Human local field potentials in motor and non-motor brain areas encode upcoming movement direction.

Limb movement direction can be inferred from local field potentials in motor cortex during movement execution. Yet, it remains unclear to what extent intended hand movements can be predicted from brain activity recorded during movement planning. Here, we set out to probe the directional-tuning of oscillatory features during motor planning and execution, using a machine learning framework on multi-site local field potentials (LFPs) in humans. We recorded intracranial EEG data from implanted epilepsy patients as they performed a four-direction delayed center-out motor task. Fronto-parietal LFP low-frequency power predicted hand-movement direction during planning while execution was largely mediated by higher frequency power and low-frequency phase in motor areas. By contrast, Phase-Amplitude Coupling showed uniform modulations across directions. Finally, multivariate classification led to an increase in overall decoding accuracy (>80%). The novel insights revealed here extend our understanding of the role of neural oscillations in encoding motor plans.

Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data.

Machine learning (ML) is increasingly used in cognitive, computational and clinical neuroscience. The reliable and efficient application of ML requires a sound understanding of its subtleties and limitations. Training ML models on datasets with imbalanced classes is a particularly common problem, and it can have severe consequences if not adequately addressed. With the neuroscience ML user in mind, this paper provides a didactic assessment of the class imbalance problem and illustrates its impact through systematic manipulation of data imbalance ratios in (i) simulated data and (ii) brain data recorded with electroencephalography (EEG), magnetoencephalography (MEG) and functional magnetic resonance imaging (fMRI). Our results illustrate how the widely-used Accuracy (Acc) metric, which measures the overall proportion of successful predictions, yields misleadingly high performances, as class imbalance increases. Because Acc weights the per-class ratios of correct predictions proportionally to class size, it largely disregards the performance on the minority class. A binary classification model that learns to systematically vote for the majority class will yield an artificially high decoding accuracy that directly reflects the imbalance between the two classes, rather than any genuine generalizable ability to discriminate between them. We show that other evaluation metrics such as the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC), and the less common Balanced Accuracy (BAcc) metric - defined as the arithmetic mean between sensitivity and specificity, provide more reliable performance evaluations for imbalanced data. Our findings also highlight the robustness of Random Forest (RF), and the benefits of using stratified cross-validation and hyperprameter optimization to tackle data imbalance. Critically, for neuroscience ML applications that seek to minimize overall classification error, we recommend the routine use of BAcc, which in the specific case of balanced data is equivalent to using standard Acc, and readily extends to multi-class settings. Importantly, we present a list of recommendations for dealing with imbalanced data, as well as open-source code to allow the neuroscience community to replicate and extend our observations and explore alternative approaches to coping with imbalanced data.

Beta Oscillations in Monkey Striatum Encode Reward Prediction Error Signals.

Reward prediction error (RPE) signals are crucial for reinforcement learning and decision-making as they quantify the mismatch between predicted and obtained rewards. RPE signals are encoded in the neural activity of multiple brain areas, such as midbrain dopaminergic neurons, prefrontal cortex, and striatum. However, it remains unclear how these signals are expressed through anatomically and functionally distinct subregions of the striatum. In the current study, we examined to which extent RPE signals are represented across different striatal regions. To do so, we recorded local field potentials (LFPs) in sensorimotor, associative, and limbic striatal territories of two male rhesus monkeys performing a free-choice probabilistic learning task. The trial-by-trial evolution of RPE during task performance was estimated using a reinforcement learning model fitted on monkeys' choice behavior. Overall, we found that changes in beta band oscillations (15-35 Hz), after the outcome of the animal's choice, are consistent with RPE encoding. Moreover, we provide evidence that the signals related to RPE are more strongly represented in the ventral (limbic) than dorsal (sensorimotor and associative) part of the striatum. To conclude, our results suggest a relationship between striatal beta oscillations and the evaluation of outcomes based on RPE signals and highlight a major contribution of the ventral striatum to the updating of learning processes.SIGNIFICANCE STATEMENT Reward prediction error (RPE) signals are crucial for reinforcement learning and decision-making as they quantify the mismatch between predicted and obtained rewards. Current models suggest that RPE signals are encoded in the neural activity of multiple brain areas, including the midbrain dopaminergic neurons, prefrontal cortex and striatum. However, it remains elusive whether RPEs recruit anatomically and functionally distinct subregions of the striatum. Our study provides evidence that RPE-related modulations in local field potential (LFP) power are dominant in the striatum. In particular, they are stronger in the rostro-ventral rather than the caudo-dorsal striatum. Our findings contribute to a better understanding of the role of striatal territories in reward-based learning and may be relevant for neuropsychiatric and neurologic diseases that affect striatal circuits.

Cholinergic interneuron inhibition potentiates corticostriatal transmission in direct medium spiny neurons and rescues motor learning in parkinsonism.

Striatal cholinergic interneurons (CINs) respond to salient or reward prediction-related stimuli after conditioning with brief pauses in their activity, implicating them in learning and action selection. This pause is lost in animal models of Parkinson's disease. How this signal regulates the striatal network remains an open question. Here, we examine the impact of CIN firing inhibition on glutamatergic transmission between the cortex and the medium spiny neurons expressing dopamine D1 receptor (D1 MSNs). Brief interruption of CIN activity has no effect in control conditions, whereas it increases glutamatergic responses in D1 MSNs after dopamine denervation. This potentiation depends upon M4 muscarinic receptor and protein kinase A. Decreasing CIN firing by optogenetics/chemogenetics in vivo partially rescues long-term potentiation in MSNs and motor learning deficits in parkinsonian mice. Our findings demonstrate that the control exerted by CINs on corticostriatal transmission and striatal-dependent motor-skill learning depends on the integrity of dopaminergic inputs.

Group-level inference of information-based measures for the analyses of cognitive brain networks from neurophysiological data.

The reproducibility crisis in neuroimaging and in particular in the case of underpowered studies has introduced doubts on our ability to reproduce, replicate and generalize findings. As a response, we have seen the emergence of suggested guidelines and principles for neuroscientists known as Good Scientific Practice for conducting more reliable research. Still, every study remains almost unique in its combination of analytical and statistical approaches. While it is understandable considering the diversity of designs and brain data recording, it also represents a striking point against reproducibility. Here, we propose a non-parametric permutation-based statistical framework, primarily designed for neurophysiological data, in order to perform group-level inferences on non-negative measures of information encompassing metrics from information-theory, machine-learning or measures of distances. The framework supports both fixed- and random-effect models to adapt to inter-individuals and inter-sessions variability. Using numerical simulations, we compared the accuracy in ground-truth retrieving of both group models, such as test- and cluster-wise corrections for multiple comparisons. We then reproduced and extended existing results using both spatially uniform MEG and non-uniform intracranial neurophysiological data. We showed how the framework can be used to extract stereotypical task- and behavior-related effects across the population covering scales from the local level of brain regions, inter-areal functional connectivity to measures summarizing network properties. We also present an open-source Python toolbox called Frites1 that includes the proposed statistical pipeline using information-theoretic metrics such as single-trial functional connectivity estimations for the extraction of cognitive brain networks. Taken together, we believe that this framework deserves careful attention as its robustness and flexibility could be the starting point toward the uniformization of statistical approaches.

Good scientific practice in EEG and MEG research: Progress and perspectives.

Good scientific practice (GSP) refers to both explicit and implicit rules, recommendations, and guidelines that help scientists to produce work that is of the highest quality at any given time, and to efficiently share that work with the community for further scrutiny or utilization. For experimental research using magneto- and electroencephalography (MEEG), GSP includes specific standards and guidelines for technical competence, which are periodically updated and adapted to new findings. However, GSP also needs to be regularly revisited in a broader light. At the LiveMEEG 2020 conference, a reflection on GSP was fostered that included explicitly documented guidelines and technical advances, but also emphasized intangible GSP: a general awareness of personal, organizational, and societal realities and how they can influence MEEG research. This article provides an extensive report on most of the LiveMEEG contributions and new literature, with the additional aim to synthesize ongoing cultural changes in GSP. It first covers GSP with respect to cognitive biases and logical fallacies, pre-registration as a tool to avoid those and other early pitfalls, and a number of resources to enable collaborative and reproducible research as a general approach to minimize misconceptions. Second, it covers GSP with respect to data acquisition, analysis, reporting, and sharing, including new tools and frameworks to support collaborative work. Finally, GSP is considered in light of ethical implications of MEEG research and the resulting responsibility that scientists have to engage with societal challenges. Considering among other things the benefits of peer review and open access at all stages, the need to coordinate larger international projects, the complexity of MEEG subject matter, and today's prioritization of fairness, privacy, and the environment, we find that current GSP tends to favor collective and cooperative work, for both scientific and for societal reasons.

Subthalamic low-frequency oscillations predict vulnerability to cocaine addiction.

Identifying vulnerable individuals before they transition to a compulsive pattern of drug seeking and taking is a key challenge in addiction to develop efficient prevention strategies. Oscillatory activity within the subthalamic nucleus (STN) has been associated with compulsive-related disorders. To study compulsive cocaine-seeking behavior, a core component of drug addiction, we have used a rat model in which cocaine seeking despite a foot-shock contingency only emerges in some vulnerable individuals having escalated their cocaine intake. We show that abnormal oscillatory activity within the alpha/theta and low-beta bands during the escalation of cocaine intake phase predicts the subsequent emergence of compulsive-like seeking behavior. In fact, mimicking STN pathological activity in noncompulsive rats during cocaine escalation turns them into compulsive ones. We also find that 30 Hz, but not 130 Hz, STN deep brain stimulation (DBS) reduces pathological cocaine seeking in compulsive individuals. Our results identify an early electrical signature of future compulsive-like cocaine-seeking behavior and further advocates the use of frequency-dependent STN DBS for the treatment of addiction.

Decoding the neural dynamics of free choice in humans.

How do we choose a particular action among equally valid alternatives? Nonhuman primate findings have shown that decision-making implicates modulations in unit firing rates and local field potentials (LFPs) across frontal and parietal cortices. Yet the electrophysiological brain mechanisms that underlie free choice in humans remain ill defined. Here, we address this question using rare intracerebral electroencephalography (EEG) recordings in surgical epilepsy patients performing a delayed oculomotor decision task. We find that the temporal dynamics of high-gamma (HG, 60-140 Hz) neural activity in distinct frontal and parietal brain areas robustly discriminate free choice from instructed saccade planning at the level of single trials. Classification analysis was applied to the LFP signals to isolate decision-related activity from sensory and motor planning processes. Compared with instructed saccades, free-choice trials exhibited delayed and longer-lasting HG activity during the delay period. The temporal dynamics of the decision-specific sustained HG activity indexed the unfolding of a deliberation process, rather than memory maintenance. Taken together, these findings provide the first direct electrophysiological evidence in humans for the role of sustained high-frequency neural activation in frontoparietal cortex in mediating the intrinsically driven process of freely choosing among competing behavioral alternatives.

Tensorpac: An open-source Python toolbox for tensor-based phase-amplitude coupling measurement in electrophysiological brain signals.

Despite being the focus of a thriving field of research, the biological mechanisms that underlie information integration in the brain are not yet fully understood. A theory that has gained a lot of traction in recent years suggests that multi-scale integration is regulated by a hierarchy of mutually interacting neural oscillations. In particular, there is accumulating evidence that phase-amplitude coupling (PAC), a specific form of cross-frequency interaction, plays a key role in numerous cognitive processes. Current research in the field is not only hampered by the absence of a gold standard for PAC analysis, but also by the computational costs of running exhaustive computations on large and high-dimensional electrophysiological brain signals. In addition, various signal properties and analyses parameters can lead to spurious PAC. Here, we present Tensorpac, an open-source Python toolbox dedicated to PAC analysis of neurophysiological data. The advantages of Tensorpac include (1) higher computational efficiency thanks to software design that combines tensor computations and parallel computing, (2) the implementation of all most widely used PAC methods in one package, (3) the statistical analysis of PAC measures, and (4) extended PAC visualization capabilities. Tensorpac is distributed under a BSD-3-Clause license and can be launched on any operating system (Linux, OSX and Windows). It can be installed directly via pip or downloaded from Github (https://github.com/EtienneCmb/tensorpac). By making Tensorpac available, we aim to enhance the reproducibility and quality of PAC research, and provide open tools that will accelerate future method development in neuroscience.

NeuroPycon: An open-source python toolbox for fast multi-modal and reproducible brain connectivity pipelines.

Recent years have witnessed a massive push towards reproducible research in neuroscience. Unfortunately, this endeavor is often challenged by the large diversity of tools used, project-specific custom code and the difficulty to track all user-defined parameters. NeuroPycon is an open-source multi-modal brain data analysis toolkit which provides Python-based template pipelines for advanced multi-processing of MEG, EEG, functional and anatomical MRI data, with a focus on connectivity and graph theoretical analyses. Importantly, it provides shareable parameter files to facilitate replication of all analysis steps. NeuroPycon is based on the NiPype framework which facilitates data analyses by wrapping many commonly-used neuroimaging software tools into a common Python environment. In other words, rather than being a brain imaging software with is own implementation of standard algorithms for brain signal processing, NeuroPycon seamlessly integrates existing packages (coded in python, Matlab or other languages) into a unified python framework. Importantly, thanks to the multi-threaded processing and computational efficiency afforded by NiPype, NeuroPycon provides an easy option for fast parallel processing, which critical when handling large sets of multi-dimensional brain data. Moreover, its flexible design allows users to easily configure analysis pipelines by connecting distinct nodes to each other. Each node can be a Python-wrapped module, a user-defined function or a well-established tool (e.g. MNE-Python for MEG analysis, Radatools for graph theoretical metrics, etc.). Last but not least, the ability to use NeuroPycon parameter files to fully describe any pipeline is an important feature for reproducibility, as they can be shared and used for easy replication by others. The current implementation of NeuroPycon contains two complementary packages: The first, called ephypype, includes pipelines for electrophysiology analysis and a command-line interface for on the fly pipeline creation. Current implementations allow for MEG/EEG data import, pre-processing and cleaning by automatic removal of ocular and cardiac artefacts, in addition to sensor or source-level connectivity analyses. The second package, called graphpype, is designed to investigate functional connectivity via a wide range of graph-theoretical metrics, including modular partitions. The present article describes the philosophy, architecture, and functionalities of the toolkit and provides illustrative examples through interactive notebooks. NeuroPycon is available for download via github (https://github.com/neuropycon) and the two principal packages are documented online (https://neuropycon.github.io/ephypype/index.html, and https://neuropycon.github.io/graphpype/index.html). Future developments include fusion of multi-modal data (eg. MEG and fMRI or intracranial EEG and fMRI). We hope that the release of NeuroPycon will attract many users and new contributors, and facilitate the efforts of our community towards open source tool sharing and development, as well as scientific reproducibility.

Visbrain: A Multi-Purpose GPU-Accelerated Open-Source Suite for Multimodal Brain Data Visualization.

We present Visbrain, a Python open-source package that offers a comprehensive visualization suite for neuroimaging and electrophysiological brain data. Visbrain consists of two levels of abstraction: (1) objects which represent highly configurable neuro-oriented visual primitives (3D brain, sources connectivity, etc.) and (2) graphical user interfaces for higher level interactions. The object level offers flexible and modular tools to produce and automate the production of figures using an approach similar to that of Matplotlib with subplots. The second level visually connects these objects by controlling properties and interactions through graphical interfaces. The current release of Visbrain (version 0.4.2) contains 14 different objects and three responsive graphical user interfaces, built with PyQt: Signal, for the inspection of time-series and spectral properties, Brain for any type of visualization involving a 3D brain and Sleep for polysomnographic data visualization and sleep analysis. Each module has been developed in tight collaboration with end-users, i.e., primarily neuroscientists and domain experts, who bring their experience to make Visbrain as transparent as possible to the recording modalities (e.g., intracranial EEG, scalp-EEG, MEG, anatomical and functional MRI). Visbrain is developed on top of VisPy, a Python package providing high-performance 2D and 3D visualization by leveraging the computational power of the graphics card. Visbrain is available on Github and comes with a documentation, examples, and datasets (http://visbrain.org).

Long-range temporal correlations in the brain distinguish conscious wakefulness from induced unconsciousness.

Rhythmic neuronal synchronization across large-scale networks is thought to play a key role in the regulation of conscious states. Changes in neuronal oscillation amplitude across states of consciousness have been widely reported, but little is known about possible changes in the temporal dynamics of these oscillations. The temporal structure of brain oscillations may provide novel insights into the neural mechanisms underlying consciousness. To address this question, we examined long-range temporal correlations (LRTC) of EEG oscillation amplitudes recorded during both wakefulness and anesthetic-induced unconsciousness. Importantly, the time-varying EEG oscillation envelopes were assessed over the course of a sevoflurane sedation protocol during which the participants alternated between states of consciousness and unconsciousness. Both spectral power and LRTC in oscillation amplitude were computed across multiple frequency bands. State-dependent differences in these features were assessed using non-parametric tests and supervised machine learning. We found that periods of unconsciousness were associated with increases in LRTC in beta (15-30Hz) amplitude over frontocentral channels and with a suppression of alpha (8-13Hz) amplitude over occipitoparietal electrodes. Moreover, classifiers trained to predict states of consciousness on single epochs demonstrated that the combination of beta LRTC with alpha amplitude provided the highest classification accuracy (above 80%). These results suggest that loss of consciousness is accompanied by an augmentation of temporal persistence in neuronal oscillation amplitude, which may reflect an increase in regularity and a decrease in network repertoire compared to the brain's activity during resting-state consciousness.

Sleep: An Open-Source Python Software for Visualization, Analysis, and Staging of Sleep Data.

We introduce Sleep, a new Python open-source graphical user interface (GUI) dedicated to visualization, scoring and analyses of sleep data. Among its most prominent features are: (1) Dynamic display of polysomnographic data, spectrogram, hypnogram and topographic maps with several customizable parameters, (2) Implementation of several automatic detection of sleep features such as spindles, K-complexes, slow waves, and rapid eye movements (REM), (3) Implementation of practical signal processing tools such as re-referencing or filtering, and (4) Display of main descriptive statistics including publication-ready tables and figures. The software package supports loading and reading raw EEG data from standard file formats such as European Data Format, in addition to a range of commercial data formats. Most importantly, Sleep is built on top of the VisPy library, which provides GPU-based fast and high-level visualization. As a result, it is capable of efficiently handling and displaying large sleep datasets. Sleep is freely available (http://visbrain.org/sleep) and comes with sample datasets and an extensive documentation. Novel functionalities will continue to be added and open-science community efforts are expected to enhance the capacities of this module.

Measuring alterations in oscillatory brain networks in schizophrenia with resting-state MEG: State-of-the-art and methodological challenges.

OBJECTIVE: Neuroimaging studies provide evidence of disturbed resting-state brain networks in Schizophrenia (SZ). However, untangling the neuronal mechanisms that subserve these baseline alterations requires measurement of their electrophysiological underpinnings. This systematic review specifically investigates the contributions of resting-state Magnetoencephalography (MEG) in elucidating abnormal neural organization in SZ patients. METHOD: A systematic literature review of resting-state MEG studies in SZ was conducted. This literature is discussed in relation to findings from resting-state fMRI and EEG, as well as to task-based MEG research in SZ population. Importantly, methodological limitations are considered and recommendations to overcome current limitations are proposed. RESULTS: Resting-state MEG literature in SZ points towards altered local and long-range oscillatory network dynamics in various frequency bands. Critical methodological challenges with respect to experiment design, and data collection and analysis need to be taken into consideration. CONCLUSION: Spontaneous MEG data show that local and global neural organization is altered in SZ patients. MEG is a highly promising tool to fill in knowledge gaps about the neurophysiology of SZ. However, to reach its fullest potential, basic methodological challenges need to be overcome. SIGNIFICANCE: MEG-based resting-state power and connectivity findings could be great assets to clinical and translational research in psychiatry, and SZ in particular.

Alterations of Intrinsic Brain Connectivity Patterns in Depression and Bipolar Disorders: A Critical Assessment of Magnetoencephalography-Based Evidence.

Despite being the object of a thriving field of clinical research, the investigation of intrinsic brain network alterations in psychiatric illnesses is still in its early days. Because the pathological alterations are predominantly probed using functional magnetic resonance imaging (fMRI), many questions about the electrophysiological bases of resting-state alterations in psychiatric disorders, particularly among mood disorder patients, remain unanswered. Alongside important research using electroencephalography (EEG), the specific recent contributions and future promise of magnetoencephalography (MEG) in this field are not fully recognized and valued. Here, we provide a critical review of recent findings from MEG resting-state connectivity within major depressive disorder (MDD) and bipolar disorder (BD). The clinical MEG resting-state results are compared with those previously reported with fMRI and EEG. Taken together, MEG appears to be a promising but still critically underexploited technique to unravel the neurophysiological mechanisms that mediate abnormal (both hyper- and hypo-) connectivity patterns involved in MDD and BD. In particular, a major strength of MEG is its ability to provide source-space estimations of neuromagnetic long-range rhythmic synchronization at various frequencies (i.e., oscillatory coupling). The reviewed literature highlights the relevance of probing local and interregional rhythmic synchronization to explore the pathophysiological underpinnings of each disorder. However, before we can fully take advantage of MEG connectivity analyses in psychiatry, several limitations inherent to MEG connectivity analyses need to be understood and taken into account. Thus, we also discuss current methodological challenges and outline paths for future research. MEG resting-state studies provide an important window onto perturbed spontaneous oscillatory brain networks and hence supply an important complement to fMRI-based resting-state measurements in psychiatric populations.

Meet Spinky: An Open-Source Spindle and K-Complex Detection Toolbox Validated on the Open-Access Montreal Archive of Sleep Studies (MASS).

Sleep spindles and K-complexes are among the most prominent micro-events observed in electroencephalographic (EEG) recordings during sleep. These EEG microstructures are thought to be hallmarks of sleep-related cognitive processes. Although tedious and time-consuming, their identification and quantification is important for sleep studies in both healthy subjects and patients with sleep disorders. Therefore, procedures for automatic detection of spindles and K-complexes could provide valuable assistance to researchers and clinicians in the field. Recently, we proposed a framework for joint spindle and K-complex detection (Lajnef et al., 2015a) based on a Tunable Q-factor Wavelet Transform (TQWT; Selesnick, 2011a) and morphological component analysis (MCA). Using a wide range of performance metrics, the present article provides critical validation and benchmarking of the proposed approach by applying it to open-access EEG data from the Montreal Archive of Sleep Studies (MASS; O'Reilly et al., 2014). Importantly, the obtained scores were compared to alternative methods that were previously tested on the same database. With respect to spindle detection, our method achieved higher performance than most of the alternative methods. This was corroborated with statistic tests that took into account both sensitivity and precision (i.e., Matthew's coefficient of correlation (MCC), F1, Cohen κ). Our proposed method has been made available to the community via an open-source tool named Spinky (for spindle and K-complex detection). Thanks to a GUI implementation and access to Matlab and Python resources, Spinky is expected to contribute to an open-science approach that will enhance replicability and reliable comparisons of classifier performances for the detection of sleep EEG microstructure in both healthy and patient populations.

Direct Recordings from Human Anterior Insula Reveal its Leading Role within the Error-Monitoring Network.

The ability to monitor our own errors is mediated by a network that includes dorsomedial prefrontal cortex (dmPFC) and anterior insula (AI). However, the dynamics of the underlying neurophysiological processes remain unclear. In particular, whether AI is on the receiving or driving end of the error-monitoring network is unresolved. Here, we recorded intracerebral electroencephalography signals simultaneously from AI and dmPFC in epileptic patients while they performed a stop-signal task. We found that errors selectively modulated broadband neural activity in human AI. Granger causality estimates revealed that errors were immediately followed by a feedforward influence from AI onto anterior cingulate cortex and, subsequently, onto presupplementary motor area. The reverse pattern of information flow was observed on correct responses. Our findings provide the first direct electrophysiological evidence indicating that the anterior insula rapidly detects and conveys error signals to dmPFC, while the latter might use this input to adapt behavior following inappropriate actions.

From intentions to actions: Neural oscillations encode motor processes through phase, amplitude and phase-amplitude coupling.

Goal-directed motor behavior is associated with changes in patterns of rhythmic neuronal activity across widely distributed brain areas. In particular, movement initiation and execution are mediated by patterns of synchronization and desynchronization that occur concurrently across distinct frequency bands and across multiple motor cortical areas. To date, motor-related local oscillatory modulations have been predominantly examined by quantifying increases or suppressions in spectral power. However, beyond signal power, spectral properties such as phase and phase-amplitude coupling (PAC) have also been shown to carry information with regards to the oscillatory dynamics underlying motor processes. Yet, the distinct functional roles of phase, amplitude and PAC across the planning and execution of goal-directed motor behavior remain largely elusive. Here, we address this question with unprecedented resolution thanks to multi-site intracerebral EEG recordings in human subjects while they performed a delayed motor task. To compare the roles of phase, amplitude and PAC, we monitored intracranial brain signals from 748 sites across six medically intractable epilepsy patients at movement execution, and during the delay period where motor intention is present but execution is withheld. In particular, we used a machine-learning framework to identify the key contributions of various neuronal responses. We found a high degree of overlap between brain network patterns observed during planning and those present during execution. Prominent amplitude increases in the delta (2-4Hz) and high gamma (60-200Hz) bands were observed during both planning and execution. In contrast, motor alpha (8-13Hz) and beta (13-30Hz) power were suppressed during execution, but enhanced during the delay period. Interestingly, single-trial classification revealed that low-frequency phase information, rather than spectral power change, was the most discriminant feature in dissociating action from intention. Additionally, despite providing weaker decoding, PAC features led to statistically significant classification of motor states, particularly in anterior cingulate cortex and premotor brain areas. These results advance our understanding of the distinct and partly overlapping involvement of phase, amplitude and the coupling between them, in the neuronal mechanisms underlying motor intentions and executions.

Exceeding chance level by chance: The caveat of theoretical chance levels in brain signal classification and statistical assessment of decoding accuracy.

Machine learning techniques are increasingly used in neuroscience to classify brain signals. Decoding performance is reflected by how much the classification results depart from the rate achieved by purely random classification. In a 2-class or 4-class classification problem, the chance levels are thus 50% or 25% respectively. However, such thresholds hold for an infinite number of data samples but not for small data sets. While this limitation is widely recognized in the machine learning field, it is unfortunately sometimes still overlooked or ignored in the emerging field of brain signal classification. Incidentally, this field is often faced with the difficulty of low sample size. In this study we demonstrate how applying signal classification to Gaussian random signals can yield decoding accuracies of up to 70% or higher in two-class decoding with small sample sets. Most importantly, we provide a thorough quantification of the severity and the parameters affecting this limitation using simulations in which we manipulate sample size, class number, cross-validation parameters (k-fold, leave-one-out and repetition number) and classifier type (Linear-Discriminant Analysis, Naïve Bayesian and Support Vector Machine). In addition to raising a red flag of caution, we illustrate the use of analytical and empirical solutions (binomial formula and permutation tests) that tackle the problem by providing statistical significance levels (p-values) for the decoding accuracy, taking sample size into account. Finally, we illustrate the relevance of our simulations and statistical tests on real brain data by assessing noise-level classifications in Magnetoencephalography (MEG) and intracranial EEG (iEEG) baseline recordings.