Decoding naturalistic affective behaviour from spectro-spatial features in multiday human iEEG

Naturalistic acute pain states decoded from neural and facial dynamics

Pain remains poorly understood in task-free contexts, limiting our understanding of its neurobehavioral basis in naturalistic settings. Here, we use a multimodal, data-driven approach with intracranial electroencephalography, pain self-reports, and facial expression analysis to study acute pain in twelve epilepsy patients under continuous neural and audiovisual monitoring. Using machine learning, we successfully decode individual participants' high versus low pain states from distributed neural activity, involving mesolimbic regions, striatum, and temporoparietal cortex. Neural representation of pain remains stable for hours and is modulated by pain onset and relief. Objective facial expressions also classify pain states, concordant with neural findings. Importantly, we identify transient periods of momentary pain as a distinct naturalistic acute pain measure, which can be reliably discriminated from affect-neutral periods using neural and facial features. These findings reveal reliable neurobehavioral markers of acute pain across naturalistic contexts, underscoring the potential for monitoring and personalizing pain interventions in real-world settings.

Challenges and opportunities of acquiring cortical recordings for chronic adaptive deep brain stimulation

Deep brain stimulation (DBS), a proven treatment for movement disorders, also holds promise for the treatment of psychiatric and cognitive conditions. However, for DBS to be clinically effective, it may require DBS technology that can alter or trigger stimulation in response to changes in biomarkers sensed from the patient's brain. A growing body of evidence suggests that such adaptive DBS is feasible, it might achieve clinical effects that are not possible with standard continuous DBS and that some of the best biomarkers are signals from the cerebral cortex. Yet capturing those markers requires the placement of cortex-optimized electrodes in addition to standard electrodes for DBS. In this Perspective we argue that the need for cortical biomarkers in adaptive DBS and the unfortunate convergence of regulatory and financial factors underpinning the unavailability of cortical electrodes for chronic uses threatens to slow down or stall research on adaptive DBS and propose public-private partnerships as a potential solution to such a critical technological gap.

Stereo-encephalography-guided multi-lead deep brain stimulation for treatment-refractory obsessive compulsive disorder - study design and individualized surgical targeting approach

Introduction

Treatment-refractory obsessive-compulsive disorder (trOCD) is a complex brain network disorder that remains partially understood and may require personalized treatment strategies due to disease heterogeneity. While stereo-electroencephalography (sEEG) is standard of care for surgical epilepsy workups, its use in refractory neuropsychiatric disorders remains investigational. A multi-site, multi-stage, double-blinded, randomized crossover clinical trial is currently underway, using sEEG to guide selection of multi-nodal targets for subsequent deep brain stimulation (DBS) in the treatment of trOCD.

Objectives

To describe the study design of this ongoing clinical trial, with an emphasis on personalized surgical targeting strategies that ensure both the feasibility and precision of sEEG electrode placement, and enable adequate sampling of relevant targets in trOCD for network evaluation and modulation.

Methods

Adult patients with severe trOCD (Yale-Brown Obsessive Compulsive Scale ≥ 28) who meet eligibility criteria will be enrolled in this study. The clinical trial ( NCT05623306 ) involves three stages. In stage 1, up to 20 sEEG electrodes will be implanted in cortical and subcortical regions implicated in trOCD. Individualized probabilistic-tractography-guided target refinement will be performed for surgical planning. To ensure surgical feasibility of non-conventional surgical trajectories, patient-specific three-dimensional (3D) printed head models may be used for surgical rehearsal. Continuous and synchronous audiovisual and intracranial electroencephalographic (iEEG) recordings will be performed in the psychiatric monitoring unit. Participants undergo psychologist-led symptom provocations, brain stimulation evoked potential mapping, acute stimulation testing and cognitive tasks over a 12-day inpatient evaluation. In stage 2, up to four permanent DBS electrodes will be implanted followed by stimulation optimization for up to 52 weeks. Stage 3 involves a randomized, double-blinded cross-over phase.

Expected Outcomes

Safety, feasibility and preliminary efficacy will be assessed in this ongoing study. Primary safety endpoints include the number and type of serious adverse events. Feasibility endpoints include percentage of patients in whom OCD-relevant network or stimulation target can be identified. Treatment response will be determined by change in Y-BOCS II score between active and sham stimulation conditions. We anticipate that sEEG to guide selection of multi-nodal targets for DBS will be safe, feasible and result in clinically meaningful improvements in symptom severity and functional impairment in trOCD.

Discussion

We present the clinical protocol of sEEG-guided investigation of brain networks involved in trOCD and describe our tractography-guided surgical targeting strategy designed to optimize individualized network engagement and neuromodulation.

How mood-related physiological states bias economic decisions

When making decisions, humans are susceptible to all sorts of biases, relative to rational norms. An important factor is incidental changes in affective states, such as variations in mood between happiness and sadness. We previously developed a computational model, in which mood affects choice by forming a predisposition to face costs and seek more rewards. Here, we generalized this theory to account for how specific inductions of happiness and sadness affect different types of economic decisions involving a tradeoff between costs (risk, delay, effort) and benefits (financial rewards). Across exploratory and confirmatory studies (N = 94), we observed a consistent bias exerted by transitory mood states, whether they were assessed through self-reports (rated happiness minus sadness) or inferred from physiological measures (valence of facial expression times intensity of autonomous arousal). This choice bias was best explained by our computational model, with a mood-scaled bonus added to the value of the more rewarded but more costly option, irrespective of the cost type (risk, delay or effort). Additionally, gaze tracking during decision making confirmed that the choice bias was driven by an early preference for the mood-congruent option. Together, these results demonstrate the feasibility of predicting irrational choices from objective measures of affective states.

Cortisol awakening response prompts dynamic reconfiguration of brain networks in emotional and executive functioning

Emotion and cognition involve an intricate crosstalk of neural and endocrine systems that support dynamic reallocation of neural resources and optimal adaptation for upcoming challenges, an active process analogous to allostasis. As a hallmark of human endocrine activity, the cortisol awakening response (CAR) is recognized to play a critical role in proactively modulating emotional and executive functions. Yet, the underlying mechanisms of such proactive effects remain elusive. By leveraging pharmacological neuroimaging and hidden Markov modeling of brain state dynamics, we show that the CAR proactively modulates rapid spatiotemporal reconfigurations (state) of large-scale brain networks involved in emotional and executive functions. Behaviorally, suppression of CAR proactively impaired performance of emotional discrimination but not working memory (WM), while individuals with higher CAR exhibited better performance for both emotional and WM tasks. Neuronally, suppression of CAR led to a decrease in fractional occupancy and mean lifetime of task-related brain states dominant to emotional and WM processing. Further information-theoretic analyses on sequence complexity of state transitions revealed that a suppressed or lower CAR led to higher transition complexity among states primarily anchored in visual-sensory and salience networks during emotional task. Conversely, an opposite pattern of transition complexity was observed among states anchored in executive control and visuospatial networks during WM, indicating that CAR distinctly modulates neural resources allocated to emotional and WM processing. Our findings establish a causal link of CAR with brain network dynamics across emotional and executive functions, suggesting a neuroendocrine account for CAR proactive effects on human emotion and cognition.

Neural decoding and feature selection methods for closed-loop control of avoidance behavior

Objective.Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local field potentials (LFPs) could serve as the foundational technology for closed-loop control of such disorders. A significant challenge is identifying the LFP features that encode these defensive behaviors.Approach.We analyzed LFP signals from the infralimbic cortex and basolateral amygdala of rats undergoing tone-shock conditioning and extinction, standard for investigating defensive behaviors. We utilized a comprehensive set of neuro-markers across spectral, temporal, and connectivity domains, employing SHapley Additive exPlanations for feature importance evaluation within Light Gradient-Boosting Machine models. Our goal was to decode three commonly studied avoidance/defensive behaviors: freezing, bar-press suppression, and motion (accelerometry), examining the impact of different features on decoding performance.Main results.Band power and band power ratio between channels emerged as optimal features across sessions. High-gamma (80-150 Hz) power, power ratios, and inter-regional correlations were more informative than other bands that are more classically linked to defensive behaviors. Focusing on highly informative features enhanced performance. Across 4 recording sessions with 16 subjects, we achieved an average coefficient of determination of 0.5357 and 0.3476, and Pearson correlation coefficients of 0.7579 and 0.6092 for accelerometry jerk and bar press rate, respectively. Utilizing only the most informative features revealed differential encoding between accelerometry and bar press rate, with the former primarily through local spectral power and the latter via inter-regional connectivity. Our methodology demonstrated remarkably low training/inference time and memory usage, requiring<310 ms for training,<0.051 ms for inference, and 16.6 kB of memory, using a single core of AMD Ryzen Threadripper PRO 5995WX CPU.Significance.Our results demonstrate the feasibility of accurately decoding defensive behaviors with minimal latency, using LFP features from neural circuits strongly linked to these behaviors. This methodology holds promise for real-time decoding to identify physiological targets in closed-loop psychiatric neuromodulation.

EEG-based emotional valence and emotion regulation classification: a data-centric and explainable approach

Emotion classification using electroencephalographic (EEG) data is a challenging task in the field of Artificial Intelligence. While many researchers have focused on finding the best model or feature extraction technique to achieve optimal results, few have attempted to select the best methodological steps for working with the dataset. In this study, we applied two different theoretical approaches based on the noise of the dataset: curriculum learning and confident learning. Curriculum learning involves presenting training examples to the model in a specific order, starting with easier examples and gradually increasing in difficulty. This approach has been shown to improve model performance. Confident learning is a method for identifying and correcting label errors in datasets. By identifying and correcting these errors, confident learning can improve the performance of machine learning models trained on noisy datasets. We then applied the Integrated Gradient technique in order to assess the explainability of each model. Our aim was to explore the impact of different models and methods on emotion classification performance using EEG data. We collected and used an EEG dataset in which participants rated the emotional valence of positive and negative pictures while performing an emotion regulation (ER) task, comparing a control condition (Look) with two ER strategies: cognitive reappraisal and expressive suppression. We performed a multilabel classification to identify emotional neutrality or polarization of emotional valence (both positive and negative) rated by participants and the emotion regulation strategy adopted during the task. We compared the performance of models trained on three datasets selected based on label noise and evaluated their suitability for this task. Our results suggest different patterns based on the architecture used for feature importance, highlighting both advantages and criticisms.

Establishing connectivity through microdissections of midbrain stimulation-related neural circuits

Comprehensive understanding of the neural circuits involving the ventral tegmental area is essential for elucidating the anatomofunctional mechanisms governing human behaviour, in addition to the therapeutic and adverse effects of deep brain stimulation for neuropsychiatric diseases. Although the ventral tegmental area has been targeted successfully with deep brain stimulation for different neuropsychiatric diseases, the axonal connectivity of the region is not fully understood. Here, using fibre microdissections in human cadaveric hemispheres, population-based high-definition fibre tractography and previously reported deep brain stimulation hotspots, we find that the ventral tegmental area participates in an intricate network involving the serotonergic pontine nuclei, basal ganglia, limbic system, basal forebrain and prefrontal cortex, which is implicated in the treatment of obsessive-compulsive disorder, major depressive disorder, Alzheimer's disease, cluster headaches and aggressive behaviours.

Spectral-switching analysis reveals real-time neuronal network representations of concurrent spontaneous naturalistic behaviors in human brain

Despite abundant evidence of functional networks in the human brain, their neuronal underpinnings, and relationships to real-time behavior have been challenging to resolve. Analyzing brain-wide intracranial-EEG recordings with video monitoring, acquired in awake subjects during clinical epilepsy evaluation, we discovered the tendency of each brain region to switch back and forth between 2 distinct power spectral densities (PSDs 2-55Hz). We further recognized that this 'spectral switching' occurs synchronously between distant sites, even between regions with differing baseline PSDs, revealing long-range functional networks that would be obscured in analysis of individual frequency bands. Moreover, the real-time PSD-switching dynamics of specific networks exhibited striking alignment with activities such as conversation and hand movements, revealing a multi-threaded functional network representation of concurrent naturalistic behaviors. Network structures and their relationships to behaviors were stable across days, but were altered during N3 sleep. Our results provide a new framework for understanding real-time, brain-wide neural-network dynamics.

A Review of Motor Brain-Computer Interfaces Using Intracranial Electroencephalography Based on Surface Electrodes and Depth Electrodes

Brain-computer interfaces (BCIs) provide a communication interface between the brain and external devices and have the potential to restore communication and control in patients with neurological injury or disease. For the invasive BCIs, most studies recruited participants from hospitals requiring invasive device implantation. Three widely used clinical invasive devices that have the potential for BCIs applications include surface electrodes used in electrocorticography (ECoG) and depth electrodes used in Stereo-electroencephalography (SEEG) and deep brain stimulation (DBS). This review focused on BCIs research using surface (ECoG) and depth electrodes (including SEEG, and DBS electrodes) for movement decoding on human subjects. Unlike previous reviews, the findings presented here are from the perspective of the decoding target or task. In detail, five tasks will be considered, consisting of the kinematic decoding, kinetic decoding,identification of body parts, dexterous hand decoding, and motion intention decoding. The typical studies are surveyed and analyzed. The reviewed literature demonstrated a distributed motor-related network that spanned multiple brain regions. Comparison between surface and depth studies demonstrated that richer information can be obtained using surface electrodes. With regard to the decoding algorithms, deep learning exhibited superior performance using raw signals than traditional machine learning algorithms. Despite the promising achievement made by the open-loop BCIs, closed-loop BCIs with sensory feedback are still in their early stage, and the chronic implantation of both ECoG surface and depth electrodes has not been thoroughly evaluated.

Neural Decoding and Feature Selection Techniques for Closed-Loop Control of Defensive Behavior

Objective

Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local field potentials (LFPs) could serve as foundational technology for closed-loop control of such disorders. A significant challenge is identifying the LFP features that encode these defensive behaviors.

Approach

We analyzed LFP signals from the infralimbic cortex and basolateral amygdala of rats undergoing tone-shock conditioning and extinction, standard for investigating defensive behaviors. We utilized a comprehensive set of neuro-markers across spectral, temporal, and connectivity domains, employing SHapley Additive exPlanations for feature importance evaluation within Light Gradient-Boosting Machine models. Our goal was to decode three commonly studied avoidance/defensive behaviors: freezing, bar-press suppression, and motion (accelerometry), examining the impact of different features on decoding performance.

Main results

Band power and band power ratio between channels emerged as optimal features across sessions. High-gamma (80-150 Hz) power, power ratios, and inter-regional correlations were more informative than other bands that are more classically linked to defensive behaviors. Focusing on highly informative features enhanced performance. Across 4 recording sessions with 16 subjects, we achieved an average coefficient of determination of 0.5357 and 0.3476, and Pearson correlation coefficients of 0.7579 and 0.6092 for accelerometry jerk and bar press rate, respectively. Utilizing only the most informative features revealed differential encoding between accelerometry and bar press rate, with the former primarily through local spectral power and the latter via inter-regional connectivity. Our methodology demonstrated remarkably low time complexity, requiring <110 ms for training and <1 ms for inference.

Significance

Our results demonstrate the feasibility of accurately decoding defensive behaviors with minimal latency, using LFP features from neural circuits strongly linked to these behaviors. This methodology holds promise for real-time decoding to identify physiological targets in closed-loop psychiatric neuromodulation.

Consistent spectro-spatial features of human ECoG successfully decode naturalistic behavioral states

Objective

Understanding the neural correlates of naturalistic behavior is critical for extending and confirming the results obtained from trial-based experiments and designing generalizable brain-computer interfaces that can operate outside laboratory environments. In this study, we aimed to pinpoint consistent spectro-spatial features of neural activity in humans that can discriminate between naturalistic behavioral states.

Approach

We analyzed data from five participants using electrocorticography (ECoG) with broad spatial coverage. Spontaneous and naturalistic behaviors such as "Talking" and "Watching TV" were labeled from manually annotated videos. Linear discriminant analysis (LDA) was used to classify the two behavioral states. The parameters learned from the LDA were then used to determine whether the neural signatures driving classification performance are consistent across the participants.

Main results

Spectro-spatial feature values were consistently discriminative between the two labeled behavioral states across participants. Mainly, θ, α, and low and high γ in the postcentral gyrus, precentral gyrus, and temporal lobe showed significant classification performance and feature consistency across participants. Subject-specific performance exceeded 70%. Combining neural activity from multiple cortical regions generally does not improve decoding performance, suggesting that information regarding the behavioral state is non-additive as a function of the cortical region.

Significance

To the best of our knowledge, this is the first attempt to identify specific spectro-spatial neural correlates that consistently decode naturalistic and active behavioral states. The aim of this work is to serve as an initial starting point for developing brain-computer interfaces that can be generalized in a realistic setting and to further our understanding of the neural correlates of naturalistic behavior in humans.

Naturalistic acute pain states decoded from neural and facial dynamics

Pain is a complex experience that remains largely unexplored in naturalistic contexts, hindering our understanding of its neurobehavioral representation in ecologically valid settings. To address this, we employed a multimodal, data-driven approach integrating intracranial electroencephalography, pain self-reports, and facial expression quantification to characterize the neural and behavioral correlates of naturalistic acute pain in twelve epilepsy patients undergoing continuous monitoring with neural and audiovisual recordings. High self-reported pain states were associated with elevated blood pressure, increased pain medication use, and distinct facial muscle activations. Using machine learning, we successfully decoded individual participants' high versus low self-reported pain states from distributed neural activity patterns (mean AUC = 0.70), involving mesolimbic regions, striatum, and temporoparietal cortex. High self-reported pain states exhibited increased low-frequency activity in temporoparietal areas and decreased high-frequency activity in mesolimbic regions (hippocampus, cingulate, and orbitofrontal cortex) compared to low pain states. This neural pain representation remained stable for hours and was modulated by pain onset and relief. Objective facial expression changes also classified self-reported pain states, with results concordant with electrophysiological predictions. Importantly, we identified transient periods of momentary pain as a distinct naturalistic acute pain measure, which could be reliably differentiated from affect-neutral periods using intracranial and facial features, albeit with neural and facial patterns distinct from self-reported pain. These findings reveal reliable neurobehavioral markers of naturalistic acute pain across contexts and timescales, underscoring the potential for developing personalized pain interventions in real-world settings.

Neural evidence for attentional capture by salient distractors

Salient objects often capture our attention, serving as distractors and hindering our current goals. It remains unclear when and how salient distractors interact with our goals, and our knowledge on the neural mechanisms responsible for attentional capture is limited to a few brain regions recorded from non-human primates. Here we conducted a multivariate analysis on human intracranial signals covering most brain regions and successfully dissociated distractor-specific representations from target-arousal signals in the high-frequency (60-100 Hz) activity. We found that salient distractors were processed rapidly around 220 ms, while target-tuning attention was attenuated simultaneously, supporting initial capture by distractors. Notably, neuronal activity specific to the distractor representation was strongest in the superior and middle temporal gyrus, amygdala and anterior cingulate cortex, while there were smaller contributions from the parietal and frontal cortices. These results provide neural evidence for attentional capture by salient distractors engaging a much larger network than previously appreciated.

Neural response properties predict perceived contents and locations elicited by intracranial electrical stimulation of human auditory cortex

Intracranial electrical stimulation (iES) of auditory cortex can elicit sound experiences with a variety of perceived contents (hallucination or illusion) and locations (contralateral or bilateral side), independent of actual acoustic inputs. However, the neural mechanisms underlying this elicitation heterogeneity remain undiscovered. Here, we collected subjective reports following iES at 3062 intracranial sites in 28 patients (both sexes) and identified 113 auditory cortical sites with iES-elicited sound experiences. We then decomposed the sound-induced intracranial electroencephalogram (iEEG) signals recorded from all 113 sites into time-frequency features. We found that the iES-elicited perceived contents can be predicted by the early high-γ features extracted from sound-induced iEEG. In contrast, the perceived locations elicited by stimulating hallucination sites and illusion sites are determined by the late high-γ and long-lasting α features, respectively. Our study unveils the crucial neural signatures of iES-elicited sound experiences in human and presents a new strategy to hearing restoration for individuals suffering from deafness.

A week in the life of the human brain: stable states punctuated by chaotic transitions

Many important neurocognitive states, such as performing natural activities and fluctuations of arousal, shift over minutes-to-hours in the real-world. We harnessed 3-12 days of continuous multi-electrode intracranial recordings in twenty humans during natural behavior (socializing, using digital devices, sleeping, etc.) to study real-world neurodynamics. Applying deep learning with dynamical systems approaches revealed that brain networks formed consistent stable states that predicted behavior and physiology. Changes in behavior were associated with bursts of rapid neural fluctuations where brain networks chaotically explored many configurations before settling into new states. These trajectories traversed an hourglass-shaped structure anchored around a set of networks that slowly tracked levels of outward awareness related to wake-sleep stages, and a central attractor corresponding to default mode network activation. These findings indicate ways our brains use rapid, chaotic transitions that coalesce into neurocognitive states slowly fluctuating around a stabilizing central equilibrium to balance flexibility and stability during real-world behavior.

Prefrontal network engagement by deep brain stimulation in limbic hubs

Prefrontal circuits in the human brain play an important role in cognitive and affective processing. Neuromodulation therapies delivered to certain key hubs within these circuits are being used with increasing frequency to treat a host of neuropsychiatric disorders. However, the detailed neurophysiological effects of stimulation to these hubs are largely unknown. Here, we performed intracranial recordings across prefrontal networks while delivering electrical stimulation to two well-established white matter hubs involved in cognitive regulation and depression: the subcallosal cingulate (SCC) and ventral capsule/ventral striatum (VC/VS). We demonstrate a shared frontotemporal circuit consisting of the ventromedial prefrontal cortex, amygdala, and lateral orbitofrontal cortex where gamma oscillations are differentially modulated by stimulation target. Additionally, we found participant-specific responses to stimulation in the dorsal anterior cingulate cortex and demonstrate the capacity for further tuning of neural activity using current-steered stimulation. Our findings indicate a potential neurophysiological mechanism for the dissociable therapeutic effects seen across the SCC and VC/VS targets for psychiatric neuromodulation and our results lay the groundwork for personalized, network-guided neurostimulation therapy.

Aperiodic neural activity is a biomarker for depression severity

A reliable physiological biomarker for Major Depressive Disorder (MDD) is necessary to improve treatment success rates by shoring up variability in outcome measures. In this study, we establish a passive biomarker that tracks with changes in mood on the order of minutes to hours. We record from intracranial electrodes implanted deep in the brain - a surgical setting providing exquisite temporal and spatial sensitivity to detect this relationship in a difficult-to-measure brain area, the ventromedial prefrontal cortex (VMPFC). The aperiodic slope of the power spectral density captures the balance of activity across all frequency bands and is construed as a putative proxy for excitatory/inhibitory balance in the brain. This study demonstrates how shifts in aperiodic slope correlate with depression severity in a clinical trial of deep brain stimulation for treatment-resistant depression (TRD). The correlation between depression severity scores and aperiodic slope is significant in N=5 subjects, indicating that flatter (less negative) slopes correspond to reduced depression severity, especially in the ventromedial prefrontal cortex. This biomarker offers a new way to track patient response to MDD treatment, facilitating individualized therapies in both intracranial and non-invasive monitoring scenarios.

Decoding Depression Severity From Intracranial Neural Activity

BACKGROUND

Disorders of mood and cognition are prevalent, disabling, and notoriously difficult to treat. Fueling this challenge in treatment is a significant gap in our understanding of their neurophysiological basis.

METHODS

We recorded high-density neural activity from intracranial electrodes implanted in depression-relevant prefrontal cortical regions in 3 human subjects with severe depression. Neural recordings were labeled with depression severity scores across a wide dynamic range using an adaptive assessment that allowed sampling with a temporal frequency greater than that possible with typical rating scales. We modeled these data using regularized regression techniques with region selection to decode depression severity from the prefrontal recordings.

RESULTS

Across prefrontal regions, we found that reduced depression severity is associated with decreased low-frequency neural activity and increased high-frequency activity. When constraining our model to decode using a single region, spectral changes in the anterior cingulate cortex best predicted depression severity in all 3 subjects. Relaxing this constraint revealed unique, individual-specific sets of spatiospectral features predictive of symptom severity, reflecting the heterogeneous nature of depression.

CONCLUSIONS

The ability to decode depression severity from neural activity increases our fundamental understanding of how depression manifests in the human brain and provides a target neural signature for personalized neuromodulation therapies.

State-specific modulation of mood using intracranial electrical stimulation of the orbitofrontal cortex

BACKGROUND

Orbitofrontal cortex (OFC) is a promising target for intracranial electrical stimulation (iES) aimed at improving mood states. However, knowledge gaps remain regarding the underlying neural mechanisms of iES effects, such as the effect of the OFC target in comparison with other emotional network targets, the impact of brain state at the time of stimulation, and the neural response induced by iES at both local and network scales.

OBJECTIVE

Our study aims to address the neural mechanisms underlying the effects of iES in improving mood states.

METHODS

We conducted a study in 24 epilepsy patients who received iES through implanted electrodes in the emotional network and compared the effects of iES on multiple targets in the emotional network.

RESULTS

We found that only iES applied to the orbitofrontal cortex (OFC) led to mood improvement and changes in neural activity. We also observed that iES to the OFC suppressed the delta-theta power when the brain was in a low mood state. Moreover, the iES to the OFC decreased delta-theta power and increased gamma power at local regions within the emotional network, and enhanced the information flow through the frequency domain among regions within the emotional network.

CONCLUSIONS

These findings provide insight into the neural correlates of iES-induced mood improvement and support the potential of iES as a therapeutic intervention for mood disorders.

The potential of convolutional neural networks for identifying neural states based on electrophysiological signals: experiments on synthetic and real patient data

Processing incoming neural oscillatory signals in real-time and decoding from them relevant behavioral or pathological states is often required for adaptive Deep Brain Stimulation (aDBS) and other brain-computer interface (BCI) applications. Most current approaches rely on first extracting a set of predefined features, such as the power in canonical frequency bands or various time-domain features, and then training machine learning systems that use those predefined features as inputs and infer what the underlying brain state is at each given time point. However, whether this algorithmic approach is best suited to extract all available information contained within the neural waveforms remains an open question. Here, we aim to explore different algorithmic approaches in terms of their potential to yield improvements in decoding performance based on neural activity such as measured through local field potentials (LFPs) recordings or electroencephalography (EEG). In particular, we aim to explore the potential of end-to-end convolutional neural networks, and compare this approach with other machine learning methods that are based on extracting predefined feature sets. To this end, we implement and train a number of machine learning models, based either on manually constructed features or, in the case of deep learning-based models, on features directly learnt from the data. We benchmark these models on the task of identifying neural states using simulated data, which incorporates waveform features previously linked to physiological and pathological functions. We then assess the performance of these models in decoding movements based on local field potentials recorded from the motor thalamus of patients with essential tremor. Our findings, derived from both simulated and real patient data, suggest that end-to-end deep learning-based methods may surpass feature-based approaches, particularly when the relevant patterns within the waveform data are either unknown, difficult to quantify, or when there may be, from the point of view of the predefined feature extraction pipeline, unidentified features that could contribute to decoding performance. The methodologies proposed in this study might hold potential for application in adaptive deep brain stimulation (aDBS) and other brain-computer interface systems.

Predictive neuromodulation of cingulo-frontal neural dynamics in major depressive disorder using a brain-computer interface system: A simulation study

Introduction

Deep brain stimulation (DBS) is a promising therapy for treatment-resistant major depressive disorder (MDD). MDD involves the dysfunction of a brain network that can exhibit complex nonlinear neural dynamics in multiple frequency bands. However, current open-loop and responsive DBS methods cannot track the complex multiband neural dynamics in MDD, leading to imprecise regulation of symptoms, variable treatment effects among patients, and high battery power consumption.

Methods

Here, we develop a closed-loop brain-computer interface (BCI) system of predictive neuromodulation for treating MDD. We first use a biophysically plausible ventral anterior cingulate cortex (vACC)-dorsolateral prefrontal cortex (dlPFC) neural mass model of MDD to simulate nonlinear and multiband neural dynamics in response to DBS. We then use offline system identification to build a dynamic model that predicts the DBS effect on neural activity. We next use the offline identified model to design an online BCI system of predictive neuromodulation. The online BCI system consists of a dynamic brain state estimator and a model predictive controller. The brain state estimator estimates the MDD brain state from the history of neural activity and previously delivered DBS patterns. The predictive controller takes the estimated MDD brain state as the feedback signal and optimally adjusts DBS to regulate the MDD neural dynamics to therapeutic targets. We use the vACC-dlPFC neural mass model as a simulation testbed to test the BCI system and compare it with state-of-the-art open-loop and responsive DBS treatments of MDD.

Results

We demonstrate that our dynamic model accurately predicts nonlinear and multiband neural activity. Consequently, the predictive neuromodulation system accurately regulates the neural dynamics in MDD, resulting in significantly smaller control errors and lower DBS battery power consumption than open-loop and responsive DBS.

Discussion

Our results have implications for developing future precisely-tailored clinical closed-loop DBS treatments for MDD.