ABSTRACT
State-space models are widely employed across various research disciplines to study unobserved dynamics. Conventional estimation techniques, such as Kalman filtering and expectation maximisation, offer valuable insights but incur high computational costs in large-scale analyses. Sparse inverse covariance estimators can mitigate these costs, but at the expense of a trade-off between enforced sparsity and increased estimation bias, necessitating careful assessment in low signal-to-noise ratio (SNR) situations. To address these challenges, we propose a three-fold solution: (1) Introducing multiple penalised state-space (MPSS) models that leverage data-driven regularisation; (2) Developing novel algorithms derived from backpropagation, gradient descent, and alternating least squares to solve MPSS models; (3) Presenting a K-fold cross-validation extension for evaluating regularisation parameters. We validate this MPSS regularisation framework through lower and more complex simulations under varying SNR conditions, including a large-scale synthetic magneto- and electro-encephalography (MEG/EEG) data analysis. In addition, we apply MPSS models to concurrently solve brain source localisation and functional connectivity problems for real event-related MEG/EEG data, encompassing thousands of sources on the cortical surface. The proposed methodology overcomes the limitations of existing approaches, such as constraints to small-scale and region-of-interest analyses. Thus, it may enable a more accurate and detailed exploration of cognitive brain functions.
Subject(s)
Electroencephalography , Magnetoencephalography , Humans , Magnetoencephalography/methods , Electroencephalography/methods , Brain Mapping/methods , Brain , Signal-To-Noise Ratio , Algorithms , Models, Neurological , Computer SimulationABSTRACT
Biomarkers for Alzheimer's disease (AD) diagnosis do not always correlate reliably with cognitive symptoms, making clinical diagnosis inconsistent. In this study, the performance of a graphical neural network (GNN) classifier based on data-driven diagnostic classes from unsupervised clustering on heterogeneous data is compared to the performance of a classifier using clinician diagnosis as an outcome. Unsupervised clustering on tau-positron emission tomography (PET) and cognitive and functional assessment data was performed. Five clusters embedded in a non-linear uniform manifold approximation and project (UMAP) space were identified. The individual clusters revealed specific feature characteristics with respect to clinical diagnosis of AD, gender, family history, age, and underlying neurological risk factors (NRFs). In particular, one cluster comprised mainly diagnosed AD cases. All cases within this cluster were re-labelled AD cases. The re-labelled cases are characterized by high cerebrospinal fluid amyloid beta (CSF Aß) levels at a younger age, even though Aß data was not used for clustering. A GNN model was trained using the re-labelled data with a multiclass area-under-the-curve (AUC) of 95.2%, higher than the AUC of a GNN trained on clinician diagnosis (91.7%; p = 0.02). Overall, our work suggests that more objective cluster-based diagnostic labels combined with GNN classification may have value in clinical risk stratification and diagnosis of AD.
ABSTRACT
Background: Systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, and further integrated into an environment. Exploring Systems Medicine implies understanding and combining concepts coming from diametral different fields, including medicine, biology, statistics, modeling and simulation, and data science. Such heterogeneity leads to semantic issues, which may slow down implementation and fruitful interaction between these highly diverse fields. Methods: In this review, we collect and explain more than100 terms related to Systems Medicine. These include both modeling and data science terms and basic systems medicine terms, along with some synthetic definitions, examples of applications, and lists of relevant references. Results: This glossary aims at being a first aid kit for the Systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and references for digging into the topic.
ABSTRACT
BACKGROUND: Brain functional connectivity (FC) analyses based on magneto/electroencephalography (M/EEG) signals have yet to exploit the intrinsic high-dimensional information. Typically, these analyses are constrained to regions of interest to avoid the curse of dimensionality, with the latter leading to conservative hypothesis testing. NEW METHOD: We removed such constraint by estimating high-dimensional source-based M/EEG-FC using cluster-permutation statistic (CPS) and demonstrated the feasibility of this approach by identifying resting-state changes in mild cognitive impairment (MCI), a prodromal stage of Alzheimer's disease. Particularly, we proposed a unified framework for CPS analysis together with a novel neighbourhood measure to estimate more compact and neurophysiological plausible neural communication. As clusters could more confidently reveal interregional communication, we proposed and tested a cluster-strength index to demonstrate other advantages of CPS analysis. RESULTS: We found clusters of increased communication or hypersynchronization in MCI compared to healthy controls in delta (1-4 Hz) and higher-theta (6-8 Hz) bands oscillations. These mainly consisted of interactions between occipitofrontal and occipitotemporal regions in the left hemisphere, which may be critically affected in the early stages of Alzheimer's disease. CONCLUSIONS: Our approach could be important to create high-resolution FC maps from neuroimaging studies in general, allowing the multimodal analysis of neural communication across multiple spatial scales. Particularly, FC clusters more robustly represent the interregional communication by identifying dense bundles of connections that are less sensitive to inter-individual anatomical and functional variability. Overall, this approach could help to better understand neural information processing in healthy and disease conditions as needed for developing biomarker research.
Subject(s)
Brain Mapping , Magnetoencephalography , Brain/diagnostic imaging , Electroencephalography , Neural Pathways/diagnostic imagingABSTRACT
BACKGROUND: Dementia is caused by a variety of neurodegenerative diseases and is associated with a decline in memory and other cognitive abilities, while inflicting an enormous socioeconomic burden. The complexity of dementia and its associated comorbidities presents immense challenges for dementia research and care, particularly in clinical decision-making. MAIN BODY: Despite the lack of disease-modifying therapies, there is an increasing and urgent need to make timely and accurate clinical decisions in dementia diagnosis and prognosis to allow appropriate care and treatment. However, the dementia care pathway is currently suboptimal. We propose that through computational approaches, understanding of dementia aetiology could be improved, and dementia assessments could be more standardised, objective and efficient. In particular, we suggest that these will involve appropriate data infrastructure, the use of data-driven computational neurology approaches and the development of practical clinical decision support systems. We also discuss the technical, structural, economic, political and policy-making challenges that accompany such implementations. CONCLUSION: The data-driven era for dementia research has arrived with the potential to transform the healthcare system, creating a more efficient, transparent and personalised service for dementia.
Subject(s)
Computational Biology/trends , Critical Pathways , Databases, Factual/supply & distribution , Dementia/therapy , Neurology/trends , Big Data/supply & distribution , Comorbidity , Computational Biology/methods , Computational Biology/organization & administration , Critical Pathways/organization & administration , Critical Pathways/standards , Critical Pathways/statistics & numerical data , Data Science/methods , Data Science/organization & administration , Data Science/trends , Dementia/epidemiology , Humans , Neurology/methods , Neurology/organization & administrationABSTRACT
The brain's functional connectivity (FC) estimated at sensor level from electromagnetic (EEG/MEG) signals can provide quick and useful information towards understanding cognition and brain disorders. Volume conduction (VC) is a fundamental issue in FC analysis due to the effects of instantaneous correlations. FC methods based on the imaginary part of the coherence (iCOH) of any two signals are readily robust to VC effects, but neglecting the real part of the coherence leads to negligible FC when the processes are truly connected but with zero or π-phase (modulus 2π) interaction. We ameliorate this issue by proposing a novel method that implements an envelope of the imaginary coherence (EIC) to approximate the coherence estimate of supposedly active underlying sources. We compare EIC with state-of-the-art FC measures that included lagged coherence, iCOH, phase lag index (PLI) and weighted PLI (wPLI), using bivariate autoregressive and stochastic neural mass models. Additionally, we create realistic simulations where three and five regions were mapped on a template cortical surface and synthetic MEG signals were obtained after computing the electromagnetic leadfield. With this simulation and comparison study, we also demonstrate the feasibility of sensor FC analysis using receiver operating curve analysis whilst varying the signal's noise level. However, these results should be interpreted with caution given the known limitations of the sensor-based FC approach. Overall, we found that EIC and iCOH demonstrate superior results with most accurate FC maps. As they complement each other in different scenarios, that will be important to study normal and diseased brain activity.
Subject(s)
Brain/physiology , Electroencephalography/methods , Magnetoencephalography/methods , Brain Mapping/methods , Humans , Models, Neurological , Neural Pathways/physiologyABSTRACT
This article describes a spatio-temporal EEG/MEG source imaging (ESI) that extracts a parsimonious set of "atoms" or components, each the outer product of both a spatial and a temporal signature. The sources estimated are localized as smooth, minimally overlapping patches of cortical activation that are obtained by constraining spatial signatures to be nonnegative (NN), orthogonal, sparse, and smooth-in effect integrating ESI with NN-ICA. This constitutes a generalization of work by this group on the use of multiple penalties for ESI. A multiplicative update algorithm is derived being stable, fast and converging within seconds near the optimal solution. This procedure, spatio-temporal tomographic NN ICA (STTONNICA), is equally able to recover superficial or deep sources without additional weighting constraints as tested with simulations. STTONNICA analysis of ERPs to familiar and unfamiliar faces yields an occipital-fusiform atom activated by all faces and a more frontal atom that only is active with familiar faces. The temporal signatures are at present unconstrained but can be required to be smooth, complex, or following a multivariate autoregressive model.
Subject(s)
Brain Mapping/methods , Electroencephalography/methods , Auditory Perception/physiology , Brain/diagnostic imaging , Brain/physiology , Computer Simulation , Electrophysiology/methods , Evoked Potentials, Auditory , Humans , Magnetoencephalography/methods , Models, Neurological , Space Perception , Tomography/methods , Tomography, X-Ray Computed/methodsABSTRACT
This article reviews progress and challenges in model driven EEG/fMRI fusion with a focus on brain oscillations. Fusion is the combination of both imaging modalities based on a cascade of forward models from ensemble of post-synaptic potentials (ePSP) to net primary current densities (nPCD) to EEG; and from ePSP to vasomotor feed forward signal (VFFSS) to BOLD. In absence of a model, data driven fusion creates maps of correlations between EEG and BOLD or between estimates of nPCD and VFFS. A consistent finding has been that of positive correlations between EEG alpha power and BOLD in both frontal cortices and thalamus and of negative ones for the occipital region. For model driven fusion we formulate a neural mass EEG/fMRI model coupled to a metabolic hemodynamic model. For exploratory simulations we show that the Local Linearization (LL) method for integrating stochastic differential equations is appropriate for highly nonlinear dynamics. It has been successfully applied to small and medium sized networks, reproducing the described EEG/BOLD correlations. A new LL-algebraic method allows simulations with hundreds of thousands of neural populations, with connectivities and conduction delays estimated from diffusion weighted MRI. For parameter and state estimation, Kalman filtering combined with the LL method estimates the innovations or prediction errors. From these the likelihood of models given data are obtained. The LL-innovation estimation method has been already applied to small and medium scale models. With improved Bayesian computations the practical estimation of very large scale EEG/fMRI models shall soon be possible.
Subject(s)
Biological Clocks/physiology , Brain Mapping/methods , Brain/physiology , Electroencephalography/methods , Magnetic Resonance Imaging/methods , Bayes Theorem , Brain/anatomy & histology , Cerebrovascular Circulation/physiology , Computer Simulation , Evoked Potentials/physiology , Humans , Nerve Net/physiologyABSTRACT
A question subject to intense debate is whether scalp-recorded event-related brain potentials are due to phase resetting of the ongoing electroencephalogram (EEG) or rather to the superimposition of time-locked components on background activity. The two hypotheses are usually assessed by means of statistics in the time-frequency domain, for example, through wavelet transformation of multiple EEG trials that yield for each time and frequency a scatter plot of complex values coefficients. Currently, intertrial phase correlation (phase locking or phase coherence) is taken as evidence for phase resetting at a given frequency and latency. Here we present a formal analysis using a complex t-statistic to illustrate that such measures are, in effect, tests for the mean vector of the repeated trials, and as such on their own are inappropriate measures of phase resetting. We also propose simple t-like statistics for testing changes in (i) the mean (presence of an event-related potential), (ii) the amplitude variance (presence of (de)synchronization) and (iii) the concentration of phases (phase locking). The first two statistics are found to be proper measures of the presence of a non-zero mean activity and induced activity, respectively. In the third case, two different tests are introduced: one based on measuring the alignment of coefficients in the complex plane and another derived from the argument that phase locking persists when the mean of the coefficients is removed. Both statistics gave unambiguous evidence of the presence of phase locking suggesting that they constitute promising tools in the analysis of event-related brain dynamics.
Subject(s)
Brain/physiology , Data Interpretation, Statistical , Electroencephalography , Evoked Potentials/physiology , HumansABSTRACT
The recorded electrical activity of complex brain networks through the EEG reflects their intrinsic spatial, temporal and spectral properties. In this work we study the application of new penalized regression methods to i) the spatial characterization of the brain networks associated with the identification of faces and ii) the PARAFAC analysis of resting-state EEG. The use of appropriate constraints through non-convex penalties allowed three types of inverse solutions (Loreta, Lasso Fusion and ENet L) to spatially localize networks in agreement with previous studies with fMRI. Furthermore, we propose a new penalty based in the Information Entropy for the constrained PARAFAC analysis of resting EEG that allowed the identification in time, frequency and space of those brain networks with minimum spectral entropy. This study is an initial attempt to explicitly include complexity descriptors as a constraint in multilinear EEG analysis.
ABSTRACT
There is much current interest in identifying the anatomical and functional circuits that are the basis of the brain's computations, with hope that functional neuroimaging techniques will allow the in vivo study of these neural processes through the statistical analysis of the time-series they produce. Ideally, the use of techniques such as multivariate autoregressive (MAR) modelling should allow the identification of effective connectivity by combining graphical modelling methods with the concept of Granger causality. Unfortunately, current time-series methods perform well only for the case that the length of the time-series Nt is much larger than p, the number of brain sites studied, which is exactly the reverse of the situation in neuroimaging for which relatively short time-series are measured over thousands of voxels. Methods are introduced for dealing with this situation by using sparse MAR models. These can be estimated in a two-stage process involving (i) penalized regression and (ii) pruning of unlikely connections by means of the local false discovery rate developed by Efron. Extensive simulations were performed with idealized cortical networks having small world topologies and stable dynamics. These show that the detection efficiency of connections of the proposed procedure is quite high. Application of the method to real data was illustrated by the identification of neural circuitry related to emotional processing as measured by BOLD.
Subject(s)
Brain Mapping/methods , Brain/physiology , Emotions/physiology , Magnetic Resonance Imaging/methods , Models, Neurological , Models, Statistical , Brain/anatomy & histology , Computer Simulation , Female , Humans , Multivariate Analysis , Regression AnalysisABSTRACT
There is much current interest in identifying the anatomical and functional circuits that are the basis of the brain's computations, with hope that functional neuroimaging techniques will allow the in vivo study of these neural processes through the statistical analysis of the time-series they produce. Ideally, the use of techniques such as multivariate autoregressive (MAR) modelling should allow the identification of effective connectivity by combining graphical modelling methods with the concept of Granger causality. Unfortunately, current time-series methods perform well only for the case that the length of the time-series Nt is much larger than p, the number of brain sites studied, which is exactly the reverse of the situation in neuroimaging for which relatively short time-series are measured over thousands of voxels. Methods are introduced for dealing with this situation by using sparse MAR models. These can be estimated in a two-stage process involving (i) penalized regression and (ii) pruning of unlikely connections by means of the local false discovery rate developed by Efron. Extensive simulations were performed with idealized cortical networks having small world topologies and stable dynamics. These show that the detection efficiency of connections of the proposed procedure is quite high. Application of the method to real data was illustrated by the identification of neural circuitry related to emotional processing as measured by BOLD(AU)