Aberrant MEG multi-frequency phase temporal synchronization predicts conversion from mild cognitive impairment-to-Alzheimer's disease

Bayesian reduced rank regression models generalizable neural fingerprints that differentiate between individuals in magnetoencephalography data

Recent magnetoencephalography (MEG) studies have reported that functional connectivity (FC) and power spectra can be used as neural fingerprints in differentiating individuals. Such studies have mainly used correlations between measurement sessions to distinguish individuals from each other. However, it has remained unclear whether such correlations might reflect a more generalizable principle of individually distinctive brain patterns. Here, we evaluated a machine-learning based approach, termed latent-noise Bayesian reduced rank regression (BRRR) as a means of modelling individual differences in the resting-state MEG data of the Human Connectome Project (HCP), using FC and power spectra as neural features. First, we verified that BRRR could model and reproduce the differences between metrics that correlation-based fingerprinting yields. We trained BRRR models to distinguish individuals based on data from one measurement and used the models to identify subsequent measurement sessions of those same individuals. The best performing BRRR models, using only 20 spatiospectral components, were able to identify subjects across measurement sessions with over 90% accuracy, approaching the highest correlation-based accuracies. Using cross-validation, we then determined whether that BRRR model could generalize to unseen subjects, successfully classifying the measurement sessions of novel individuals with over 80% accuracy. The results demonstrate that individual neurofunctional differences can be reliably extracted from MEG data with a low-dimensional predictive model and that the model is able to classify novel subjects.

Intelligent digital tools for screening of brain connectivity and dementia risk estimation in people affected by mild cognitive impairment: the AI-Mind clinical study protocol

More than 10 million Europeans show signs of mild cognitive impairment (MCI), a transitional stage between normal brain aging and dementia stage memory disorder. The path MCI takes can be divergent; while some maintain stability or even revert to cognitive norms, alarmingly, up to half of the cases progress to dementia within 5 years. Current diagnostic practice lacks the necessary screening tools to identify those at risk of progression. The European patient experience often involves a long journey from the initial signs of MCI to the eventual diagnosis of dementia. The trajectory is far from ideal. Here, we introduce the AI-Mind project, a pioneering initiative with an innovative approach to early risk assessment through the implementation of advanced artificial intelligence (AI) on multimodal data. The cutting-edge AI-based tools developed in the project aim not only to accelerate the diagnostic process but also to deliver highly accurate predictions regarding an individual's risk of developing dementia when prevention and intervention may still be possible. AI-Mind is a European Research and Innovation Action (RIA H2020-SC1-BHC-06-2020, No. 964220) financed between 2021 and 2026. First, the AI-Mind Connector identifies dysfunctional brain networks based on high-density magneto- and electroencephalography (M/EEG) recordings. Second, the AI-Mind Predictor predicts dementia risk using data from the Connector, enriched with computerized cognitive tests, genetic and protein biomarkers, as well as sociodemographic and clinical variables. AI-Mind is integrated within a network of major European initiatives, including The Virtual Brain, The Virtual Epileptic Patient, and EBRAINS AISBL service for sensitive data, HealthDataCloud, where big patient data are generated for advancing digital and virtual twin technology development. AI-Mind's innovation lies not only in its early prediction of dementia risk, but it also enables a virtual laboratory scenario for hypothesis-driven personalized intervention research. This article introduces the background of the AI-Mind project and its clinical study protocol, setting the stage for future scientific contributions.

Neurophysiological consequences of synapse loss in progressive supranuclear palsy

Synaptic loss occurs early in many neurodegenerative diseases and contributes to cognitive impairment even in the absence of gross atrophy. Currently, for human disease there are few formal models to explain how cortical networks underlying cognition are affected by synaptic loss. We advocate that biophysical models of neurophysiology offer both a bridge from preclinical to clinical models of pathology and quantitative assays for experimental medicine. Such biophysical models can also disclose hidden neuronal dynamics generating neurophysiological observations such as EEG and magnetoencephalography. Here, we augment a biophysically informed mesoscale model of human cortical function by inclusion of synaptic density estimates as captured by 11C-UCB-J PET, and provide insights into how regional synapse loss affects neurophysiology. We use the primary tauopathy of progressive supranuclear palsy (Richardson's syndrome) as an exemplar condition, with high clinicopathological correlations. Progressive supranuclear palsy causes a marked change in cortical neurophysiology in the presence of mild cortical atrophy and is associated with a decline in cognitive functions associated with the frontal lobe. Using parametric empirical Bayesian inversion of a conductance-based canonical microcircuit model of magnetoencephalography data, we show that the inclusion of regional synaptic density-as a subject-specific prior on laminar-specific neuronal populations-markedly increases model evidence. Specifically, model comparison suggests that a reduction in synaptic density in inferior frontal cortex affects superficial and granular layer glutamatergic excitation. This predicted individual differences in behaviour, demonstrating the link between synaptic loss, neurophysiology and cognitive deficits. The method we demonstrate is not restricted to progressive supranuclear palsy or the effects of synaptic loss: such pathology-enriched dynamic causal models can be used to assess the mechanisms of other neurological disorders, with diverse non-invasive measures of pathology, and is suitable to test the effects of experimental pharmacology.

Brain network analysis for the discrimination of dementia disorders using electrophysiology signals: A systematic review

Background

Dementia-related disorders have been an age-long challenge to the research and healthcare communities as their various forms are expressed with similar clinical symptoms. These disorders are usually irreversible at their late onset, hence their lack of validated and approved cure. Since their prodromal stages usually lurk for a long period of time before the expression of noticeable clinical symptoms, a secondary prevention which has to do with treating the early onsets has been suggested as the possible solution. Connectivity analysis of electrophysiology signals has played significant roles in the diagnosis of various dementia disorders through early onset identification.

Objective

With the various applications of electrophysiology signals, the purpose of this study is to systematically review the step-by-step procedures of connectivity analysis frameworks for dementia disorders. This study aims at identifying the methodological issues involved in such frameworks and also suggests approaches to solve such issues.

Methods

In this study, ProQuest, PubMed, IEEE Xplore, Springer Link, and Science Direct databases are employed for exploring the evolution and advancement of connectivity analysis of electrophysiology signals of dementia-related disorders between January 2016 to December 2022. The quality of assessment of the studied articles was done using Cochrane guidelines for the systematic review of diagnostic test accuracy.

Results

Out of a total of 4,638 articles found to have been published on the review scope between January 2016 to December 2022, a total of 51 peer-review articles were identified to completely satisfy the review criteria. An increasing trend of research in this domain is identified within the considered time frame. The ratio of MEG and EEG utilization found within the reviewed articles is 1:8. Most of the reviewed articles employed graph theory metrics for their analysis with clustering coefficient (CC), global efficiency (GE), and characteristic path length (CPL) appearing more frequently compared to other metrics.

Significance

This study provides general insight into how to employ connectivity measures for the analysis of electrophysiology signals of dementia-related disorders in order to better understand their underlying mechanism and their differential diagnosis.

Oscillatory markers of neuroHIV-related cognitive impairment and Alzheimer's disease during attentional interference processing

People with HIV (PWH) frequently experience mild cognitive decline, which is typically attributed to HIV-associated neurocognitive disorder (HAND). However, such declines could also be a sign of early Alzheimer's disease (AD) in older PWH. Distinguishing these two pathologies in PWH is exceedingly difficult, as there is a major knowledge gap regarding their neural and neuropsychological bases. In the current study, we begin to address this knowledge gap by recording magnetoencephalography (MEG) during a flanker interference task in 31 biomarker-confirmed patients on the AD spectrum (ADS), 25 older participants with HAND, and 31 cognitively-normal controls. MEG data was examined in the time-frequency domain using a data-driven approach. Our results indicated that the clinical groups (ADS/HAND) performed significantly worse than controls on the task and exhibited aberrations in interference-related theta and alpha oscillations, some of which were disease-specific. Specifically, patients (ADS/HAND) exhibited weaker interference activity in frontoparietal and cingulate cortices compared to controls, while the ADS group exhibited stronger theta interference than those with HAND in frontoparietal, occipital, and temporal cortices. These results reveal overlapping and distinct patterns of neurophysiological alterations among those with ADS and HAND in attentional processing centers and suggest the existence of unique oscillatory markers of each condition.

Synchronization of a higher-order network of Rulkov maps

In neuronal network analysis on, for example, synchronization, it has been observed that the influence of interactions between pairwise nodes is essential. This paper further reveals that there exist higher-order interactions among multi-node simplicial complexes. Using a neuronal network of Rulkov maps, the impact of such higher-order interactions on network synchronization is simulated and analyzed. The results show that multi-node interactions can considerably enhance the Rulkov network synchronization, better than pairwise interactions, for involving more and more neurons in the network.

Abnormal information interaction in multilayer directed network based on cross-frequency integration of mild cognitive impairment and Alzheimer’s disease

Mild cognitive impairment (MCI) and Alzheimer’s disease (AD) have been reported to result in abnormal cross-frequency integration. However, previous studies have failed to consider specific abnormalities in receiving and outputting information among frequency bands during integration. Here, we investigated heterogeneity in receiving and outputting information during cross-frequency integration in patients. The results showed that during cross-frequency integration, information interaction first increased and then decreased, manifesting in the heterogeneous distribution of inter-frequency nodes for receiving information. A possible explanation was that due to damage to some inter-frequency hub nodes, intra-frequency nodes gradually became new inter-frequency nodes, whereas original inter-frequency nodes gradually became new inter-frequency hub nodes. Notably, damage to the brain regions that receive information between layers was often accompanied by a strengthened ability to output information and the emergence of hub nodes for outputting information. Moreover, an important compensatory mechanism assisted in the reception of information in the cingulo-opercular and auditory networks and in the outputting of information in the visual network. This study revealed specific abnormalities in information interaction and compensatory mechanism during cross-frequency integration, providing important evidence for understanding cross-frequency integration in patients with MCI and AD.

Oscillatory Activity of the Hippocampus in Prodromal Alzheimer’s Disease: A Source-Space Magnetoencephalography Study

Background: In Alzheimer’s disease (AD), oscillatory activity of the human brain slows down. However, oscillatory slowing varies between individuals, particularly in prodromal AD. Cortical oscillatory changes have shown suboptimal accuracy as diagnostic markers. We speculated that focusing on the hippocampus might prove more successful, particularly using magnetoencephalography (MEG) for capturing subcortical oscillatory activity. Objective: We explored MEG-based detection of hippocampal oscillatory abnormalities in prodromal AD patients. Methods: We acquired resting-state MEG data of 18 AD dementia patients, 18 amyloid-β-positive amnestic mild cognitive impairment (MCI, prodromal AD) patients, and 18 amyloid-β-negative persons with subjective cognitive decline (SCD). Oscillatory activity in 78 cortical regions and both hippocampi was reconstructed using beamforming. Between-group and hippocampal-cortical differences in spectral power were assessed. Classification accuracy was explored using ROC curves. Results: The MCI group showed intermediate power values between SCD and AD, except for the alpha range, where it was higher than both (p < 0.05 and p < 0.001). The largest differences between MCI and SCD were in the theta band, with higher power in MCI (p < 0.01). The hippocampi showed several unique group differences, such as higher power in the higher alpha band in MCI compared to SCD (p < 0.05). Classification accuracy (MCI versus SCD) was best for absolute theta band power in the right hippocampus (AUC = 0.87). Conclusion: In this MEG study, we detected oscillatory abnormalities of the hippocampi in prodromal AD patients. Moreover, hippocampus-based classification performed better than cortex-based classification. We conclude that a focus on hippocampal MEG may improve early detection of AD-related neuronal dysfunction.

The Road to Personalized Medicine in Alzheimer’s Disease: The Use of Artificial Intelligence

Dementia remains an extremely prevalent syndrome among older people and represents a major cause of disability and dependency. Alzheimer’s disease (AD) accounts for the majority of dementia cases and stands as the most common neurodegenerative disease. Since age is the major risk factor for AD, the increase in lifespan not only represents a rise in the prevalence but also adds complexity to the diagnosis. Moreover, the lack of disease-modifying therapies highlights another constraint. A shift from a curative to a preventive approach is imminent and we are moving towards the application of personalized medicine where we can shape the best clinical intervention for an individual patient at a given point. This new step in medicine requires the most recent tools and analysis of enormous amounts of data where the application of artificial intelligence (AI) plays a critical role on the depiction of disease–patient dynamics, crucial in reaching early/optimal diagnosis, monitoring and intervention. Predictive models and algorithms are the key elements in this innovative field. In this review, we present an overview of relevant topics regarding the application of AI in AD, detailing the algorithms and their applications in the fields of drug discovery, and biomarkers.

Synchronization in Hindmarsh-Rose neurons subject to higher-order interactions

Higher-order interactions might play a significant role in the collective dynamics of the brain. With this motivation, we here consider a simplicial complex of neurons, in particular, studying the effects of pairwise and three-body interactions on the emergence of synchronization. We assume pairwise interactions to be mediated through electrical synapses, while for second-order interactions, we separately study diffusive coupling and nonlinear chemical coupling. For all the considered cases, we derive the necessary conditions for synchronization by means of linear stability analysis, and we compute the synchronization errors numerically. Our research shows that the second-order interactions, even if of weak strength, can lead to synchronization under significantly lower first-order coupling strengths. Moreover, the overall synchronization cost is reduced due to the introduction of three-body interactions if compared to pairwise interactions.

Electrophysiological Signature and the Prediction of Deep Brain Stimulation Withdrawal and Insertion Effects

Deep brain stimulation (DBS) serves as a treatment for neurological and psychiatric disorders, such as Parkinson's disease (PD), essential tremor, dystonia, Tourette Syndrome (GTS), Huntington's disease, and obsessive-compulsive disorder (OCD). There is broad experience with the short-term effects of DBS in individual diseases and their signs/symptoms. However, even in acute treatment and for the same disorder or a given disorder, a prediction of effect is not perfect. Even further, the factors that influence the long-term effect of DBS and its withdrawal are hardly characterized. In this work, we aim to shed light on an important topic, the question of “DBS dependency.” To address this, we make use of the Kuramoto model of phase synchronization (oscillation feature) endowed with neuroplasticity to study the effects of DBS under successive withdrawals and renewals of neuromodulation as well as influence of treatment duration in de novo DBS “patients.” The results of our simulation show that the characteristics of neuroplasticity have a profound effect on the stability and mutability of oscillation synchronization patterns across successive withdrawal and renewal of DBS in chronic “patients” and also in de novo DBS “patients” with varying duration of treatment (here referred to as the “number of iterations”). Importantly, the results demonstrate the strong effect of the individual neuroplasticity makeup on the behavior of synchrony of oscillatory activity that promotes certain disorder/disease states or symptoms. The effect of DBS-mediated neuromodulation and withdrawal is highly dependent on the makeup of the neuroplastic signature of a disorder or an individual.

Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review

BACKGROUND

An increase in lifespan in our society is a double-edged sword that entails a growing number of patients with neurocognitive disorders, Alzheimer's disease being the most prevalent. Advances in medical imaging and computational power enable new methods for the early detection of neurocognitive disorders with the goal of preventing or reducing cognitive decline. Computer-aided image analysis and early detection of changes in cognition is a promising approach for patients with mild cognitive impairment, sometimes a prodromal stage of Alzheimer's disease dementia.

METHODS

We conducted a systematic review following PRISMA guidelines of studies where machine learning was applied to neuroimaging data in order to predict whether patients with mild cognitive impairment might develop Alzheimer's disease dementia or remain stable. After removing duplicates, we screened 452 studies and selected 116 for qualitative analysis.

RESULTS

Most studies used magnetic resonance image (MRI) and positron emission tomography (PET) data but also magnetoencephalography. The datasets were mainly extracted from the Alzheimer's disease neuroimaging initiative (ADNI) database with some exceptions. Regarding the algorithms used, the most common was support vector machine with a mean accuracy of 75.4%, but convolutional neural networks achieved a higher mean accuracy of 78.5%. Studies combining MRI and PET achieved overall better classification accuracy than studies that only used one neuroimaging technique. In general, the more complex models such as those based on deep learning, combined with multimodal and multidimensional data (neuroimaging, clinical, cognitive, genetic, and behavioral) achieved the best performance.

CONCLUSIONS

Although the performance of the different methods still has room for improvement, the results are promising and this methodology has a great potential as a support tool for clinicians and healthcare professionals.

Artificial Intelligence for Alzheimer's Disease: Promise or Challenge?

Decades of experimental and clinical research have contributed to unraveling many mechanisms in the pathogenesis of Alzheimer's disease (AD), but the puzzle is still incomplete. Although we can suppose that there is no complete set of puzzle pieces, the recent growth of open data-sharing initiatives collecting lifestyle, clinical, and biological data from AD patients has provided a potentially unlimited amount of information about the disease, far exceeding the human ability to make sense of it. Moreover, integrating Big Data from multi-omics studies provides the potential to explore the pathophysiological mechanisms of the entire biological continuum of AD. In this context, Artificial Intelligence (AI) offers a wide variety of methods to analyze large and complex data in order to improve knowledge in the AD field. In this review, we focus on recent findings and future challenges for AI in AD research. In particular, we discuss the use of Computer-Aided Diagnosis tools for AD diagnosis and the use of AI to potentially support clinical practices for the prediction of individual risk of AD conversion as well as patient stratification in order to finally develop effective and personalized therapies.

Deep-MEG: spatiotemporal CNN features and multiband ensemble classification for predicting the early signs of Alzheimer’s disease with magnetoencephalography

In this paper, we present the novel Deep-MEG approach in which image-based representations of magnetoencephalography (MEG) data are combined with ensemble classifiers based on deep convolutional neural networks. For the scope of predicting the early signs of Alzheimer’s disease (AD), functional connectivity (FC) measures between the brain bio-magnetic signals originated from spatially separated brain regions are used as MEG data representations for the analysis. After stacking the FC indicators relative to different frequency bands into multiple images, a deep transfer learning model is used to extract different sets of deep features and to derive improved classification ensembles. The proposed Deep-MEG architectures were tested on a set of resting-state MEG recordings and their corresponding magnetic resonance imaging scans, from a longitudinal study involving 87 subjects. Accuracy values of 89% and 87% were obtained, respectively, for the early prediction of AD conversion in a sample of 54 mild cognitive impairment subjects and in a sample of 87 subjects, including 33 healthy controls. These results indicate that the proposed Deep-MEG approach is a powerful tool for detecting early alterations in the spectral–temporal connectivity profiles and in their spatial relationships.

When the time is right: Temporal dynamics of brain activity in healthy aging and dementia

Brain activity and communications are complex phenomena that dynamically unfold over time. However, in contrast with the large number of studies reporting neuroanatomical differences in activation relative to young adults, changes of temporal dynamics of neural activity during normal and pathological aging have been grossly understudied and are still poorly known. Here, we synthesize the current state of knowledge from MEG and EEG studies that aimed at specifying the effects of healthy and pathological aging on local and network dynamics, and discuss the clinical and theoretical implications of these findings. We argue that considering the temporal dynamics of brain activations and networks could provide a better understanding of changes associated with healthy aging, and the progression of neurodegenerative disease. Recent research has also begun to shed light on the association of these dynamics with other imaging modalities and with individual differences in cognitive performance. These insights hold great potential for driving new theoretical frameworks and development of biomarkers to aid in identifying and treating age-related cognitive changes.

A Graph Gaussian Embedding Method for Predicting Alzheimer's Disease Progression With MEG Brain Networks

Characterizing the subtle changes of functional brain networks associated with the pathological cascade of Alzheimer's disease (AD) is important for early diagnosis and prediction of disease progression prior to clinical symptoms. We developed a new deep learning method, termed multiple graph Gaussian embedding model (MG2G), which can learn highly informative network features by mapping high-dimensional resting-state brain networks into a low-dimensional latent space. These latent distribution-based embeddings enable a quantitative characterization of subtle and heterogeneous brain connectivity patterns at different regions, and can be used as input to traditional classifiers for various downstream graph analytic tasks, such as AD early stage prediction, and statistical evaluation of between-group significant alterations across brain regions. We used MG2G to detect the intrinsic latent dimensionality of MEG brain networks, predict the progression of patients with mild cognitive impairment (MCI) to AD, and identify brain regions with network alterations related to MCI.

A Review of Automated Techniques for Assisting the Early Detection of Alzheimer's Disease with a Focus on EEG

In this paper, we review state-of-the-art approaches that apply signal processing (SP) and machine learning (ML) to automate the detection of Alzheimer's disease (AD) and its prodromal stages. In the first part of the document, we describe the economic and social implications of the disease, traditional diagnosis techniques, and the fundaments of automated AD detection. Then, we present electroencephalography (EEG) as an appropriate alternative for the early detection of AD, owing to its reduced cost, portability, and non-invasiveness. We also describe the main time and frequency domain EEG features that are employed in AD detection. Subsequently, we examine some of the main studies of the last decade that aim to provide an automatic detection of AD and its previous stages by means of SP and ML. In these studies, brain data was acquired using multiple medical techniques such as magnetic resonance imaging, positron emission tomography, and EEG. The main aspects of each approach, namely feature extraction, classification model, validation approach, and performance metrics, are compiled and discussed. Lastly, a set of conclusions and recommendations for future research on AD automatic detection are drawn in the final section of the paper.

The Wisdom and Vision From the ACMEGS Inaugural Decade

Concise history of fascinating magnetoencephalography (MEG) technology and catalog of very selected milestone preclinical and clinical MEG studies are provided as the background. The focus is the societal context defining a journey of MEG to and through clinical practice and formation of the American Clinical MEG Society (ACMEGS). We aspired to provide an objective historic perspective and document contributions of many professionals while focusing on the role of ACMEGS in the growth and maturation of clinical MEG field. The ACMEGS was born (2006) out of inevitability to address two vital issues-fair reimbursement and proper clinical acceptance. A beacon of accountable MEG practice and utilization is now an expanding professional organization with the highest level of competence in practice of clinical MEG and clinical credibility. The ACMEGS facilitated a favorable disposition of insurances toward MEG in the United States by combining the national replication of the grassroots efforts and teaming up with the strategic partners-particularly the American Academy of Neurology (AAN), published two Position Statements (2009 and 2017), the world's only set of MEG Clinical Practice Guidelines (CPGs; 2011) and surveys of clinical MEG practice (2011 and 2020) and use (2020). In addition to the annual ACMEGS Course (2012), we directly engaged MEG practitioners through an Invitational Summit (2019). The Society remains focused on the improvements and expansion of clinical practice, education, clinical training, and constructive engagement of vendors in these issues and pivotal studies toward additional MEG indications. The ACMEGS not only had the critical role in the progress of Clinical MEG in the United States and beyond since 2006 but positioned itself as the field leader in the future.