NC) is still one of the most challenging problems. Dynamic functional connectivity (dFC), consisting of time-varying spatiotemporal dynamics, may characterize "chronnectome" diagnostic information for improving MCI classification. However, most of the current dFC studies are based on detecting discrete major "brain status" via spatial clustering, which ignores rich spatiotemporal dynamics contained in such chronnectome. We propose for exhaustively mining the comprehensive information, especially the hidden higher-level features, i.e., the dFC time series that may add critical diagnostic power for MCI classification. To this end, we devise a new Fully-connected Long Short-Term Memory (LSTM) network (Full-BiLSTM) to effectively learn the periodic brain status changes using both past and future information for each brief time segment and then fuse them to form the final output. We have applied our method to a rigorously built large-scale multi-site database (i.e., with 164 data from NCs and 330 from MCIs, which can be further augmented by 25 folds). Our method outperforms other state-of-the-art approaches with an accuracy of 73.6% under solid cross-validations. We also made extensive comparisons among multiple variants of LSTM models. The results suggest high feasibility of our method with promising value also for other brain disorder diagnoses.

Frontotemporal dementia (FTD) is a progressive neurodegenerative disorder with a diverse range of symptoms, including personality changes, behavioral disturbances, language deficits, and impaired executive functions. FTD has three main subtypes: behavioral variant FTD, non-fluent variant primary progressive aphasia, and semantic variant primary progressive aphasia. While there has been extensive research on detecting FTD, there is a limited exploration of the progression of FTD severity in patients over time. FTD typically manifests at a younger age, occurring between 40 and 65 years, than any other dementia forms. Therefore, detecting specific FTD subtypes early on becomes more feasible when assessing disease severity in the initial stages. This study aims to forecast an individual's future cognitive status using their neuropsychiatric inventory. This inventory consists solely of neuropsychological test scores related to FTD markers collected from one or more time points. We proposed and applied a regression framework with Encoder-Decoder Long-Short-Term-Memory (ED-LSTM) model to the data from the Frontotemporal Lobar Degeneration Neuroimaging Initiative (FTLDNI/NIFD) comprising longitudinal data of 288 participant's 918 instances. This study represents the first comprehensive exploration of forecasting individuals' FTD markers (cognitive scores) over four years into the future. We compared the performance of the proposed model with two baseline recurrent neural network models (LSTM and Simple RNN). The results indicate that the suggested model outperforms other implemented models when considering mean absolute error and root mean square error performance metrics.Clinical relevance- This study aims to provide valuable insights into the early identification and prognosis of cognitive decline in individuals with FTD. This could contribute to more timely and targeted interventions, improving patient outcomes and enhancing the overall management of FTD.

Alzheimer's disease (AD) is an irreversible brain degenerative disorder affecting people aged older than 65 years. Currently, there is no effective cure for AD, but its progression can be delayed with some treatments. Accurate and early diagnosis of AD is vital for the patient care and development of future treatment. Fluorodeoxyglucose positrons emission tomography (FDG-PET) is a functional molecular imaging modality, which proves to be powerful to help understand the anatomical and neural changes of brain related to AD. Most existing methods extract the handcrafted features from images, and then design a classifier to distinguish AD from other groups. These methods highly depends on the preprocessing of brain images, including image rigid registration and segmentation. Motivated by the success of deep learning in image classification, this paper proposes a new classification framework based on combination of 2D convolutional neural networks (CNN) and recurrent neural networks (RNNs), which learns the intra-slice and inter-slice features for classification after decomposition of the 3D PET image into a sequence of 2D slices. The 2D CNNs are built to capture the features of image slices while the gated recurrent unit (GRU) of RNN is cascaded to learn and integrate the inter-slice features for image classification. No rigid registration and segmentation are required for PET images. Our method is evaluated on the baseline FDG-PET images acquired from 339 subjects including 93 AD patients, 146 mild cognitive impairments (MCI) and 100 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an area under receiver operating characteristic curve (AUC) of 95.3% for AD vs. NC classification and 83.9% for MCI vs. NC classification, demonstrating the promising classification performance.

Neuroimaging provides a powerful tool to characterize neurodegenerative progression and therapeutic efficacy in Alzheimer's disease (AD) and its prodromal stage-mild cognitive impairment (MCI). However, since the disease pathology might cause different patterns of structural degeneration, which is not pre-known, it is still a challenging problem to identify the relevant imaging markers for facilitating disease interpretation and classification. Recently, sparse learning methods have been investigated in neuroimaging studies for selecting the relevant imaging biomarkers and have achieved very promising results on disease classification. However, in the standard sparse learning method, the spatial structure is often ignored, although it is important for identifying the informative biomarkers. In this paper, a sparse learning method with tree-structured regularization is proposed to capture patterns of pathological degeneration from fine to coarse scale, for helping identify the informative imaging biomarkers to guide the disease classification and interpretation. Specifically, we first develop a new tree construction method based on the hierarchical agglomerative clustering of voxel-wise imaging features in the whole brain, by taking into account their spatial adjacency, feature similarity and discriminability. In this way, the complexity of all possible multi-scale spatial configurations of imaging features can be reduced to a single tree of nested regions. Second, we impose the tree-structured regularization on the sparse learning to capture the imaging structures, and then use them for selecting the most relevant biomarkers. Finally, we train a support vector machine (SVM) classifier with the selected features to make the classification. We have evaluated our proposed method by using the baseline MR images of 830 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, which includes 198 AD patients, 167 progressive MCI (pMCI), 236 stable MCI (sMCI), and 229 normal controls (NC). Our experimental results show that our method can achieve accuracies of 90.2 %, 87.2 %, and 70.7 % for classifications of AD vs. NC, pMCI vs. NC, and pMCI vs. sMCI, respectively, demonstrating promising performance compared with other state-of-the-art methods.

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. In recent years, machine learning methods have been widely used on analysis of neuroimage for quantitative evaluation and computer-aided diagnosis of AD or prediction on the conversion from mild cognitive impairment (MCI) to AD. In this study, we aimed to develop a new deep learning method to detect or predict AD in an efficient way.We proposed a densely connected convolution neural network with connection-wise attention mechanism to learn the multi-level features of brain MR images for AD classification. We used the densely connected neural network to extract multi-scale features from pre-processed images, and connection-wise attention mechanism was applied to combine connections among features from different layers to hierarchically transform the MR images into more compact high-level features. Furthermore, we extended the convolution operation to 3D to capture the spatial information of MRI. The features extracted from each 3D convolution layer were integrated with features from all preceding layers with different attention, and were finally used for classification. Our method was evaluated on the baseline MRI of 968 subjects from ADNI database to discriminate (1) AD versus healthy subjects, (2) MCI converters versus healthy subjects, and (3) MCI converters versus non-converters.The proposed method achieved 97.35% accuracy for distinguishing AD patients from healthy control, 87.82% for MCI converters against healthy control, and 78.79% for MCI converters against non-converters. Compared with some neural networks and methods reported in recent studies, the classification performance of our proposed algorithm was among the top ranks and improved in discriminating MCI subjects who were in high risks of conversion to AD.Deep learning techniques provide a powerful tool to explore minute but intricate characteristics in MR images which may facilitate early diagnosis and prediction of AD.Copyright © 2021 The Author(s). Published by Elsevier Inc. All rights reserved.

Alzheimer’s disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer’s disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer’s disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer’s disease and cognitively normal subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset (n = 417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n = 382), the Framingham Heart Study (n = 102), and the National Alzheimer’s Coordinating Center (NACC) (n = 582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n = 11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer’s disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.