David Ibanez-Soria

State Visual Evoked Potentials (SSVEPs) arise from a resonance phenomenon in the visual cortex that is produced by a repetitive visual stimulus. SSVEPs have long been considered a steady-state response resulting from purely oscillatory components phase locked with the stimulation source, matching the stimulation frequency and its harmonics. Here we explore the dynamical character of the SSVEP response by proposing a novel non-stationary methodology for SSVEP detection based on an ensemble of Echo State Networks (ESN). The performance of this dynamical approach is compared to stationary canonical correlation analysis (CCA) for the detection of 6 visual stimulation frequencies ranging from 12 to 22 Hz. ESN-based methodology outperformed CCA, achieving an average information transfer rate of 47 bits/minute when simulating a BCI system of 6 degrees of freedom. However, for some subjects and stimulation frequencies the detection accuracy of CCA exceeds that of ESN. The comparison suggests that each methodology captures different features of the SSVEP response: while CCA captures purely stationary patterns, the ESN-based approach presented here is capable of detecting the non-stationary nature of the SSVEP.

Objective: Attention-deficit hyperactivity disorder (ADHD) is the neurobehavioral disorder with the largest prevalence rate in childhood. ADHD is generally assessed based on physical examination of the child and interviews, and therefore prone to subjectivity. This fact may lead to a high risk of mis- and over-diagnosis, a problem that can be addressed through the use of objective markers. Methods: Here we propose to use phase-amplitude coupling as a digital biomarker in ADHD. We investigated the hypothesis that coupling between the phase of slow brain rhythms and the amplitude of fast rhythms is altered in the ADHD population. We tested this hypothesis measuring phase-amplitude coupling (PAC) in the 4 to 200Hz range in electroencephalographic (EEG) signals recorded in the central-frontal area in children during eyes closed resting state. Results: Using automatic clustering, we observed statistically significant beta-gamma PAC deficits in the ADHD population in the frontal-left hemisphere. Conclusions: These findings suggests alterations in the beta-gamma coupling in the ADHD population. We discuss the hypothesis that these alterations may be indicators of working memory and attention deficits. Significance: The study of the coupling between the different brain rhythms can potentially contribute to the understanding and clinical diagnosis of ADHD.

Generalized synchronization between coupled dynamical systems is a phenomenon of relevance in applications that range from secure communications to physiological modelling. Here, we test the capabilities of reservoir computing and, in particular, echo state networks for the detection of generalized synchronization. A nonlinear dynamical system consisting of two coupled Rössler chaotic attractors is used to generate temporal series consisting of time-locked generalized synchronized sequences interleaved with unsynchronized ones. Correctly tuned, echo state networks are able to efficiently discriminate between unsynchronized and synchronized sequences even in the presence of relatively high levels of noise. Compared to other state-of-the-art techniques of synchronization detection, the online capabilities of the proposed Echo State Network based methodology make it a promising choice for real-time applications aiming to monitor dynamical synchronization changes in continuous signals.

Attention-Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder characterized by inattention, hyperactivity and impulsivity. It is one of the most commonly diagnosed neurodevelopmental and psychiatric disorders of childhood and therefore presents a very high prevalence rate. However the high rate of ADHD misdiagnosis makes the discovery of neurophysiological ADHD biomarkers an important clinical challenge. This study proposes a novel non-stationary ADHD biomarker based on Echo State Networks to quantify EEG dynamical changes between low attention/arousal states (resting with eyes closed, or EC) and normal attention/arousal states (resting with eyes open, or EO). Traditionally, EEG biomarkers have revealed an increase in stationary power in the theta band along with a decrease in beta, with these frequencies largely accepted to be altered in the ADHD population. We successfully verify the hypothesis that measured differences between these two conditions are altered in the ADHD population. Statistically significant differences between a group of ADHD subjects and an aged-matched control population were obtained in theta and beta rhythms. Our network discriminates between EO/EC EEG regimes in the ADHDs better than in controls, suggesting that differences in EEG patterns between low and normal arousal/attention states are larger in the ADHD population.

Background: Recent years have witnessed an increased interest in the use of steady state visual evoked potentials (SSVEPs) in brain computer interfaces (BCI), SSVEP is considered a stationary brain process that appears when gazing at a stimulation light source. New Methods: The complex nature of brain processes advocates for non-linear EEG analysis techniques. In this work we explore the use of an Echo State Networks (ESN) based architecture for dynamical SSVEP detection. Results: When simulating a 6-degrees of freedom BCI system, an information transfer rate of 49bits/min was achieved. Detection accuracy proved to be similar for observation windows ranging from 0.5 to 4 seconds. Comparison with existing methods: SSVEP detection performance has been compared to standard canonical correlation analysis (CCA). CCA achieved a maximum information transfer rate of 21 bits/minute. In this case detection accuracy increased along with the observation window length Conclusions: According to here presented results ESN outperforms standard canonical correlation and has proved to require shorter observation time windows. However ESN and CCA approaches delivered diverse classification accuracies at subject level for various stimulation frequencies, proving to be complementary methods. A possible explanation of these results may be the occurrence of evoked responses of different nature, which are then detected by different approaches. While reservoir computing methods are able to detect complex dynamical patterns and/or complex synchronization among EEG channels, CCA exclusively captures stationary patterns. Therefore, the ESN-based approach may be used to extend the definition of steady-state response, considered so far a stationary process. Highlights: We present a novel SSVEP dynamical detection approach based on ESN. This is the first time ESNs are applied to SSVEP based BCI systems. We provide experimental validation of proposed methodology. Experimental results indicate non-stationarity in SSVEP patterns.

Transcranial current stimulation (tCS) is a noninvasive form of brain stimulation that applies weak direct electrical currents to the brain through electrodes placed on the scalp. Different types of stimulation are available based on how the current delivered to the brain is modulated.¹ The most common approach is to hold the current constant during the stimulation period, this is known as transcranial direct current stimulation (tDCS). This method is commonly referred to as tDCS, but in order to avoid confusion with the optical method, we here use DC-tCS. DC-tCS induces bidirectional, polarity-dependent changes in cerebral excitability of humans^2,3 and has been shown to modulate cognition in both healthy subjects (improvement of cognitive function) and in patients (reversing the effects of cognitive deficits after a stroke).^4,5 Positive effects have also been shown in treatment of depression, chronic and acute pain, Parkinson’s disease, focal epilepsy, and for improving recovery after stroke.⁶ 7. 8. ^{– 9} A therapeutic application of this technique is appealing due to its relative low cost, to its demonstrated safety,¹⁰ and as a substitute for pharmacotherapy, especially for patients with poor drug tolerability.⁸

REM Behavior Disorder (RBD) is now recognized as the prodromal stage of α -synucleinopathies such as Parkinson’s disease (PD). In this paper, we describe deep learning models for diagnosis/prognosis derived from a few minutes of eyes-closed resting electroencephalography data (EEG) collected from idiopathic RBD patients (n=121) and healthy controls (HC, n=91). A few years after the EEG acquisition (4 ± 2 years), a subset of the RBD patients eventually developed either PD (n=14) or Dementia with Lewy bodies (DLB, n=13), while the rest remained idiopathic. We describe first a simple convolutional neural network (DCNN) with a five-layer architecture combining filtering and pooling, which we train using stacked multi-channel EEG spectrograms. We treat the data as in audio or image classification problems where deep networks have proven highly successful by exploiting compositional and translationally invariant features in the data. For comparison, we study an even simpler deep recurrent neural network using three stacked Long Short Term Memory network (LSTM) cells or gated-recurrent unit (GRU) cells—with very similar results. The performance of these networks typically reaches 80% (±1%) classification accuracy in the balanced HC vs. PD-outcome classification problem. In particular, using data from a single EEG channel we obtain an area under the curve (AUC) of 87% (±1%) while avoiding spectral feature selection. The trained classifier can also be used to generate synthetic spectrograms to study what spectrogram features are relevant for classification, pointing to the presence of theta band bursts and a decrease of power in the alpha band in future PD or DLB patients compared to HCs. We conclude that deep networks may provide a key tool for the analysis of EEG dynamics even from relatively small datasets and enable the delivery of new biomarkers.

Generalized synchronization between coupled dynamical systems is a phenomenon of relevance in applications that range from secure communications to physiological modelling. Here we test the capabilities of reservoir computing and, in particular, echo state networks for the detection of generalized synchronization. A nonlinear dynamical system consisting of two coupled R\"ossler chaotic attractors is used to generate temporal series consisting of time-locked generalized synchronized sequences interleaved by unsynchronized ones. Correctly tuned, echo state networks are able to efficiently discriminate between unsynchronized and synchronized sequences. Compared to other state-of-the-art techniques of synchronization detection, the online capabilities of the proposed ESN based methodology make it a promising choice for real-time applications aiming to monitor dynamical synchronization changes in continuous signals.

SUMMARY: Little is known about the precise neural mechanisms by which tACS affects the human cortex. Current hypothesis suggest that transcranial current stimulation (tCS) can directly enhance ongoing brain oscillations and induce long - lasting effects through the activation of synaptic plasticity mechanisms [1]. Entrainment has been demonstrated in in - vitro studies, but its presence in non-invasive human studies is still under debate [2,3]. Here, we aim to investigate the immediate and short-term effects of tACS bursts on the occipital cortex of participants engaged in a change – of - speed detection task, a task that has previously reported to have a clear physiology - behavior relationship, where trials with faster responses also have increased power in γ - oscillations (50 - 80 Hz) [4]. The dominant brain oscillations related to the visual task are modulated using multichannel tACS at 10 and 70 Hz within occipital cortex. We found that tACS stimulation at 10 Hz (tACS ₁₀ ) enhanced both α (8 - 13 Hz) and γ oscillations, in hand with an increase in reaction time (RT) in the change – of - speed detection visual task. On the other hand, tACS at 70Hz desynchronized visual cortices, impairing both phase - locked and endogenous γ - power while increasing RT. While both tACS protocols seem to revert the relationship reported in [4], we argue that tACS produces a shift in attentional resources within visual cortex while leaving unaltered the resources required to conduct the task. This theory is supported by the fact that the correlation between fast RT and high γ- power trials is maintained for tACS sessions too. Finally, we measured cortical excitability by analyzing Event – Related - Potentials (ERP) Lempel – Ziv - Welch Complexity (LZW). In control sessions we observe that lower γ - LZW complexity correlates to faster reaction times. Both metrics are altered by tACS stimulation, as tACS ₁₀ decreased amplitude of the P300 peak, while increasing γ- LZW complexity. To this end, our study highlights the nonlinear cross - frequency interaction between exogenous stimulation and endogenous brain dynamics, and proposes the use of complexity metrics, as LZW, to characterize excitability patterns of cortical areas in a behaviorally relevant timescale. These insights will hopefully contribute to the design of adaptive and personalized tACS protocols where cortical excitability can be characterized through complexity metrics. Additional Title Page Footnotes: We introduce a bursting tACS protocol to study semi-concurrent tACS effects in the visual system and their impact on behavior as measured by reaction time. Burst 10 Hz tACS (tACS ₁₀ ) applied to the visual cortex entrained γ-oscillations and increased RTs in a change-of-speed detection visual task more than 70 Hz tACS (tACS ₇₀ ) or Control conditions. Burst tACS ₁₀ also decreased amplitude of the P300 peak, while increasing α-power and γ-LZW complexity. Physiological and behavioral impact of occipital tACS ₁₀ and tACS ₇₀ was frequency-specific. tACS ₇₀ reduced γ-oscillations after 20min of tACS stimulation. Cognitive task may determine cortical excitation levels as measured by complexity metrics, as lower γ-LZW complexity correlates to faster reaction times.