Inference in the age of big data: Future perspectives on neuroscience

What have we really learned from functional connectivity in clinical populations?

Functional connectivity (FC), or the statistical interdependence of blood-oxygen dependent level (BOLD) signals between brain regions using fMRI, has emerged as a widely used tool for probing functional abnormalities in clinical populations due to the promise of the approach across conceptual, technical, and practical levels. With an already vast and steadily accumulating neuroimaging literature on neurodevelopmental, psychiatric, and neurological diseases and disorders in which FC is a primary measure, we aim here to provide a high-level synthesis of major concepts that have arisen from FC findings in a manner that cuts across different clinical conditions and sheds light on overarching principles. We highlight that FC has allowed us to discover the ubiquity of intrinsic functional networks across virtually all brains and clarify typical patterns of neurodevelopment over the lifespan. This understanding of typical FC maturation with age has provided important benchmarks against which to evaluate divergent maturation in early life and degeneration in late life. This in turn has led to the important insight that many clinical conditions are associated with complex, distributed, network-level changes in the brain, as opposed to solely focal abnormalities. We further emphasize the important role that FC studies have played in supporting a dimensional approach to studying transdiagnostic clinical symptoms and in enhancing the multimodal characterization and prediction of the trajectory of symptom progression across conditions. We highlight the unprecedented opportunity offered by FC to probe functional abnormalities in clinical conditions where brain function could not be easily studied otherwise, such as in disorders of consciousness. Lastly, we suggest high priority areas for future research and acknowledge critical barriers associated with the use of FC methods, particularly those related to artifact removal, data denoising and feasibility in clinical contexts.

The default mode network in cognition: a topographical perspective

The default mode network (DMN) is a set of widely distributed brain regions in the parietal, temporal and frontal cortex. These regions often show reductions in activity during attention-demanding tasks but increase their activity across multiple forms of complex cognition, many of which are linked to memory or abstract thought. Within the cortex, the DMN has been shown to be located in regions furthest away from those contributing to sensory and motor systems. Here, we consider how our knowledge of the topographic characteristics of the DMN can be leveraged to better understand how this network contributes to cognition and behaviour.

Educating the future generation of researchers: A cross-disciplinary survey of trends in analysis methods

Methods for data analysis in the biomedical, life, and social (BLS) sciences are developing at a rapid pace. At the same time, there is increasing concern that education in quantitative methods is failing to adequately prepare students for contemporary research. These trends have led to calls for educational reform to undergraduate and graduate quantitative research method curricula. We argue that such reform should be based on data-driven insights into within- and cross-disciplinary use of analytic methods. Our survey of peer-reviewed literature analyzed approximately 1.3 million openly available research articles to monitor the cross-disciplinary mentions of analytic methods in the past decade. We applied data-driven text mining analyses to the "Methods" and "Results" sections of a large subset of this corpus to identify trends in analytic method mentions shared across disciplines, as well as those unique to each discipline. We found that the t test, analysis of variance (ANOVA), linear regression, chi-squared test, and other classical statistical methods have been and remain the most mentioned analytic methods in biomedical, life science, and social science research articles. However, mentions of these methods have declined as a percentage of the published literature between 2009 and 2020. On the other hand, multivariate statistical and machine learning approaches, such as artificial neural networks (ANNs), have seen a significant increase in the total share of scientific publications. We also found unique groupings of analytic methods associated with each BLS science discipline, such as the use of structural equation modeling (SEM) in psychology, survival models in oncology, and manifold learning in ecology. We discuss the implications of these findings for education in statistics and research methods, as well as within- and cross-disciplinary collaboration.

Improved inference in coupling, encoding, and decoding models and its consequence for neuroscientific interpretation

BACKGROUND

A central goal of systems neuroscience is to understand the relationships amongst constituent units in neural populations, and their modulation by external factors, using high-dimensional and stochastic neural recordings. Parametric statistical models (e.g., coupling, encoding, and decoding models), play an instrumental role in accomplishing this goal. However, extracting conclusions from a parametric model requires that it is fit using an inference algorithm capable of selecting the correct parameters and properly estimating their values. Traditional approaches to parameter inference have been shown to suffer from failures in both selection and estimation. The recent development of algorithms that ameliorate these deficiencies raises the question of whether past work relying on such inference procedures have produced inaccurate systems neuroscience models, thereby impairing their interpretation.

NEW METHOD

We used algorithms based on Union of Intersections, a statistical inference framework based on stability principles, capable of improved selection and estimation.

COMPARISON

We fit functional coupling, encoding, and decoding models across a battery of neural datasets using both UoI and baseline inference procedures (e.g., ℓ₁-penalized GLMs), and compared the structure of their fitted parameters.

RESULTS

Across recording modality, brain region, and task, we found that UoI inferred models with increased sparsity, improved stability, and qualitatively different parameter distributions, while maintaining predictive performance. We obtained highly sparse functional coupling networks with substantially different community structure, more parsimonious encoding models, and decoding models that relied on fewer single-units.

CONCLUSIONS

Together, these results demonstrate that improved parameter inference, achieved via UoI, reshapes interpretation in diverse neuroscience contexts.

Resample aggregating improves the generalizability of connectome predictive modeling

It is a longstanding goal of neuroimaging to produce reliable, generalizable models of brain behavior relationships. More recently, data driven predictive models have become popular. However, overfitting is a common problem with statistical models, which impedes model generalization. Cross validation (CV) is often used to estimate expected model performance within sample. Yet, the best way to generate brain behavior models, and apply them out-of-sample, on an unseen dataset, is unclear. As a solution, this study proposes an ensemble learning method, in this case resample aggregating, encompassing both model parameter estimation and feature selection. Here we investigate the use of resampled aggregated models when used to estimate fluid intelligence (fIQ) from fMRI based functional connectivity (FC) data. We take advantage of two large openly available datasets, the Human Connectome Project (HCP), and the Philadelphia Neurodevelopmental Cohort (PNC). We generate aggregated and non-aggregated models of fIQ in the HCP, using the Connectome Prediction Modelling (CPM) framework. Over various test-train splits, these models are evaluated in sample, on left-out HCP data, and out-of-sample, on PNC data. We find that a resample aggregated model performs best both within- and out-of-sample. We also find that feature selection can vary substantially within-sample. More robust feature selection methods, as detailed here, are needed to improve cross sample performance of CPM based brain behavior models.

Functional specialization within the inferior parietal lobes across cognitive domains

The inferior parietal lobe (IPL) is a key neural substrate underlying diverse mental processes, from basic attention to language and social cognition, that define human interactions. Its putative domain-global role appears to tie into poorly understood differences between cognitive domains in both hemispheres. Across attentional, semantic, and social cognitive tasks, our study explored functional specialization within the IPL. The task specificity of IPL subregion activity was substantiated by distinct predictive signatures identified by multivariate pattern-learning algorithms. Moreover, the left and right IPL exerted domain-specific modulation of effective connectivity among their subregions. Task-evoked functional interactions of the anterior and posterior IPL subregions involved recruitment of distributed cortical partners. While anterior IPL subregions were engaged in strongly lateralized coupling links, both posterior subregions showed more symmetric coupling patterns across hemispheres. Our collective results shed light on how under-appreciated hemispheric specialization in the IPL supports some of the most distinctive human mental capacities.

Jumping over baselines with new methods to predict activation maps from resting-state fMRI

Cognitive fMRI research primarily relies on task-averaged responses over many subjects to describe general principles of brain function. Nonetheless, there exists a large variability between subjects that is also reflected in spontaneous brain activity as measured by resting state fMRI (rsfMRI). Leveraging this fact, several recent studies have therefore aimed at predicting task activation from rsfMRI using various machine learning methods within a growing literature on 'connectome fingerprinting'. In reviewing these results, we found lack of an evaluation against robust baselines that reliably supports a novelty of predictions for this task. On closer examination to reported methods, we found most underperform against trivial baseline model performances based on massive group averaging when whole-cortex prediction is considered. Here we present a modification to published methods that remedies this problem to large extent. Our proposed modification is based on a single-vertex approach that replaces commonly used brain parcellations. We further provide a summary of this model evaluation by characterizing empirical properties of where prediction for this task appears possible, explaining why some predictions largely fail for certain targets. Finally, with these empirical observations we investigate whether individual prediction scores explain individual behavioral differences in a task.

A hitchhiker's guide to working with large, open-source neuroimaging datasets

Large datasets that enable researchers to perform investigations with unprecedented rigor are growing increasingly common in neuroimaging. Due to the simultaneous increasing popularity of open science, these state-of-the-art datasets are more accessible than ever to researchers around the world. While analysis of these samples has pushed the field forward, they pose a new set of challenges that might cause difficulties for novice users. Here we offer practical tips for working with large datasets from the end-user's perspective. We cover all aspects of the data lifecycle: from what to consider when downloading and storing the data to tips on how to become acquainted with a dataset one did not collect and what to share when communicating results. This manuscript serves as a practical guide one can use when working with large neuroimaging datasets, thus dissolving barriers to scientific discovery.

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises including representation and transfer learning, as well as modelling domain-specific priors. After reviewing recent applications within neuroimaging-based psychiatric research, such as the diagnosis of psychiatric diseases, delineation of disease subtypes, normative modeling, and the development of neuroimaging biomarkers, we discuss current challenges. This includes for example the difficulty of training models on small, heterogeneous and biased data sets, the lack of validity of clinical labels, algorithmic bias, and the influence of confounding variables.

Deep learning identifies partially overlapping subnetworks in the human social brain

Complex social interplay is a defining property of the human species. In social neuroscience, many experiments have sought to first define and then locate ‘perspective taking’, ‘empathy’, and other psychological concepts to specific brain circuits. Seldom, bottom-up studies were conducted to first identify explanatory patterns of brain variation, which are then related to psychological concepts; perhaps due to a lack of large population datasets. In this spirit, we performed a systematic de-construction of social brain morphology into its elementary building blocks, involving ~10,000 UK Biobank participants. We explored coherent representations of structural co-variation at population scale within a recent social brain atlas, by translating autoencoder neural networks from deep learning. The learned subnetworks revealed essential patterns of structural relationships between social brain regions, with the nucleus accumbens, medial prefrontal cortex, and temporoparietal junction embedded at the core. Some of the uncovered subnetworks contributed to predicting examined social traits in general, while other subnetworks helped predict specific facets of social functioning, such as the experience of social isolation. As a consequence of our population-level evidence, spatially overlapping subsystems of the social brain probably relate to interindividual differences in everyday social life.

Kiesow et al. use deep learning to identify partially overlapping subnetworks in the human social brain at the population level. They also demonstrate that the learned subnetwork representations can be used to predict social traits.

Do High Mental Demands at Work Protect Cognitive Health in Old Age via Hippocampal Volume? Results From a Community Sample

As higher mental demands at work are associated with lower dementia risk and a key symptom of dementia is hippocampal atrophy, the study aimed at investigating the association between mental demands at work and hippocampal volume. We analyzed data from the population-based LIFE-Adult-Study in Leipzig, Germany (n = 1,409, age 40–80). Hippocampal volumes were measured via three-dimensional Magnetic resonance imaging (MRI; 3D MP-RAGE) and mental demands at work were classified via the O*NET database. Linear regression analyses adjusted for gender, age, education, APOE e4-allele, hypertension, and diabetes revealed associations between higher demands in “language and knowledge,” “information processing,” and “creativity” at work on larger white and gray matter volume and better cognitive functioning with “creativity” having stronger effects for people not yet retired. Among retired individuals, higher demands in “pattern detection” were associated with larger white matter volume as well as larger hippocampal subfields CA2/CA3, suggesting a retention effect later in life. There were no other relevant associations with hippocampal volume. Our findings do not support the idea that mental demands at work protect cognitive health via hippocampal volume or brain volume. Further research may clarify through what mechanism mentally demanding activities influence specifically dementia pathology in the brain.

Identification of Major Psychiatric Disorders From Resting-State Electroencephalography Using a Machine Learning Approach

We aimed to develop a machine learning (ML) classifier to detect and compare major psychiatric disorders using electroencephalography (EEG). We retrospectively collected data from medical records, intelligence quotient (IQ) scores from psychological assessments, and quantitative EEG (QEEG) at resting-state assessments from 945 subjects [850 patients with major psychiatric disorders (six large-categorical and nine specific disorders) and 95 healthy controls (HCs)]. A combination of QEEG parameters including power spectrum density (PSD) and functional connectivity (FC) at frequency bands was used to establish models for the binary classification between patients with each disorder and HCs. The support vector machine, random forest, and elastic net ML methods were applied, and prediction performances were compared. The elastic net model with IQ adjustment showed the highest accuracy. The best feature combinations and classification accuracies for discrimination between patients and HCs with adjusted IQ were as follows: schizophrenia = alpha PSD, 93.83%; trauma and stress-related disorders = beta FC, 91.21%; anxiety disorders = whole band PSD, 91.03%; mood disorders = theta FC, 89.26%; addictive disorders = theta PSD, 85.66%; and obsessive-compulsive disorder = gamma FC, 74.52%. Our findings suggest that ML in EEG may predict major psychiatric disorders and provide an objective index of psychiatric disorders.

Individual Differences in Intrinsic Brain Networks Predict Symptom Severity in Autism Spectrum Disorders

The neurobiology of heterogeneous neurodevelopmental disorders such as Autism Spectrum Disorders (ASD) is still unknown. We hypothesized that differences in subject-level properties of intrinsic brain networks were important features that could predict individual variation in ASD symptom severity. We matched cases and controls from a large multicohort ASD dataset (ABIDE-II) on age, sex, IQ, and image acquisition site. Subjects were matched at the individual level (rather than at group level) to improve homogeneity within matched case-control pairs (ASD: n = 100, mean age = 11.43 years, IQ = 110.58; controls: n = 100, mean age = 11.43 years, IQ = 110.70). Using task-free functional magnetic resonance imaging, we extracted intrinsic functional brain networks using projective non-negative matrix factorization. Intrapair differences in strength in subnetworks related to the salience network (SN) and the occipital-temporal face perception network were robustly associated with individual differences in social impairment severity (T = 2.206, P = 0.0301). Findings were further replicated and validated in an independent validation cohort of monozygotic twins (n = 12; 3 pairs concordant and 3 pairs discordant for ASD). Individual differences in the SN and face-perception network are centrally implicated in the neural mechanisms of social deficits related to ASD.

Brain network dynamics fingerprints are resilient to data heterogeneity

CONTEXT

Large multi-site neuroimaging datasets have significantly advanced our quest to understand brain-behavior relationships and to develop biomarkers of psychiatric and neurodegenerative disorders. Yet, such data collections come at a cost, as the inevitable differences across samples may lead to biased or erroneous conclusions.

OBJECTIVE

We aim to validate the estimation of individual brain network dynamics fingerprints and appraise sources of variability in large resting-state functional magnetic resonance imaging (rs-fMRI) datasets by providing a novel point of view based on data-driven dynamical models.

APPROACH

Previous work has investigated this critical issue in terms of effects on static measures, such as functional connectivity and brain parcellations. Here, we utilize dynamical models (Hidden Markov models - HMM) to examine how diverse scanning factors in multi-site fMRI recordings affect our ability to infer the brain's spatiotemporal wandering between large-scale networks of activity. Specifically, we leverage a stable HMM trained on the Human Connectome Project (homogeneous) dataset, which we then apply to an heterogeneous dataset of traveling subjects scanned under a multitude of conditions.

MAIN RESULTS

Building upon this premise, we first replicate previous work on the emergence of non-random sequences of brain states. We next highlight how these time-varying brain activity patterns are robust subject-specific fingerprints. Finally, we suggest these fingerprints may be used to assess which scanning factors induce high variability in the data.

SIGNIFICANCE

These results demonstrate that we can i) use large scale dataset to train models that can be then used to interrogate subject-specific data, ii) recover the unique trajectories of brain activity changes in each individual, but also iii) urge caution as our ability to infer such patterns is affected by how, where and when we do so.

Brain anatomical covariation patterns linked to binge drinking and age at first full drink

•

We identified a reproducible cortical and subcortical brain structural covariation pattern.

•

A novel pattern discovery method Joint and Individual Variance Explained (JIVE) was used.

•

The cortical and subcortical structural covariation pattern is related to alcohol use initiation.

•

The identified pattern is dominated by covariation among brainstem, thalamus and PFC.

•

A thalamic-PFC-brainstem circuitry might be related to alcohol use initiation.

Binge drinking and age at first full drink (AFD) of alcohol prior to 21 years (AFD < 21) have been linked to neuroanatomical differences in cortical and subcortical grey matter (GM) volume, cortical thickness, and surface area. Despite the importance of understanding network-level relationships, structural covariation patterns among these morphological measures have yet to be examined in relation to binge drinking and AFD < 21. Here, we used the Joint and Individual Variance Explained (JIVE) method to characterize structural covariation patterns common across and specific to morphological measures in 293 participants (149 individuals with past-12-month binge drinking and 144 healthy controls) from the Human Connectome Project (HCP). An independent dataset (Nathan Kline Institute Rockland Sample; NKI-RS) was used to examine reproducibility/generalizability. We identified a reproducible joint component dominated by structural covariation between GM volume in the brainstem and thalamus proper, and GM volume and surface area in prefrontal cortical regions. Using linear mixed regression models, we found that participants with AFD < 21 showed lower joint component scores in both the HCP (beta = 0.059, p-value = 0.016; Cohen’s d = 0.441) and NKI-RS (beta = 0.023, p-value = 0.040, Cohen’s d = 0.216) datasets, whereas the individual thickness component associated with binge drinking (p-value = 0.02) and AFD < 21 (p-value < 0.001) in the HCP dataset was not statistically significant in the NKI-RS sample. Our findings were also generalizable to the HCP full sample (n = 880 participants). Taken together, our results show that use of JIVE analysis in high-dimensional, large-scale, psychiatry-related datasets led to discovery of a reproducible cortical and subcortical structural covariation pattern involving brain regions relevant to thalamic-PFC-brainstem neural circuitry which is related to AFD < 21 and suggests a possible extension of existing addiction neurocircuitry in humans.

Using resting-state intrinsic network connectivity to identify suicide risk in mood disorders

BACKGROUND

Little is known about the neural substrates of suicide risk in mood disorders. Improving the identification of biomarkers of suicide risk, as indicated by a history of suicide-related behavior (SB), could lead to more targeted treatments to reduce risk.

METHODS

Participants were 18 young adults with a mood disorder with a history of SB (as indicated by endorsing a past suicide attempt), 60 with a mood disorder with a history of suicidal ideation (SI) but not SB, 52 with a mood disorder with no history of SI or SB (MD), and 82 healthy comparison participants (HC). Resting-state functional connectivity within and between intrinsic neural networks, including cognitive control network (CCN), salience and emotion network (SEN), and default mode network (DMN), was compared between groups.

RESULTS

Several fronto-parietal regions (k > 57, p < 0.005) were identified in which individuals with SB demonstrated distinct patterns of connectivity within (in the CCN) and across networks (CCN-SEN and CCN-DMN). Connectivity with some of these same regions also distinguished the SB group when participants were re-scanned after 1-4 months. Extracted data defined SB group membership with good accuracy, sensitivity, and specificity (79-88%).

CONCLUSIONS

These results suggest that individuals with a history of SB in the context of mood disorders may show reliably distinct patterns of intrinsic network connectivity, even when compared to those with mood disorders without SB. Resting-state fMRI is a promising tool for identifying subtypes of patients with mood disorders who may be at risk for suicidal behavior.

Precision multidimensional neural population code recovered from single intracellular recordings

Neurons in sensory cortices are more naturally and deeply integrated than any current neural population recording tools (e.g. electrode arrays, fluorescence imaging). Two concepts facilitate efforts to observe population neural code with single-cell recordings. First, even the highest quality single-cell recording studies find a fraction of the stimulus information in high-dimensional population recordings. Finding any of this missing information provides proof of principle. Second, neurons and neural populations are understood as coupled nonlinear differential equations. Therefore, fitted ordinary differential equations provide a basis for single-trial single-cell stimulus decoding. We obtained intracellular recordings of fluctuating transmembrane current and potential in mouse visual cortex during stimulation with drifting gratings. We use mean deflection from baseline when comparing to prior single-cell studies because action potentials are too sparse and the deflection response to drifting grating stimuli (e.g. tuning curves) are well studied. Equation-based decoders allowed more precise single-trial stimulus discrimination than tuning-curve-base decoders. Performance varied across recorded signal types in a manner consistent with population recording studies and both classification bases evinced distinct stimulus-evoked phases of population dynamics, providing further corroboration. Naturally and deeply integrated observations of population dynamics would be invaluable. We offer proof of principle and a versatile framework.

Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets

Recently, deep learning has unlocked unprecedented success in various domains, especially using images, text, and speech. However, deep learning is only beneficial if the data have nonlinear relationships and if they are exploitable at available sample sizes. We systematically profiled the performance of deep, kernel, and linear models as a function of sample size on UKBiobank brain images against established machine learning references. On MNIST and Zalando Fashion, prediction accuracy consistently improves when escalating from linear models to shallow-nonlinear models, and further improves with deep-nonlinear models. In contrast, using structural or functional brain scans, simple linear models perform on par with more complex, highly parameterized models in age/sex prediction across increasing sample sizes. In sum, linear models keep improving as the sample size approaches ~10,000 subjects. Yet, nonlinearities for predicting common phenotypes from typical brain scans remain largely inaccessible to the examined kernel and deep learning methods.

Toward Robust Anxiety Biomarkers: A Machine Learning Approach in a Large-Scale Sample

BACKGROUND

The field of psychiatry has long sought biomarkers that can objectively diagnose patients, predict treatment response, or identify individuals at risk of illness onset. However, reliable psychiatric biomarkers have yet to emerge. The recent application of machine learning techniques to develop neuroimaging-based biomarkers has yielded promising preliminary results. However, much of the work in this domain has not met best practice standards from the field of machine learning. This is especially true for studies of anxiety, creating uncertainty about the potential for anxiety biomarker development.

METHODS

We applied machine learning tools to predict trait anxiety from neuroimaging measurements in humans. Using publicly available data from the Brain Genomics Superstruct Project, we compared a suite of neuroimaging-based machine learning models predicting anxiety within a discovery sample (n = 531, 307 women) via k-fold cross-validation, and we tested the final model (a stacked model incorporating region-to-region functional connectivity, amygdala seed-to-voxel connectivity, and volumetric and cortical thickness data) in a held-out, unseen test sample (n = 348, 209 women).

RESULTS

Though the best model was able to predict anxiety within the discovery sample (cross-validated R2 of .06, permutation test p < .001), the generalization test within the holdout sample failed (R2 of -.04, permutation test p > .05).

CONCLUSIONS

In this study, we did not find evidence of a generalizable anxiety biomarker. However, we encourage other researchers to investigate this topic, utilizing large samples and proper methodology, to clarify the potential of neuroimaging-based anxiety biomarkers.

Revisiting 'brain modes' in a new computational era: approaches for the characterization of brain-behavioural associations

The study of brain-function relationships is undergoing a conceptual and methodological transformation due to the emergence of network neuroscience and the development of multivariate methods for lesion-deficit inferences. Anticipating this process, in 1998 Godefroy and co-workers conceptualized the potential of four elementary typologies of brain-behaviour relationships named 'brain modes' (unicity, equivalence, association, summation) as building blocks able to describe the association between intact or lesioned brain regions and cognitive processes or neurological deficits. In the light of new multivariate lesion inference and network approaches, we critically revisit and update the original theoretical notion of brain modes, and provide real-life clinical examples that support their existence. To improve the characterization of elementary units of brain-behavioural relationships further, we extend such conceptualization with a fifth brain mode (mutual inhibition/masking summation). We critically assess the ability of these five brain modes to account for any type of brain-function relationship, and discuss past versus future contributions in redefining the anatomical basis of human cognition. We also address the potential of brain modes for predicting the behavioural consequences of lesions and their future role in the design of cognitive neurorehabilitation therapies.

Neurocognitive patterns dissociating semantic processing from executive control are linked to more detailed off-task mental time travel

Features of ongoing experience are common across individuals and cultures. However, certain people express specific patterns of thought to a greater extent than others. Contemporary psychological theory assumes that individual differences in thought patterns occur because different types of experience depend on the expression of different neurocognitive processes. Consequently, individual variation in the underlying neurocognitive architecture is hypothesised to determine the ease with which certain thought patterns are generated or maintained. Our study (N = 178) tested this hypothesis using multivariate pattern analysis to infer shared variance among measures of cognitive function and neural organisation and examined whether these latent variables explained reports of the patterns of on-going thoughts people experienced in the lab. We found that relatively better performance on tasks relying primarily on semantic knowledge, rather than executive control, was linked to a neural functional organisation associated, via meta-analysis, with task labels related to semantic associations (sentence processing, reading and verbal semantics). Variability of this functional mode predicted significant individual variation in the types of thoughts that individuals experienced in the laboratory: neurocognitive patterns linked to better performance at tasks that required guidance from semantic representation, rather than those dependent on executive control, were associated with patterns of thought characterised by greater subjective detail and a focus on time periods other than the here and now. These relationships were consistent across different days and did not vary with level of task demands, indicating they are relatively stable features of an individual’s cognitive profile. Together these data confirm that individual variation in aspects of ongoing experience can be inferred from hidden neurocognitive architecture and demonstrate that performance trade-offs between executive control and long-term semantic knowledge are linked to a person’s tendency to imagine situations that transcend the here and now.

Incorporating structured assumptions with probabilistic graphical models in fMRI data analysis

With the wide adoption of functional magnetic resonance imaging (fMRI) by cognitive neuroscience researchers, large volumes of brain imaging data have been accumulated in recent years. Aggregating these data to derive scientific insights often faces the challenge that fMRI data are high-dimensional, heterogeneous across people, and noisy. These challenges demand the development of computational tools that are tailored both for the neuroscience questions and for the properties of the data. We review a few recently developed algorithms in various domains of fMRI research: fMRI in naturalistic tasks, analyzing full-brain functional connectivity, pattern classification, inferring representational similarity and modeling structured residuals. These algorithms all tackle the challenges in fMRI similarly: they start by making clear statements of assumptions about neural data and existing domain knowledge, incorporate those assumptions and domain knowledge into probabilistic graphical models, and use those models to estimate properties of interest or latent structures in the data. Such approaches can avoid erroneous findings, reduce the impact of noise, better utilize known properties of the data, and better aggregate data across groups of subjects. With these successful cases, we advocate wider adoption of explicit model construction in cognitive neuroscience. Although we focus on fMRI, the principle illustrated here is generally applicable to brain data of other modalities.

Combining magnetoencephalography with magnetic resonance imaging enhances learning of surrogate-biomarkers

Electrophysiological methods, that is M/EEG, provide unique views into brain health. Yet, when building predictive models from brain data, it is often unclear how electrophysiology should be combined with other neuroimaging methods. Information can be redundant, useful common representations of multimodal data may not be obvious and multimodal data collection can be medically contraindicated, which reduces applicability. Here, we propose a multimodal model to robustly combine MEG, MRI and fMRI for prediction. We focus on age prediction as a surrogate biomarker in 674 subjects from the Cam-CAN dataset. Strikingly, MEG, fMRI and MRI showed additive effects supporting distinct brain-behavior associations. Moreover, the contribution of MEG was best explained by cortical power spectra between 8 and 30 Hz. Finally, we demonstrate that the model preserves benefits of stacking when some data is missing. The proposed framework, hence, enables multimodal learning for a wide range of biomarkers from diverse types of brain signals.

The many facets of brain aging

Applying big-data analytic techniques to brain images from 18,707 individuals is shedding light on the influence of aging on the brain.

Analysing brain networks in population neuroscience: a case for the Bayesian philosophy

Network connectivity fingerprints are among today's best choices to obtain a faithful sampling of an individual's brain and cognition. Widely available MRI scanners can provide rich information tapping into network recruitment and reconfiguration that now scales to hundreds and thousands of humans. Here, we contemplate the advantages of analysing such connectome profiles using Bayesian strategies. These analysis techniques afford full probability estimates of the studied network coupling phenomena, provide analytical machinery to separate epistemological uncertainty and biological variability in a coherent manner, usher us towards avenues to go beyond binary statements on existence versus non-existence of an effect, and afford credibility estimates around all model parameters at play which thus enable single-subject predictions with rigorous uncertainty intervals. We illustrate the brittle boundary between healthy and diseased brain circuits by autism spectrum disorder as a recurring theme where, we argue, network-based approaches in neuroscience will require careful probabilistic answers. This article is part of the theme issue 'Unifying the essential concepts of biological networks: biological insights and philosophical foundations'.

Finding the needle in a high-dimensional haystack: Canonical correlation analysis for neuroscientists

The 21st century marks the emergence of "big data" with a rapid increase in the availability of datasets with multiple measurements. In neuroscience, brain-imaging datasets are more commonly accompanied by dozens or hundreds of phenotypic subject descriptors on the behavioral, neural, and genomic level. The complexity of such "big data" repositories offer new opportunities and pose new challenges for systems neuroscience. Canonical correlation analysis (CCA) is a prototypical family of methods that is useful in identifying the links between variable sets from different modalities. Importantly, CCA is well suited to describing relationships across multiple sets of data, such as in recently available big biomedical datasets. Our primer discusses the rationale, promises, and pitfalls of CCA.

Multi-scale network regression for brain-phenotype associations

Brain networks are increasingly characterized at different scales, including summary statistics, community connectivity, and individual edges. While research relating brain networks to behavioral measurements has yielded many insights into brain‐phenotype relationships, common analytical approaches only consider network information at a single scale. Here, we designed, implemented, and deployed Multi‐Scale Network Regression (MSNR), a penalized multivariate approach for modeling brain networks that explicitly respects both edge‐ and community‐level information by assuming a low rank and sparse structure, both encouraging less complex and more interpretable modeling. Capitalizing on a large neuroimaging cohort (n = 1, 051), we demonstrate that MSNR recapitulates interpretable and statistically significant connectivity patterns associated with brain development, sex differences, and motion‐related artifacts. Compared to single‐scale methods, MSNR achieves a balance between prediction performance and model complexity, with improved interpretability. Together, by jointly exploiting both edge‐ and community‐level information, MSNR has the potential to yield novel insights into brain‐behavior relationships.

EEG/ERP-based biomarker/neuroalgorithms in adults with ADHD: Development, reliability, and application in clinical practice

Objectives: The electrophysiological characteristics of attention-deficit/hyperactivity disorder (ADHD) and recent machine-learning methods promise easy-to-use approaches that can complement existing diagnostic tools when sufficiently large samples are used. Neuroalgorithms are models of multidimensional brain networks by means of which ADHD patient data can be separated from healthy control data.Methods: Spontaneous electroencephalographic and event-related potential (ERP) data were collected three times over the course of 2 years from a multicentre sample of adults comprising 181 patients with ADHD and 147 healthy controls. Spectral power and ERP amplitude and latency measures were used as input data for a semi-automatic machine-learning framework.Results: ADHD patients and healthy controls could be classified with a sensitivity ranging from 75% to 83% and specificity values of 71% to 77%. In the analysis of the repeated measurements, sensitivity values of the selected logistic regression model remained high (72% and 76%), while specificity values slightly decreased over time (64% and 67%).Conclusions: Implementation of the system in clinical practice requires facilities to track affected networks, as well as expertise in neuropathophysiology. Therefore, the use of neuroalgorithms can enhance the diagnostic process by making it less subjective and more reliable and linking it to the underlying pathology.

Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics

There is significant interest in the development and application of deep neural networks (DNNs) to neuroimaging data. A growing literature suggests that DNNs outperform their classical counterparts in a variety of neuroimaging applications, yet there are few direct comparisons of relative utility. Here, we compared the performance of three DNN architectures and a classical machine learning algorithm (kernel regression) in predicting individual phenotypes from whole-brain resting-state functional connectivity (RSFC) patterns. One of the DNNs was a generic fully-connected feedforward neural network, while the other two DNNs were recently published approaches specifically designed to exploit the structure of connectome data. By using a combined sample of almost 10,000 participants from the Human Connectome Project (HCP) and UK Biobank, we showed that the three DNNs and kernel regression achieved similar performance across a wide range of behavioral and demographic measures. Furthermore, the generic feedforward neural network exhibited similar performance to the two state-of-the-art connectome-specific DNNs. When predicting fluid intelligence in the UK Biobank, performance of all algorithms dramatically improved when sample size increased from 100 to 1000 subjects. Improvement was smaller, but still significant, when sample size increased from 1000 to 5000 subjects. Importantly, kernel regression was competitive across all sample sizes. Overall, our study suggests that kernel regression is as effective as DNNs for RSFC-based behavioral prediction, while incurring significantly lower computational costs. Therefore, kernel regression might serve as a useful baseline algorithm for future studies.

Using Machine Learning and Structural Neuroimaging to Detect First Episode Psychosis: Reconsidering the Evidence

Despite the high level of interest in the use of machine learning (ML) and neuroimaging to detect psychosis at the individual level, the reliability of the findings is unclear due to potential methodological issues that may have inflated the existing literature. This study aimed to elucidate the extent to which the application of ML to neuroanatomical data allows detection of first episode psychosis (FEP), while putting in place methodological precautions to avoid overoptimistic results. We tested both traditional ML and an emerging approach known as deep learning (DL) using 3 feature sets of interest: (1) surface-based regional volumes and cortical thickness, (2) voxel-based gray matter volume (GMV) and (3) voxel-based cortical thickness (VBCT). To assess the reliability of the findings, we repeated all analyses in 5 independent datasets, totaling 956 participants (514 FEP and 444 within-site matched controls). The performance was assessed via nested cross-validation (CV) and cross-site CV. Accuracies ranged from 50% to 70% for surfaced-based features; from 50% to 63% for GMV; and from 51% to 68% for VBCT. The best accuracies (70%) were achieved when DL was applied to surface-based features; however, these models generalized poorly to other sites. Findings from this study suggest that, when methodological precautions are adopted to avoid overoptimistic results, detection of individuals in the early stages of psychosis is more challenging than originally thought. In light of this, we argue that the current evidence for the diagnostic value of ML and structural neuroimaging should be reconsidered toward a more cautious interpretation.

Interpreting neural decoding models using grouped model reliance

Machine learning algorithms are becoming increasingly popular for decoding psychological constructs based on neural data. However, as a step towards bridging the gap between theory-driven cognitive neuroscience and data-driven decoding approaches, there is a need for methods that allow to interpret trained decoding models. The present study demonstrates grouped model reliance as a model-agnostic permutation-based approach to this problem. Grouped model reliance indicates the extent to which a trained model relies on conceptually related groups of variables, such as frequency bands or regions of interest in electroencephalographic (EEG) data. As a case study to demonstrate the method, random forest and support vector machine models were trained on within-participant single-trial EEG data from a Sternberg working memory task. Participants were asked to memorize a sequence of digits (0-9), varying randomly in length between one, four and seven digits, where EEG recordings for working memory load estimation were taken from a 3-second retention interval. The present results confirm previous findings insofar as both random forest and support vector machine models relied on alpha-band activity in most subjects. However, as revealed by further analyses, patterns in frequency and topography varied considerably between individuals, pointing to more pronounced inter-individual differences than previously reported.

Using machine learning to explain the heterogeneity of schizophrenia. Realizing the promise and avoiding the hype

Despite extensive research and prodigious advances in neuroscience, our comprehension of the nature of schizophrenia remains rudimentary. Our failure to make progress is attributed to the extreme heterogeneity of this condition, enormous complexity of the human brain, limitations of extant research paradigms, and inadequacy of traditional statistical methods to integrate or interpret increasingly large amounts of multidimensional information relevant to unravelling brain function. Fortunately, the rapidly developing science of machine learning appears to provide tools capable of addressing each of these impediments. Enthusiasm about the potential of machine learning methods to break the current impasse is reflected in the steep increase in the number of scientific publication about the application of machine learning to the study of schizophrenia. Machine learning approaches are, however, poorly understood by schizophrenia researchers and clinicians alike. In this paper, we provide a simple description of the nature and techniques of machine learning and their application to the study of schizophrenia. We then summarize its potential and constraints with illustrations from six studies of machine learning in schizophrenia and address some common misconceptions about machine learning. We suggest some guidelines for researchers, readers, science editors and reviewers of the burgeoning machine learning literature in schizophrenia. In order to realize its enormous promise, we suggest the need for the disciplined application of machine learning methods to the study of schizophrenia with a clear recognition of its capability and challenges accompanied by a concurrent effort to improve machine learning literacy among neuroscientists and mental health professionals.

Deep neural networks in psychiatry

Machine and deep learning methods, today's core of artificial intelligence, have been applied with increasing success and impact in many commercial and research settings. They are powerful tools for large scale data analysis, prediction and classification, especially in very data-rich environments ("big data"), and have started to find their way into medical applications. Here we will first give an overview of machine learning methods, with a focus on deep and recurrent neural networks, their relation to statistics, and the core principles behind them. We will then discuss and review directions along which (deep) neural networks can be, or already have been, applied in the context of psychiatry, and will try to delineate their future potential in this area. We will also comment on an emerging area that so far has been much less well explored: by embedding semantically interpretable computational models of brain dynamics or behavior into a statistical machine learning context, insights into dysfunction beyond mere prediction and classification may be gained. Especially this marriage of computational models with statistical inference may offer insights into neural and behavioral mechanisms that could open completely novel avenues for psychiatric treatment.

Clinical-learning versus machine-learning for transdiagnostic prediction of psychosis onset in individuals at-risk

Predicting the onset of psychosis in individuals at-risk is based on robust prognostic model building methods including a priori clinical knowledge (also termed clinical-learning) to preselect predictors or machine-learning methods to select predictors automatically. To date, there is no empirical research comparing the prognostic accuracy of these two methods for the prediction of psychosis onset. In a first experiment, no improved performance was observed when machine-learning methods (LASSO and RIDGE) were applied-using the same predictors-to an individualised, transdiagnostic, clinically based, risk calculator previously developed on the basis of clinical-learning (predictors: age, gender, age by gender, ethnicity, ICD-10 diagnostic spectrum), and externally validated twice. In a second experiment, two refined versions of the published model which expanded the granularity of the ICD-10 diagnosis were introduced: ICD-10 diagnostic categories and ICD-10 diagnostic subdivisions. Although these refined versions showed an increase in apparent performance, their external performance was similar to the original model. In a third experiment, the three refined models were analysed under machine-learning and clinical-learning with a variable event per variable ratio (EPV). The best performing model under low EPVs was obtained through machine-learning approaches. The development of prognostic models on the basis of a priori clinical knowledge, large samples and adequate events per variable is a robust clinical prediction method to forecast psychosis onset in patients at-risk, and is comparable to machine-learning methods, which are more difficult to interpret and implement. Machine-learning methods should be preferred for high dimensional data when no a priori knowledge is available.

Brain age prediction: Cortical and subcortical shape covariation in the developing human brain

Cortical development is characterized by distinct spatial and temporal patterns of maturational changes across various cortical shape measures. There is a growing interest in summarizing complex developmental patterns into a single index, which can be used to characterize an individual's brain age. We conducted this study with two primary aims. First, we sought to quantify covariation patterns for a variety of cortical shape measures, including cortical thickness, gray matter volume, surface area, mean curvature, and travel depth, as well as white matter volume, and subcortical gray matter volume. We examined these measures in a sample of 869 participants aged 5-18 from the Healthy Brain Network (HBN) neurodevelopmental cohort using the Joint and Individual Variation Explained (Lock et al., 2013) method. We validated our results in an independent dataset from the Nathan Kline Institute - Rockland Sample (NKI-RS; N = 210) and found remarkable consistency for some covariation patterns. Second, we assessed whether covariation patterns in the brain can be used to accurately predict a person's chronological age. Using ridge regression, we showed that covariation patterns can predict chronological age with high accuracy, reflected by our ability to cross-validate our model in an independent sample with a correlation coefficient of 0.84 between chronologic and predicted age. These covariation patterns also predicted sex with high accuracy (AUC = 0.85), and explained a substantial portion of variation in full scale intelligence quotient (R² = 0.10). In summary, we found significant covariation across different cortical shape measures and subcortical gray matter volumes. In addition, each shape measure exhibited distinct covariations that could not be accounted for by other shape measures. These covariation patterns accurately predicted chronological age, sex and general cognitive ability. In a subset of NKI-RS, test-retest (<1 month apart, N = 120) and longitudinal scans (1.22 ± 0.29 years apart, N = 77) were available, allowing us to demonstrate high reliability for the prediction models obtained and the ability to detect subtle differences in the longitudinal scan interval among participants (median and median absolute deviation of absolute differences between predicted age difference and real age difference = 0.53 ± 0.47 years, r = 0.24, p-value = 0.04).

Data-driven models in human neuroscience and neuroengineering

Discoveries in modern human neuroscience are increasingly driven by quantitative understanding of complex data. Data-intensive approaches to modeling have promise to dramatically advance our understanding of the brain and critically enable neuroengineering capabilities. In this review, we provide an accessible primer to modern modeling approaches and highlight recent data-driven discoveries in the domains of neuroimaging, single-neuron and neuronal population responses, and device neuroengineering. Further, we suggest that meaningful progress requires the community to tackle open challenges in the realms of model interpretability and generalizability, training pipelines of data-fluent human neuroscientists, and integrated consideration of data ethics.

Brain-based ranking of cognitive domains to predict schizophrenia

Schizophrenia is a devastating brain disorder that disturbs sensory perception, motor action, and abstract thought. Its clinical phenotype implies dysfunction of various mental domains, which has motivated a series of theories regarding the underlying pathophysiology. Aiming at a predictive benchmark of a catalog of cognitive functions, we developed a data-driven machine-learning strategy and provide a proof of principle in a multisite clinical dataset (n = 324). Existing neuroscientific knowledge on diverse cognitive domains was first condensed into neurotopographical maps. We then examined how the ensuing meta-analytic cognitive priors can distinguish patients and controls using brain morphology and intrinsic functional connectivity. Some affected cognitive domains supported well-studied directions of research on auditory evaluation and social cognition. However, rarely suspected cognitive domains also emerged as disease relevant, including self-oriented processing of bodily sensations in gustation and pain. Such algorithmic charting of the cognitive landscape can be used to make targeted recommendations for future mental health research.

Quantifying individual differences in brain morphometry underlying symptom severity in Autism Spectrum Disorders

The neurobiology of heterogeneous neurodevelopmental disorders such as autism spectrum disorders (ASD) are still unclear. Despite extensive efforts, most findings are difficult to reproduce due to high levels of individual variance in phenotypic expression. To quantify individual differences in brain morphometry in ASD, we implemented a novel subject-level, distance-based method on subject-specific attributes. In a large multi-cohort sample, each subject with ASD (n = 100; n = 84 males; mean age: 11.43 years; mean IQ: 110.58) was strictly matched to a control participant (n = 100; n = 84 males; mean age: 11.43 years; mean IQ: 110.70). Intrapair Euclidean distance of MRI brain morphometry and symptom severity measures (Social Responsiveness Scale) were entered into a regularised machine learning pipeline for feature selection, with rigorous out-of-sample validation and permutation testing. Subject-specific structural morphometry features significantly predicted individual variation in ASD symptom severity (19 cortical thickness features, p = 0.01, n = 5000 permutations; 10 surface area features, p = 0.006, n = 5000 permutations). Findings remained robust across subjects and were replicated in validation samples. Identified cortical regions implicate key hubs of the salience and default mode networks as neuroanatomical features of social impairment in ASD. Present results highlight the importance of subject-level markers in ASD, and offer an important step forward in understanding the neurobiology of heterogeneous disorders.

Towards Algorithmic Analytics for Large-scale Datasets

The traditional goals of quantitative analytics cherish simple, transparent models to generate explainable insights. Large-scale data acquisition, enabled for instance by brain scanning and genomic profiling with microarray-type techniques, has prompted a wave of statistical inventions and innovative applications. Modern analysis approaches 1) tame large variable arrays capitalizing on regularization and dimensionality-reduction strategies, 2) are increasingly backed up by empirical model validations rather than justified by mathematical proofs, 3) will compare against and build on open data and consortium repositories, as well as 4) often embrace more elaborate, less interpretable models in order to maximize prediction accuracy. Here we review these trends in learning from "big data" and illustrate examples from imaging neuroscience.

Simple Acoustic Features Can Explain Phoneme-Based Predictions of Cortical Responses to Speech

When we listen to speech, we have to make sense of a waveform of sound pressure. Hierarchical models of speech perception assume that, to extract semantic meaning, the signal is transformed into unknown, intermediate neuronal representations. Traditionally, studies of such intermediate representations are guided by linguistically defined concepts, such as phonemes. Here, we argue that in order to arrive at an unbiased understanding of the neuronal responses to speech, we should focus instead on representations obtained directly from the stimulus. We illustrate our view with a data-driven, information theoretic analysis of a dataset of 24 young, healthy humans who listened to a 1 h narrative while their magnetoencephalogram (MEG) was recorded. We find that two recent results, the improved performance of an encoding model in which annotated linguistic and acoustic features were combined and the decoding of phoneme subgroups from phoneme-locked responses, can be explained by an encoding model that is based entirely on acoustic features. These acoustic features capitalize on acoustic edges and outperform Gabor-filtered spectrograms, which can explicitly describe the spectrotemporal characteristics of individual phonemes. By replicating our results in publicly available electroencephalography (EEG) data, we conclude that models of brain responses based on linguistic features can serve as excellent benchmarks. However, we believe that in order to further our understanding of human cortical responses to speech, we should also explore low-level and parsimonious explanations for apparent high-level phenomena.

Why Study the History of Neuroscience?

The history of neuroscience is the memory of the discipline and this memory depends on the study of the present traces of the past; the things left behind: artifacts, equipment, written documents, data books, photographs, memoirs, etc. History, in all of its definitions, is an integral part of neuroscience and I have used examples from the literature and my personal experience to illustrate the importance of the different aspects of history in neuroscience. Each time we talk about the brain, do an experiment, or write a research article, we are involved in history. Each published experiment becomes a historical document; it relies on past research (the "Introduction" section), procedures developed in the past ("Methods" section) and as soon as new data are published, they become history and become embedded into the history of the discipline ("Discussion" section). In order to be transparent and able to be replicated, each experiment requires its own historical archive. Studying history means researching books, documents and objects in libraries, archives, and museums. It means looking at data books, letters and memos, talking to scientists, and reading biographies and autobiographies. History can be made relevant by integrating historical documents into classes and by using historical websites. Finally, conducting historical research can be interesting, entertaining, and can lead to travel to out-of-the-way and exotic places and meeting interesting people.

General functional connectivity: Shared features of resting-state and task fMRI drive reliable and heritable individual differences in functional brain networks

Intrinsic connectivity, measured using resting-state fMRI, has emerged as a fundamental tool in the study of the human brain. However, due to practical limitations, many studies do not collect enough resting-state data to generate reliable measures of intrinsic connectivity necessary for studying individual differences. Here we present general functional connectivity (GFC) as a method for leveraging shared features across resting-state and task fMRI and demonstrate in the Human Connectome Project and the Dunedin Study that GFC offers better test-retest reliability than intrinsic connectivity estimated from the same amount of resting-state data alone. Furthermore, at equivalent scan lengths, GFC displayed higher estimates of heritability than resting-state functional connectivity. We also found that predictions of cognitive ability from GFC generalized across datasets, performing as well or better than resting-state or task data alone. Collectively, our work suggests that GFC can improve the reliability of intrinsic connectivity estimates in existing datasets and, subsequently, the opportunity to identify meaningful correlates of individual differences in behavior. Given that task and resting-state data are often collected together, many researchers can immediately derive more reliable measures of intrinsic connectivity through the adoption of GFC rather than solely using resting-state data. Moreover, by better capturing heritable variation in intrinsic connectivity, GFC represents a novel endophenotype with broad applications in clinical neuroscience and biomarker discovery.

Ten simple rules for predictive modeling of individual differences in neuroimaging

Establishing brain-behavior associations that map brain organization to phenotypic measures and generalize to novel individuals remains a challenge in neuroimaging. Predictive modeling approaches that define and validate models with independent datasets offer a solution to this problem. While these methods can detect novel and generalizable brain-behavior associations, they can be daunting, which has limited their use by the wider connectivity community. Here, we offer practical advice and examples based on functional magnetic resonance imaging (fMRI) functional connectivity data for implementing these approaches. We hope these ten rules will increase the use of predictive models with neuroimaging data.

Physiological significance of R-fMRI indices: Can functional metrics differentiate structural lesions (brain tumors)?

Resting-state functional MRI (R-fMRI) research has recently entered the era of “big data”, however, few studies have provided a rigorous validation of the physiological underpinnings of R-fMRI indices. Although studies have reported that various neuropsychiatric disorders exhibit abnormalities in R-fMRI measures, these “biomarkers” have not been validated in differentiating structural lesions (brain tumors) as a concept proof. We enrolled 60 patients with intracranial tumors located in the unilateral cranialcavity and 60 matched normal controls to test whether R-fMRI indices can differentiate tumors, which represents a prerequisite for adapting such indices as biomarkers for neuropsychiatric disorders. Common R-fMRI indices of tumors and their counterpart control regions, which were defined as the contralateral normal areas (for amplitude of low frequency fluctuations (ALFF), fractional ALFF (fALFF), regional homogeneity (ReHo) and degree centrality (DC)) and ipsilateral regions surrounding the tumors (for voxel-mirrored homotopic connectivity (VMHC)), were comprehensively assessed. According to robust paired t-tests with a Bonferroni correction, only VMHC (Fisher's r-to-z transformed) could successfully differentiate substantial tumors from their counterpart normal regions in patients. Furthermore, ALFF and DC were not able to differentiate tumor from normal unless Z-standardization was employed. To validate the lower power of the between-subject design compared to the within-subject design, each metric was calculated in a matched control group, and robust two-sample t-tests were used to compare the patient tumors and the normal controls at the same place. Similarly, only VMHC succeeded in differentiating significant differences between tumors and the sham tumor areas of normal controls. This study tested the premise of R-fMRI biomarkers for differentiating lesions, and brings a new understanding to physical significance of the Z-standardization.

•

R-fMRI indices could differentiate tumors, validating their physical availability.

•

ALFF and DC could not differentiate tumors unless Z-standardization was employed.

•

Within-subject design is more powerful for R-fMRI indices in differentiating tumors.

Exploration, Inference, and Prediction in Neuroscience and Biomedicine

Recent decades have seen dramatic progress in brain research. These advances were often buttressed by probing single variables to make circumscribed discoveries, typically through null hypothesis significance testing. New ways for generating massive data fueled tension between the traditional methodology that is used to infer statistically relevant effects in carefully chosen variables, and pattern-learning algorithms that are used to identify predictive signatures by searching through abundant information. In this article we detail the antagonistic philosophies behind two quantitative approaches: certifying robust effects in understandable variables, and evaluating how accurately a built model can forecast future outcomes. We discourage choosing analytical tools via categories such as 'statistics' or 'machine learning'. Instead, to establish reproducible knowledge about the brain, we advocate prioritizing tools in view of the core motivation of each quantitative analysis: aiming towards mechanistic insight or optimizing predictive accuracy.

Unsupervised discovery of temporal sequences in high-dimensional datasets, with applications to neuroscience

Identifying low-dimensional features that describe large-scale neural recordings is a major challenge in neuroscience. Repeated temporal patterns (sequences) are thought to be a salient feature of neural dynamics, but are not succinctly captured by traditional dimensionality reduction techniques. Here, we describe a software toolbox—called seqNMF—with new methods for extracting informative, non-redundant, sequences from high-dimensional neural data, testing the significance of these extracted patterns, and assessing the prevalence of sequential structure in data. We test these methods on simulated data under multiple noise conditions, and on several real neural and behavioral data sets. In hippocampal data, seqNMF identifies neural sequences that match those calculated manually by reference to behavioral events. In songbird data, seqNMF discovers neural sequences in untutored birds that lack stereotyped songs. Thus, by identifying temporal structure directly from neural data, seqNMF enables dissection of complex neural circuits without relying on temporal references from stimuli or behavioral outputs.

Enhanced Molecular Appreciation of Psychiatric Disorders Through High-Dimensionality Data Acquisition and Analytics

The initial diagnosis, molecular investigation, treatment, and posttreatment care of major psychiatric disorders (schizophrenia and bipolar depression) are all still significantly hindered by the current inability to define these disorders in an explicit molecular signaling manner. High-dimensionality data analytics, using large datastreams from transcriptomic, proteomic, or metabolomic investigations, will likely advance both the appreciation of the molecular nature of major psychiatric disorders and simultaneously enhance our ability to more efficiently diagnose and treat these debilitating conditions. High-dimensionality data analysis in psychiatric research has been heterogeneous in aims and methods and limited by insufficient sample sizes, poorly defined case definitions, methodological inhomogeneity, and confounding results. All of these issues combine to constrain the conclusions that can be extracted from them. Here, we discuss possibilities for overcoming methodological challenges through the implementation of transcriptomic, proteomic, or metabolomics signatures in psychiatric diagnosis and offer an outlook for future investigations. To fulfill the promise of intelligent high-dimensionality data-based differential diagnosis in mental disease diagnosis and treatment, future research will need large, well-defined cohorts in combination with state-of-the-art technologies.