Automated classification of pain perception using high-density electroencephalography data

Neural response associated with the modulation of temporal summation of second pain by affective touch

Temporal summation of second pain (TSSP) is a phenomenon that has clinical relevance but insights into its functioning are limited. Lately, 'affective touch' (AT) has been shown to have pain relieving properties but only one study has investigated its effects on TSSP and the neural underpinnings of such interaction are unknown. In the present EEG study, thirty-six healthy participants went through three conditions where a TSSP protocol was applied in concomitance with no touch (NoT), discriminative touch (DT) and AT. A fourth no-pain no-touch condition acted as a baseline. Measures of attention during the four conditions and of pleasantness during the touch conditions were also recorded. Pain ratings were significantly lower only during the AT condition. The neural response during NoT, compared to the baseline, brought about a temporal decrease in power at delta and theta frequencies and a fronto-central increase mainly in the alpha rhythm. Adding AT to TSSP yielded, compared to NoT, a decrease in delta, theta and beta bands in midline regions at both central (Cz) and parietal (Pz) and also of gamma at Pz. Notably, DT was not associated with significant changes compared to pain alone (NoT), but a specific marked difference was found between AT and DT with the former showing a significant decrease in beta frequencies localized at Pz. While TSSP seems to be characterized by a modulation mostly of the lower frequencies, adding AT to TSSP brings a clear depression of all the major frequency bands. Additionally, the parietal beta reduction may be a biomarker of AT. Future studies can examine if such brain response can help finding a suitable intervention for TSSP-related chronic pain conditions. PERSPECTIVE: This study consolidates the idea that AT can lower pain in a TSSP paradigm and shows what are the brain (EEG) responses associated with both TSSP and TSSP modulation by AT. Given that TSSP is linked to central sensitization and that it can be used as an experimental model for chronic pain, our results pave the way for further studies into the neural mechanisms of AT-led analgesia, which can lead to future effective treatments.

Beta Oscillations in the Sensory Thalamus During Severe Facial Neuropathic Pain Using Novel Sensing Deep Brain Stimulation

OBJECTIVE

Advancements in deep brain stimulation (DBS) devices provide a unique opportunity to record local field potentials longitudinally to improve the efficacy of treatment for intractable facial pain. We aimed to identify potential electrophysiological biomarkers of pain in the ventral posteromedial nucleus (VPM) of the thalamus and periaqueductal gray (PAG) using a long-term sensing DBS system.

MATERIALS AND METHODS

We analyzed power spectra of ambulatory pain-related events from one patient implanted with a long-term sensing generator, representing different pain intensities (pain >7, pain >9) and pain qualities (no pain, burning, stabbing, and shocking pain). Power spectra were parametrized to separate oscillatory and aperiodic features and compared across the different pain states.

RESULTS

Overall, 96 events were marked during a 16-month follow-up. Parameterization of spectra revealed a total of 62 oscillatory peaks with most in the VPM (77.4%). The pain-free condition did not show any oscillations. In contrast, β peaks were observed in the VPM during all episodes (100%) associated with pain >9, 56% of episodes with pain >7, and 50% of burning pain events (center frequencies: 28.4 Hz, 17.8 Hz, and 20.7 Hz, respectively). Episodes of pain >9 indicated the highest relative β band power in the VPM and decreased aperiodic exponents (denoting the slope of the power spectra) in both the VPM and PAG.

CONCLUSIONS

For this patient, an increase in β band activity in the sensory thalamus was associated with severe facial pain, opening the possibility for closed-loop DBS in facial pain.

An approach to the detection of pain from autonomic and cortical correlates

OBJECTIVE

To assess the value of combining brain and autonomic measures to discriminate the subjective perception of pain from other sensory-cognitive activations.

METHODS

20 healthy individuals received 2 types of tonic painful stimulation delivered to the hand: electrical stimuli and immersion in 10 Celsius degree (°C) water, which were contrasted with non-painful immersion in 15 °C water, and stressful cognitive testing. High-density electroencephalography (EEG) and autonomic measures (pupillary, electrodermal and cardiovascular) were continuously recorded, and the accuracy of pain detection based on combinations of electrophysiological features was assessed using machine learning procedures.

RESULTS

Painful stimuli induced a significant decrease in contralateral EEG alpha power. Cardiac, electrodermal and pupillary reactivities occurred in both painful and stressful conditions. Classification models, trained on leave-one-out cross-validation folds, showed low accuracy (61-73%) of cortical and autonomic features taken independently, while their combination significantly improved accuracy to 93% in individual reports.

CONCLUSIONS

Changes in cortical oscillations reflecting somatosensory salience and autonomic changes reflecting arousal can be triggered by many activating signals other than pain; conversely, the simultaneous occurrence of somatosensory activation plus strong autonomic arousal has great probability of reflecting pain uniquely.

SIGNIFICANCE

Combining changes in cortical and autonomic reactivities appears critical to derive accurate indexes of acute pain perception.

Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns

This study aims to design a time-continuous pain level assessment system for temporomandibular joint therapy. Our objectives cover verifying literature suggestions on pain stimulus, protocols for collecting reference data, and continuous pain recognition models. We use two types of pain data acquired during 1) heat stimulation and 2) temporomandibular joint therapy. Thirty-six electrodermal activity (EDA) features are determined to build a binary classification model. The experimental dataset is used to train the initial model that produces pseudo-labels for weakly-labeled clinical data. In training the final long short-term memory (LSTM) model, we propose a novel multivariate loss involving, i.a., dynamometer data. Significant differences are found between EDA features extracted from experimental and clinical datasets in pain and no pain events. The classification model is validated at different stages of the model development. The final model classifies each four-second frame with a mean accuracy of 0.89 and an F1 score of 0.85. Our study introduces the dynamometer as a novel source of pain-feeling indications that meets the challenges given in the literature: data can be acquired in various procedures and from patients with limited abilities. The main contribution of the study is to design the first time-continuous and short-term pain assessment system for a clinical setting.

The Role of the Mu Opioid Receptors of the Medial Prefrontal Cortex in the Modulation of Analgesia Induced by Acute Restraint Stress in Male Mice

Mu opioid receptors (MORs) represent a vital mechanism related to the modulation of stress-induced analgesia (SIA). Previous studies have reported on the gamma-aminobutyric acid (GABA)ergic "disinhibition" mechanisms of MORs on the descending pain modulatory pathway of SIA induced in the midbrain. However, the role of the MORs expressed in the medial prefrontal cortex (mPFC), one of the main cortical areas participating in pain modulation, in SIA remains completely unknown. In this study, we investigated the contributions of MORs expressed on glutamatergic (MORGlut) and GABAergic (MORGABA) neurons of the medial prefrontal cortex (mPFC), as well as the functional role and activity of neurons projecting from the mPFC to the periaqueductal gray (PAG) region, in male mice. We achieved this through a combination of hot-plate tests, c-fos staining, and 1 h acute restraint stress exposure tests. The results showed that our acute restraint stress protocol produced mPFC MOR-dependent SIA effects. In particular, MORGABA was found to play a major role in modulating the effects of SIA, whereas MORGlut seemed to be unconnected to the process. We also found that mPFC-PAG projections were efficiently activated and played key roles in the effects of SIA, and their activation was mediated by MORGABA to a large extent. These results indicated that the activation of mPFC MORGABA due to restraint stress was able to activate mPFC-PAG projections in a potential "disinhibition" pathway that produced analgesic effects. These findings provide a potential theoretical basis for pain treatment or drug screening targeting the mPFC.

Development of a binary classifier model from extended facial codes toward video-based pain recognition in cancer patients

OBJECTIVES

The Automatic Pain Assessment (APA) relies on the exploitation of objective methods to evaluate the severity of pain and other pain-related characteristics. Facial expressions are the most investigated pain behavior features for APA. We constructed a binary classifier model for discriminating between the absence and presence of pain through video analysis.

METHODS

A brief interview lasting approximately two-minute was conducted with cancer patients, and video recordings were taken during the session. The Delaware Pain Database and UNBC-McMaster Shoulder Pain dataset were used for training. A set of 17 Action Units (AUs) was adopted. For each image, the OpenFace toolkit was used to extract the considered AUs. The collected data were grouped and split into train and test sets: 80 % of the data was used as a training set and the remaining 20 % as the validation set. For continuous estimation, the entire patient video with frame prediction values of 0 (no pain) or 1 (pain), was imported into an annotator (ELAN 6.4). The developed Neural Network classifier consists of two dense layers. The first layer contains 17 nodes associated with the facial AUs extracted by OpenFace for each image. The output layer is a classification label of "pain" (1) or "no pain" (0).

RESULTS

The classifier obtained an accuracy of ∼94 % after about 400 training epochs. The Area Under the ROC curve (AUROC) value was approximately 0.98.

CONCLUSIONS

This study demonstrated that the use of a binary classifier model developed from selected AUs can be an effective tool for evaluating cancer pain. The implementation of an APA classifier can be useful for detecting potential pain fluctuations. In the context of APA research, further investigations are necessary to refine the process and particularly to combine this data with multi-parameter analyses such as speech analysis, text analysis, and data obtained from physiological parameters.

Changes in alpha, theta, and gamma oscillations in distinct cortical areas are associated with altered acute pain responses in chronic low back pain patients

Introduction

Chronic pain negatively impacts a range of sensory and affective behaviors. Previous studies have shown that the presence of chronic pain not only causes hypersensitivity at the site of injury but may also be associated with pain-aversive experiences at anatomically unrelated sites. While animal studies have indicated that the cingulate and prefrontal cortices are involved in this generalized hyperalgesia, the mechanisms distinguishing increased sensitivity at the site of injury from a generalized site-nonspecific enhancement in the aversive response to nociceptive inputs are not well known.

Methods

We compared measured pain responses to peripheral mechanical stimuli applied to a site of chronic pain and at a pain-free site in participants suffering from chronic lower back pain (n = 15) versus pain-free control participants (n = 15) by analyzing behavioral and electroencephalographic (EEG) data.

Results

As expected, participants with chronic pain endorsed enhanced pain with mechanical stimuli in both back and hand. We further analyzed electroencephalographic (EEG) recordings during these evoked pain episodes. Brain oscillations in theta and alpha bands in the medial orbitofrontal cortex (mOFC) were associated with localized hypersensitivity, while increased gamma oscillations in the anterior cingulate cortex (ACC) and increased theta oscillations in the dorsolateral prefrontal cortex (dlPFC) were associated with generalized hyperalgesia.

Discussion

These findings indicate that chronic pain may disrupt multiple cortical circuits to impact nociceptive processing.

Effects of social presence on behavioral, neural, and physiological aspects of empathy for pain

In mediated interactions (e.g. video calls), less information is available about the other. To investigate how this affects our empathy for one another, we conducted an electroencephalogram study, in which 30 human participants observed 1 of 5 targets undergoing painful electric stimulation, once in a direct interaction and once in a live, video-mediated interaction. We found that observers were as accurate in judging others' pain and showed as much affective empathy via video as in a direct encounter. While mu suppression, a common neural marker of empathy, was not sensitive to others' pain, theta responses to others' pain as well as skin conductance coupling between participants were reduced in the video-mediated condition. We conclude that physical proximity with its rich social cues is important for nuanced physiological resonance with the other's experience. More studies are warranted to confirm these results and to understand their behavioral significance for remote social interactions.

Exploring Biosignals for Quantitative Pain Assessment in Cancer Patients: A Proof of Concept

Perception and expression of pain in cancer patients are influenced by distress levels, tumor type and progression, and the underlying pathophysiology of pain. Relying on traditional pain assessment tools can present limitations due to the highly subjective and multifaceted nature of the symptoms. In this scenario, objective pain assessment is an open research challenge. This work introduces a framework for automatic pain assessment. The proposed method is based on a wearable biosignal platform to extract quantitative indicators of the patient pain experience, evaluated through a self-assessment report. Two preliminary case studies focused on the simultaneous acquisition of electrocardiography (ECG), electrodermal activity (EDA), and accelerometer signals are illustrated and discussed. The results demonstrate the feasibility of the approach, highlighting the potential of EDA in capturing skin conductance responses (SCR) related to pain events in chronic cancer pain. A weak correlation (R = 0.2) is found between SCR parameters and the standard deviation of the interbeat interval series (SDRR), selected as the Heart Rate Variability index. A statistically significant (p < 0.001) increase in both EDA signal and SDRR is detected in movement with respect to rest conditions (assessed by means of the accelerometer signals) in the case of motion-associated cancer pain, thus reflecting the relationship between motor dynamics, which trigger painful responses, and the subsequent activation of the autonomous nervous system. With the objective of integrating parameters obtained from biosignals to establish pain signatures within different clinical scenarios, the proposed framework proves to be a promising research approach to define pain signatures in different clinical contexts.

PainVision-based evaluation of brain potentials: a novel approach for quantitative pain assessment

Introduction: The complex and multidimensional nature of pain poses a major challenge in clinical pain assessments. In this study, we aimed to evaluate a novel approach combining quantitative sensory testing (QST) with event-related potential measurements for assessment of experimental pain in healthy individuals. Methods: QST was performed with a commercial device (PainVision, PS-2100), and numeric rating scale (NRS) scores after exposure to different sensory stimuli were reported by the participants. Resting-state electroencephalography (EEG) was simultaneously performed to capture the cortical responses to peripheral stimulation. Results: Pain scores increased with the intensity of stimuli, with mean NRS scores of 2.7 ± 1.0 after mild stimuli and 5.6 ± 1.0 after moderate stimuli. A reproducible, significant P2-N2 complex was evoked by both mild and moderately painful stimuli, but not by non-painful stimuli. The latency of pain-related potentials was not significantly different between stimuli. The amplitudes of both P2 and N2 components significantly increased when intense nociception was applied, and the increments mainly originated from theta oscillations. Conclusion: The combination of QST with EEG was feasible for subjective and objective pain assessment. Distinct patterns of brain potentials were associated with the phenotype of the peripheral stimuli (e.g., noxious versus. innoxious, high versus. low pain intensity).

Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives

Although proper pain evaluation is mandatory for establishing the appropriate therapy, self-reported pain level assessment has several limitations. Data-driven artificial intelligence (AI) methods can be employed for research on automatic pain assessment (APA). The goal is the development of objective, standardized, and generalizable instruments useful for pain assessment in different clinical contexts. The purpose of this article is to discuss the state of the art of research and perspectives on APA applications in both research and clinical scenarios. Principles of AI functioning will be addressed. For narrative purposes, AI-based methods are grouped into behavioral-based approaches and neurophysiology-based pain detection methods. Since pain is generally accompanied by spontaneous facial behaviors, several approaches for APA are based on image classification and feature extraction. Language features through natural language strategies, body postures, and respiratory-derived elements are other investigated behavioral-based approaches. Neurophysiology-based pain detection is obtained through electroencephalography, electromyography, electrodermal activity, and other biosignals. Recent approaches involve multimode strategies by combining behaviors with neurophysiological findings. Concerning methods, early studies were conducted by machine learning algorithms such as support vector machine, decision tree, and random forest classifiers. More recently, artificial neural networks such as convolutional and recurrent neural network algorithms are implemented, even in combination. Collaboration programs involving clinicians and computer scientists must be aimed at structuring and processing robust datasets that can be used in various settings, from acute to different chronic pain conditions. Finally, it is crucial to apply the concepts of explainability and ethics when examining AI applications for pain research and management.

In search of a composite biomarker for chronic pain by way of EEG and machine learning: where do we currently stand?

Machine learning is becoming an increasingly common component of routine data analyses in clinical research. The past decade in pain research has witnessed great advances in human neuroimaging and machine learning. With each finding, the pain research community takes one step closer to uncovering fundamental mechanisms underlying chronic pain and at the same time proposing neurophysiological biomarkers. However, it remains challenging to fully understand chronic pain due to its multidimensional representations within the brain. By utilizing cost-effective and non-invasive imaging techniques such as electroencephalography (EEG) and analyzing the resulting data with advanced analytic methods, we have the opportunity to better understand and identify specific neural mechanisms associated with the processing and perception of chronic pain. This narrative literature review summarizes studies from the last decade describing the utility of EEG as a potential biomarker for chronic pain by synergizing clinical and computational perspectives.

A systematic review of neurophysiological sensing for the assessment of acute pain

Pain is a complex and personal experience that presents diverse measurement challenges. Different sensing technologies can be used as a surrogate measure of pain to overcome these challenges. The objective of this review is to summarise and synthesise the published literature to: (a) identify relevant non-invasive physiological sensing technologies that can be used for the assessment of human pain, (b) describe the analytical tools used in artificial intelligence (AI) to decode pain data collected from sensing technologies, and (c) describe the main implications in the application of these technologies. A literature search was conducted in July 2022 to query PubMed, Web of Sciences, and Scopus. Papers published between January 2013 and July 2022 are considered. Forty-eight studies are included in this literature review. Two main sensing technologies (neurological and physiological) are identified in the literature. The sensing technologies and their modality (unimodal or multimodal) are presented. The literature provided numerous examples of how different analytical tools in AI have been applied to decode pain. This review identifies different non-invasive sensing technologies, their analytical tools, and the implications for their use. There are significant opportunities to leverage multimodal sensing and deep learning to improve accuracy of pain monitoring systems. This review also identifies the need for analyses and datasets that explore the inclusion of neural and physiological information together. Finally, challenges and opportunities for designing better systems for pain assessment are also presented.

Gamma-band oscillations of pain and nociception: A systematic review and meta-analysis of human and rodent studies

Pain-induced gamma-band oscillations (GBOs) are one of the most promising biomarkers of the pain experience. Although GBOs reliably encode pain perception across different individuals and species, considerable heterogeneity could be observed in the characteristics and functions of GBOs. However, such heterogeneity of GBOs and its underlying sources have rarely been detailed previously. Here, we conducted a systematic review and meta-analysis to characterize the temporal, frequential, and spatial characteristics of GBOs and summarize the functional significance of distinct GBOs. We found that GBO heterogeneity was mainly related to pain types, with a higher frequency (∼66 Hz) GBOs at the sensorimotor cortex elicited by phasic pain and a lower frequency (∼55 Hz) GBOs at the prefrontal cortex associated with tonic and chronic pains. Positive correlations between GBO magnitudes and pain intensity were observed in healthy participants. Notably, the characteristics and functions of GBOs seemed to be phylogenetically conserved across humans and rodents. Altogether, we provided a comprehensive description of heterogeneous GBOs in pain and nociception, laying the foundation for clinical applications of GBOs.

External validation of binary machine learning models for pain intensity perception classification from EEG in healthy individuals

Discrimination of pain intensity using machine learning (ML) and electroencephalography (EEG) has significant potential for clinical applications, especially in scenarios where self-report is unsuitable. However, existing research is limited due to a lack of external validation (assessing performance using novel data). We aimed for the first external validation study for pain intensity classification with EEG. Pneumatic pressure stimuli were delivered to the fingernail bed at high and low pain intensities during two independent EEG experiments with healthy participants. Study one (n = 25) was utilised for training and cross-validation. Study two (n = 15) was used for external validation one (identical stimulation parameters to study one) and external validation two (new stimulation parameters). Time-frequency features of peri-stimulus EEG were computed on a single-trial basis for all electrodes. ML training and analysis were performed on a subset of features, identified through feature selection, which were distributed across scalp electrodes and included frontal, central, and parietal regions. Results demonstrated that ML models outperformed chance. The Random Forest (RF) achieved the greatest accuracies of 73.18, 68.32 and 60.42% for cross-validation, external validation one and two, respectively. Importantly, this research is the first to externally validate ML and EEG for the classification of intensity during experimental pain, demonstrating promising performance which generalises to novel samples and paradigms. These findings offer the most rigorous estimates of ML's clinical potential for pain classification.

Pain-related gamma band activity is dependent on the features of nociceptive stimuli: a comparison of laser and contact heat

Painful contact heat and laser stimulation offer an avenue to characterize nociceptive pathways involved in acute pain processing, by way of evoked potentials. Direct comparisons of radiant laser and contact heat are limited, particularly in context of examining time-frequency responses to stimulation. This is important in light of recent evidence to suggest that gamma band oscillations (GBOs) represent a functionally heterogeneous measure of pain. The purpose of the current study was to investigate differences in GBOs generated in response to laser and contact heat stimulation of the nondominant forearm. Following intensity matching to pain ratings, evoked electroencephalography (EEG) responses to laser and contact heat stimulation were examined in the time-frequency domain in the same participants (19 healthy adults) across two sessions. At ∼200 ms, both contact heat and laser stimulation resulted in significant, group-level event-related synchronization (ERS) in the low gamma band (i.e., 30-60 Hz) in central electrode locations (Cc, Cz, Ci). Laser stimulation also generated ERS in the 60-100 Hz range (i.e., high gamma), at ∼200 ms, while contact heat led to a significant period of desynchronization in the high gamma range between 400 and 600 ms. Both contact heat and laser GBOs were stronger on the central electrodes contralateral to the stimulated forearm, indicative of primary somatosensory cortex involvement. Based on our findings, and taken in conjunction with previous studies, laser and contact heat stimulation generate characteristically different responses in the brain, with only the former leading to high-frequency GBOs characteristic of painful stimuli.NEW & NOTEWORTHY Despite matching pain perception between noxious laser and contact heat stimuli, we report notable differences in gamma band oscillations (GBO), measured via electroencephalography. GBOs produced following contact heat more closely resembled that of nonnoxious stimuli, while GBOs following laser stimuli were in line with previous reports. Taken together, laser and contact heat stimulation generate characteristically different responses in the brain, with only the former leading to high-frequency GBOs characteristic of painful stimuli.

Electroencephalography functional connectivity-A biomarker for painful polyneuropathy

BACKGROUND AND PURPOSE

Advanced analysis of electroencephalography (EEG) data has become an essential tool in brain research. Based solely on resting state EEG signals, a data-driven, predictive and explanatory approach is presented to discriminate painful from non-painful diabetic polyneuropathy (DPN) patients.

METHODS

Three minutes long, 64 electrode resting-state recordings were obtained from 180 DPN patients. The analysis consisted of a mixture of traditional, explanatory and machine learning analyses. First, the 10 functional bivariate connections best differentiating between painful and non-painful patients in each EEG band were identified and the relevant receiver operating characteristic was calculated. Later, those connections were correlated with selected clinical parameters.

RESULTS

Predictive analysis indicated that theta and beta bands contain most of the information required for discrimination between painful and non-painful polyneuropathy patients, with area under the receiver operating characteristic curve values of 0.93 for theta and 0.89 for beta bands. Assessing statistical differences between the average magnitude of functional connectivity values and clinical pain parameters revealed that painful DPN patients had significantly higher cortical functional connectivity than non-painful ones (p = 0.008 for theta and p = 0.001 for alpha bands). Moreover, intra-band analysis of individual significant functional connections revealed a positive correlation with average reported pain in the previous 3 months in all frequency bands.

CONCLUSIONS

Resting state EEG functional connectivity can serve as a highly accurate biomarker for the presence or absence of pain in DPN patients. This highlights the importance of the brain, in addition to the peripheral lesions, in generating the clinical pain picture. This tool can probably be extended to other pain syndromes.

Resting-state electroencephalography (EEG) biomarkers of chronic neuropathic pain. A systematic review

Diagnosis and management of chronic neuropathic pain are challenging, leading to current efforts to characterize 'objective' biomarkers of pain using imaging or neurophysiological techniques, such as electroencephalography (EEG). A systematic literature review was conducted in PubMed-Medline and Web-of-Science until October 2021 to identify EEG biomarkers of chronic neuropathic pain in humans. The risk of bias was assessed by the Newcastle-Ottawa-Scale. Experimental, provoked, or chronic non-neuropathic pain studies were excluded. We identified 14 studies, in which resting-state EEG spectral analysis was compared between patients with pain related to a neurological disease and patients with the same disease but without pain or healthy controls. From these heterogeneous exploratory studies, some conclusions can be drawn, even if they must be weighted by the fact that confounding factors, such as medication and association with anxio-depressive disorders, are generally not taken into account. Overall, EEG signal power was increased in the θ band (4-7Hz) and possibly in the high-β band (20-30Hz), but decreased in the high-α-low-β band (10-20Hz) in the presence of ongoing neuropathic pain, while increased γ band oscillations were not evidenced, unlike in experimental pain. Consequently, the dominant peak frequency was decreased in the θ-α band and increased in the whole-β band in neuropathic pain patients. Disappointingly, pain intensity correlated with various EEG changes across studies, with no consistent trend. This review also discusses the location of regional pain-related EEG changes in the pain connectome, as the perspectives offered by advanced techniques of EEG signal analysis (source location, connectivity, or classification methods based on artificial intelligence). The biomarkers provided by resting-state EEG are of particular interest for optimizing the treatment of chronic neuropathic pain by neuromodulation techniques, such as transcranial alternating current stimulation or neurofeedback procedures.

Pain Identification in Electroencephalography Signal Using Fuzzy Inference System

Diagnosing pain mechanisms is one of main approaches to improve clinical treatments. Especially, detection of existence and/or level of pain could be vital when oral information is not present for instant for neonates, disabled persons, anesthetized patients and animals. Various researches have been performed to originate and classify the pain; however, consistent results are surprising. The aim of this study is to show a strict relation between electroencephalography (EEG) features and perceptual pain levels and to clarify the relation of classified signal to pain origin. Cortical regions on scalp are assigned based on an evolutional method for optimized alignment of electrodes that improve the clinical monitoring results. The EEG signals are recorded during relax condition and variety of pain conditions. Evolutionary optimization method is used to reduce the features space dimension and computational costs. A hybrid adaptive network fuzzy inference system (ANFIS) and support vector machine (SVM) scheme is used for classification of pain levels. ANFIS optimizer is used to fine tune the non-linear alignment of kernels of SVM. The results show that pain levels could be differentiated with high accuracy and robustness even for few recording electrodes. The proposed classification method provides up to 95% accuracy.

Clinical use of Electroencephalography in the Assessment of Acute Thermal Pain: A Narrative Review Based on Articles From 2009 to 2019

Nowadays, no practical system has successfully been able to decode and predict pain in clinical settings. The inability of some patients to verbally express their pain creates the need for a tool that could objectively assess pain in these individuals. Neuroimaging techniques combined with machine learning are seen as possible candidates for the identification of pain biomarkers. This review aimed to address the potential use of electroencephalographic features as predictors of acute experimental pain. Twenty-six studies using only thermal stimulations were identified using a PubMed and Scopus search. Combinations of the following terms were used: "EEG," "Electroencephalography," "Acute," "Pain," "Tonic," "Noxious," "Thermal," "Stimulation," "Brain," "Activity," "Cold," "Subjective," and "Perception." Results revealed that contact-heat-evoked potentials have been widely recorded over central areas during noxious heat stimulations. Furthermore, a decrease in alpha power over central regions was revealed, as well as increased theta and gamma powers over frontal areas. Gamma and theta rhythms were associated with connectivity between sensory and affective regions involved in pain processing. A machine learning analysis revealed that the gamma band is a predominant predictor of acute thermal pain. This review also addressed the need of supplementing current spectral features with techniques that allow the investigation of network dynamics.

Scalp EEG-based Pain Detection using Convolutional Neural Network

Pain is an integrative phenomenon coupled with dynamic interactions between sensory and contextual processes in the brain, often associated with detectable neurophysiological changes. Recent advances in brain activity recording tools and machine learning technologies have intrigued research and development of neurocomputing techniques for objective and neurophysiology-based pain detection. This paper proposes a pain detection framework based on Electroencephalogram (EEG) and deep convolutional neural networks (CNN). The feasibility of CNN is investigated for distinguishing induced pain state from resting state in the recruitment of 10 chronic back pain patients. The experimental study recorded EEG signals in two phases: 1. movement stimulation (MS), where induces back pain by executing predefined movement tasks; 2. video stimulation (VS), where induces back pain perception by watching a set of video clips. A multi-layer CNN classifies the EEG segments during the resting state and the pain state. The novel approach offers high and robust performance and hence is significant in building a powerful pain detection algorithm. The area under the receiver operating characteristic curve (AUC) of our approach is 0.83±0.09 and 0.81±0.15, in MS and VS, respectively, higher than the state-of-the-art approaches. The sub-brain-areas are also analyzed, to examine distinct brain topographies relevant for pain detection. The results indicate that MS-induced pain tends to evoke a generalized brain area, while the evoked area is relatively partial under VS-induced pain. This work may provide a new solution for researchers and clinical practitioners on pain detection.

Distinct spatio-temporal and spectral brain patterns for different thermal stimuli perception

Understanding the human brain's perception of different thermal sensations has sparked the interest of many neuroscientists. The identification of distinct brain patterns when processing thermal stimuli has several clinical applications, such as phantom-limb pain prediction, as well as increasing the sense of embodiment when interacting with neurorehabilitation devices. Notwithstanding the remarkable number of studies that have touched upon this research topic, understanding how the human brain processes different thermal stimuli has remained elusive. More importantly, very intense thermal stimuli perception dynamics, their related cortical activations, as well as their decoding using effective features are still not fully understood. In this study, using electroencephalography (EEG) recorded from three healthy human subjects, we identified spatial, temporal, and spectral patterns of brain responses to different thermal stimulations ranging from extremely cold and hot stimuli (very intense), moderately cold and hot stimuli (intense), to a warm stimulus (innocuous). Our results show that very intense thermal stimuli elicit a decrease in alpha power compared to intense and innocuous stimulations. Spatio-temporal analysis reveals that in the first 400 ms post-stimulus, brain activity increases in the prefrontal and central brain areas for very intense stimulations, whereas for intense stimulation, high activity of the parietal area was observed post-500 ms. Based on these identified EEG patterns, we successfully classified the different thermal stimulations with an average test accuracy of 84% across all subjects. En route to understanding the underlying cortical activity, we source localized the EEG signal for each of the five thermal stimuli conditions. Our findings reveal that very intense stimuli were anticipated and induced early activation (before 400 ms) of the anterior cingulate cortex (ACC). Moreover, activation of the pre-frontal cortex, somatosensory, central, and parietal areas, was observed in the first 400 ms post-stimulation for very intense conditions and starting 500 ms post-stimuli for intense conditions. Overall, despite the small sample size, this work presents novel findings and a first comprehensive approach to explore, analyze, and classify EEG-brain activity changes evoked by five different thermal stimuli, which could lead to a better understanding of thermal stimuli processing in the brain and could, therefore, pave the way for developing a real-time withdrawal reaction system when interacting with prosthetic limbs. We underpin this last point by benchmarking our EEG results with a demonstration of a real-time withdrawal reaction of a robotic prosthesis using a human-like artificial skin.

Learning Spatial-Spectral-Temporal EEG Representations with Deep Attentive-Recurrent-Convolutional Neural Networks for Pain Intensity Assessment

Electroencephalogram (EEG)-based quantitative pain measurement is valuable in the field of clinical pain treatment, providing objective pain intensity assessment especially for nonverbal patients who are unable to self-report. At present, a key challenge in modeling pain events from EEG is to find invariant representations for intra- and inter-subject variations, where current methods based on hand-crafted features cannot provide satisfactory results. Hence, we propose a novel method based on deep learning to learn such invariant representations from multi-channel EEG signals and demonstrate its great advantages in EEG-based pain classification tasks. To begin, instead of using typical EEG analysis techniques that ignore spatial information of EEG, we convert raw EEG signals into a sequence of multi-spectral topography maps (topology-preserving EEG images). Next, inspired by various deep learning techniques applied in neuroimaging domain, a deep Attentive-Recurrent-Convolutional Neural Network (ARCNN) is proposed here to learn spatial-spectral-temporal representations from EEG images. The proposed method aims to jointly preserve the spatial-spectral-temporal structures of EEG, for learning representations with high robustness against intra-subject and inter-subject variations, making it more conducive to multi-class and subject-independent scenarios. Empirical evaluation on 4-level pain intensity assessment within the subject-independent scenario demonstrated significant improvement over baseline and state-of-the-art methods in this field. Our approach applies deep neural networks (DNNs) to pain intensity assessment for the first time and demonstrates its potential advantages in modeling pain events from EEG.

Premature Infants Display Discriminable Behavioral, Physiological, and Brain Responses to Noxious and Nonnoxious Stimuli

Pain assessment in preterm infants is challenging as behavioral, autonomic, and neurophysiological measures of pain are reported to be less sensitive and specific than in term infants. Understanding the pattern of preterm infants’ noxious-evoked responses is vital to improve pain assessment in this group. This study investigated the discriminability and development of multimodal noxious-evoked responses in infants aged 28–40 weeks postmenstrual age. A classifier was trained to discriminate responses to a noxious heel lance from a nonnoxious control in 47 infants, using measures of facial expression, brain activity, heart rate, and limb withdrawal, and tested in two independent cohorts with a total of 97 infants. The model discriminates responses to the noxious from the nonnoxious procedure with an overall accuracy of 0.76–0.84 and an accuracy of 0.78–0.79 in the 28–31-week group. Noxious-evoked responses have distinct developmental patterns. Heart rate responses increase in magnitude with age, while noxious-evoked brain activity undergoes three distinct developmental stages, including a previously unreported transitory stage consisting of a negative event-related potential between 30 and 33 weeks postmenstrual age. These findings demonstrate that while noxious-evoked responses change across early development, infant responses to noxious and nonnoxious stimuli are discriminable in prematurity.

Decoding pain from brain activity

Pain is a dynamic, complex and multidimensional experience. The identification of pain from brain activity as neural readout may effectively provide a neural code for pain, and further provide useful information for pain diagnosis and treatment. Advances in neuroimaging and large-scale electrophysiology have enabled us to examine neural activity with improved spatial and temporal resolution, providing opportunities to decode pain in humans and freely behaving animals. This topical review provides a systematical overview of state-of-the-art methods for decoding pain from brain signals, with special emphasis on electrophysiological and neuroimaging modalities. We show how pain decoding analyses can help pain diagnosis and discovery of neurobiomarkers for chronic pain. Finally, we discuss the challenges in the research field and point to several important future research directions.

Systematic Review of the Effectiveness of Machine Learning Algorithms for Classifying Pain Intensity, Phenotype or Treatment Outcomes Using Electroencephalogram Data

Recent attempts to utilize machine learning (ML) to predict pain-related outcomes from Electroencephalogram (EEG) data demonstrate promising results. The primary aim of this review was to evaluate the effectiveness of ML algorithms for predicting pain intensity, phenotypes or treatment response from EEG. Electronic databases MEDLINE, EMBASE, Web of Science, PsycINFO and The Cochrane Library were searched. A total of 44 eligible studies were identified, with 22 presenting attempts to predict pain intensity, 15 investigating the prediction of pain phenotypes and seven assessing the prediction of treatment response. A meta-analysis was not considered appropriate for this review due to heterogenos methods and reporting. Consequently, data were narratively synthesized. The results demonstrate that the best performing model of the individual studies allows for the prediction of pain intensity, phenotypes and treatment response with accuracies ranging between 62 to 100%, 57 to 99% and 65 to 95.24%, respectively. The results suggest that ML has the potential to effectively predict pain outcomes, which may eventually be used to assist clinical care. However, inadequate reporting and potential bias reduce confidence in the results. Future research should improve reporting standards and externally validate models to decrease bias, which would increase the feasibility of clinical translation. PERSPECTIVE: This systematic review explores the state-of-the-art machine learning methods for predicting pain intensity, phenotype or treatmentresponse from EEG data. Results suggest that machine learning may demonstrate clinical utility, pending further research and development. Areas for improvement, including standardized processing, reporting and the need for better methodological assessment tools, are discussed.

Neurophysiological aspects of isotonic exercises in temporomandibular joint dysfunction syndrome

PURPOSE

The aim of the study was to investigate the electroneurophysiological aspects of volunteers with temporomandibular disorders before and after performing isotonic exercises for pain relief and self-care guidelines.

METHODS

The study was a parallel controlled randomized controlled trial under protocol 1,680,920. The inclusion criteria were age between 18 and 60 years, muscle temporomandibular dysfunction with or without limitation of mouth opening and self-reported pain with scores between 4 and 10. The individuals were randomized into experimental group and control. Twenty-three volunteers participated in the study, most of then were female. Control group had 11 and experimental group 12 individuals. Dropouts occurred in both groups, two in the experimental group and three in the control group. Since there were an intergroup imbalance the power density was analysed just in experimental group. Electroencephalographic recording was performed before and after the interventions, using the 32-channel apparatus, with sample frequency of 600 Hz and impedance of 5 kΩ. The data were processed through the MATLAB computer program. The individual records filtered off-line, using bandpass between 0.5 and 50 Hz. Epochs of 1,710 ms were created and the calculation of the absolute power density calculated by means of the fast Fourier transform. The statistical approach was inferential and quantitative.

RESULTS

The alpha power density analyzed presented a difference, but not significant, when compared in the two moments.

CONCLUSION

According to this study, isotonic exercises performed to reduce pain provided a small increase in alpha power density in the left temporal, parietal and occipital regions.

Elevated and Slowed EEG Oscillations in Patients with Post-Concussive Syndrome and Chronic Pain Following a Motor Vehicle Collision

(1) Background: Mild traumatic brain injury produces significant changes in neurotransmission including brain oscillations. We investigated potential quantitative electroencephalography biomarkers in 57 patients with post-concussive syndrome and chronic pain following motor vehicle collision, and 54 healthy nearly age- and sex-matched controls. (2) Methods: Electroencephalography processing was completed in MATLAB, statistical modeling in SPSS, and machine learning modeling in Rapid Miner. Group differences were calculated using current-source density estimation, yielding whole-brain topographical distributions of absolute power, relative power and phase-locking functional connectivity. Groups were compared using independent sample Mann–Whitney U tests. Effect sizes and Pearson correlations were also computed. Machine learning analysis leveraged a post hoc supervised learning support vector non-probabilistic binary linear kernel classification to generate predictive models from the derived EEG signatures. (3) Results: Patients displayed significantly elevated and slowed power compared to controls: delta (p = 0.000000, r = 0.6) and theta power (p < 0.0001, r = 0.4), and relative delta power (p < 0.00001) and decreased relative alpha power (p < 0.001). Absolute delta and theta power together yielded the strongest machine learning classification accuracy (87.6%). Changes in absolute power were moderately correlated with duration and persistence of symptoms in the slow wave frequency spectrum (<15 Hz). (4) Conclusions: Distributed increases in slow wave oscillatory power are concurrent with post-concussive syndrome and chronic pain.

The Prediction of Acute Postoperative Pain Based on Neural Oscillations Measured before the Surgery

Even with an improved understanding of pain mechanisms and advances in perioperative pain management, inadequately controlled postoperative pain remains. Predicting acute postoperative pain based on presurgery physiological measures could provide valuable insights into individualized, effective analgesic strategies, thus helping improve the analgesic efficacy. Considering the strong correlation between pain perception and neural oscillations, we hypothesize that acute postoperative pain could be predicted by neural oscillations measured shortly before the surgery. Here, we explored the relationship between neural oscillations 2 hours before the thoracoscopic surgery and the subjective intensity of acute postoperative pain. The spectral power density of resting-state beta and gamma band oscillations at the frontocentral region was significantly different between patients with different levels of acute postoperative pain (i.e., low pain vs. moderate/high pain). A positive correlation was also observed between the spectral power density of resting-state beta and gamma band oscillations and subjective reports of postoperative pain. Then, we predicted the level of acute postoperative pain based on features of neural oscillations using machine learning techniques, which achieved a prediction accuracy of 92.54% and a correlation coefficient between the real pain intensities and the predicted pain intensities of 0.84. Altogether, the prediction of acute postoperative pain based on neural oscillations measured before the surgery is feasible and could meet the clinical needs in the future for better control of postoperative pain and other unwanted negative effects. The study was registered on the Clinical Trial Registry (https://clinicaltrials.gov/ct2/show/NCT03761576?term=NCT03761576&draw=2&rank=1) with the registration number NCT03761576.

EEG changes reflecting pain: is alpha suppression better than gamma enhancement?

OBJECTIVE

Suppression of alpha and enhancement of gamma electroencephalographic (EEG) power have both been suggested as objective indicators of cortical pain processing. While gamma activity has been emphasized as the best potential marker, its spectral overlap with pain-related muscular responses is a potential drawback. Since muscle contractions are almost universal concomitants of physical pain, here we investigated alpha and gamma scalp-recorded activities during either tonic pain or voluntary facial grimaces mimicking those triggered by pain.

METHODS

High-density EEG (128 electrodes) was recorded while 14 healthy participants either underwent a cold pressor test (painful hand immersion in 10 °C water) or produced stereotyped facial/nuchal contractions (grimaces) mimicking those evoked by pain. The scalp distribution of spectral EEG changes was quantified via vector-transformation of maps and compared between the pain and grimacing conditions by calculating the cosine of the angle between the two corresponding topographies.

RESULTS

Painful stimuli significantly enhanced gamma power bilaterally in fronto-temporal regions and decreased alpha power in the contralateral central scalp. Sustained cervico-facial contractions (grimaces) gave also rise to significant gamma power increase in fronto-temporal regions but did not decrease central scalp alpha. While changes in alpha topography significantly differed between the pain and grimace situations, the scalp topography of gamma power was statistically indistinguishable from that occurring during grimaces.

CONCLUSION

Gamma power induced by painful stimuli or voluntary facial-cervical muscle contractions had overlapping topography. Pain-related alpha decrease in contralateral central scalp was less disturbed by muscle activity and may therefore prove more discriminant as an ancillary pain biomarker.

Chronic jaw pain attenuates neural oscillations during motor-evoked pain

Motor- and pain-related processes separately induce a reduction in alpha and beta power. When movement and pain occur simultaneously but are independent of each other, the effects on alpha and beta power are additive. It is not clear whether this additive effect is evident during motor-evoked pain in individuals with chronic pain. We combined highdensity electroencephalography (EEG) with a paradigm in which motor-evoked pain was induced during a jaw force task. Participants with chronic jaw pain and pain-free controls produced jaw force at 2% and 15% of their maximum voluntary contraction. The chronic jaw pain group showed exacerbated motor-evoked pain as force amplitude increased and showed increased motor variability and motor error irrespective of force amplitude. The chronic jaw pain group had an attenuated decrease in power in alpha and lower-beta frequencies in the occipital cortex during the anticipation and experience of motor-evoked pain. Rather than being additive, motor-evoked pain attenuated the modulation of alpha and beta power, and this was most evident in occipital cortex. Our findings provide the first evidence of changes in neural oscillations in the cortex during motor-evoked jaw pain.

A Novel Method to Understand Neural Oscillations During Full-Body Reaching: A Combined EEG and 3D Virtual Reality Study

Virtual reality (VR) can be used to create environments that are not possible in the real-world. Producing movements in VR holds enormous promise for rehabilitation and offers a platform from which to understand the neural control of movement. However, no study has examined the impact of a 3D fully immersive head-mounted display (HMD) VR system on the integrity of neural data. We assessed the quality of 64-channel EEG data with and without HMD VR during rest and during a full-body reaching task. We compared resting EEG while subjects completed three conditions: No HMD (EEG-only), HMD powered off (VR-off), and HMD powered on (VR-on). Within the same session, EEG were collected while subjects completed full-body reaching movements in two conditions (EEG-only, VR-on). During rest, no significant differences in data quality and power spectrum were observed between EEG-only, VR-off, and VR-on conditions. During reaching movements, the proportion of components attributed to the brain was greater in the EEG-only condition compared to the VR-on condition. Despite this difference, neural oscillations in source space were not significantly different between conditions, with both conditions associated with decreases in alpha and beta power in sensorimotor cortex during movements. Our findings demonstrate that the integrity of EEG data can be maintained while individuals execute full-body reaching movements within an immersive 3D VR environment. Clinical impact: Integrating VR and EEG is a viable approach to understanding the cortical processes of movement. Simultaneously recording movement and brain activity in combination with VR provides the foundation for neurobiologically informed rehabilitation therapies.

Metabolite activity in the anterior cingulate cortex during a painful stimulus using functional MRS

To understand neurochemical brain responses to pain, proton magnetic resonance spectroscopy (1H-MRS) is used in humans in vivo to examine various metabolites. Recent MRS investigations have adopted a functional approach, where acquisitions of MRS are performed over time to track task-related changes. Previous studies suggest glutamate is of primary interest, as it may play a role during cortical processing of noxious stimuli. The objective of this study was to examine the metabolic effect (i.e., glutamate) in the anterior cingulate cortex during noxious stimulation using fMRS. The analysis addressed changes in glutamate and glutamate + glutamine (Glx) associated with the onset of pain, and the degree by which fluctuations in metabolites corresponded with continuous pain outcomes. Results suggest healthy participants undergoing tonic noxious stimulation demonstrated increased concentrations of glutamate and Glx at the onset of pain. Subsequent reports of pain were not accompanied by corresponding changes in glutamate of Glx concentrations. An exploratory analysis on sex revealed large effect size changes in glutamate at pain onset in female participants, compared with medium-sized effects in male participants. We propose a role for glutamate in the ACC related to the detection of a noxious stimulus.

Differentiation of pain levels by deploying various EEG synchronization features and dynamic ensemble selection mechanism

OBJECTIVE

The target of this study is measuring the pain intensity in an objective manner by analysing the electroencephalogram (EEG) signals. Although this problem has attracted researchers' attention, increasing the resolution of this measurement, by increasing the number of pain states, significantly decreases the accuracy of pain level classification problem.

APPROACH

To overcome this drawback, we adopt state-of-the-art synchronization schemes to measure the linear, nonlinear and generalized synchronization between different EEG channels. 32 subjects executed the Cold Pressor Task (CPT) and experienced five defined levels of pain while recording their EEGs. Due to high number of synchronization features from 34 channels, the most discriminative features were selected using greedy overall relevancy (GOR) method. The selected features are applied to a dynamic ensemble selection system.

MAIN RESULTS

Our experiment provides 85.6% accuracy over the five classes, which significantly outperforms the results of past research. Moreover, we observe that the selected features belong to the channels placed over the ridge of cortex, the area responsible for processing somatic sensation arisen from nociceptive temperature. As expected, we noted that continuing the painful stimulus for minutes engaged regions beyond the sensorimotor cortex, e.g., the prefrontal cortex.

SIGNIFICANCE

We conclude that the amount of synchronization between scalp EEG channels is an informative tool in revealing the pain sensation.

Cortical dynamics of movement-evoked pain in chronic low back pain

KEY POINTS

Cortical activity underlying movement-evoked pain is not well understood, despite being a key symptom of chronic musculoskeletal pain. We combined high-density electroencephalography with a full-body reaching protocol in a virtual reality environment to assess cortical activity during movement-evoked pain in chronic low back pain. Movement-evoked pain in individuals with chronic low back pain was associated with longer reaction times, delayed peak velocity and greater movement variability. Movement-evoked pain was associated with attenuated disinhibition in prefrontal motor areas, as evidenced by an attenuated reduction in beta power in the premotor cortex and supplementary motor area.

ABSTRACT

Although experimental pain alters neural activity in the cortex, evidence of changes in neural activity in individuals with chronic low back pain (cLBP) remains scarce and results are inconsistent. One of the challenges in studying cLBP is that the clinical pain fluctuates over time and often changes during movement. The goal of the present study was to address this challenge by recording high-density electroencephalography (HD-EEG) data during a full-body reaching task to understand neural activity during movement-evoked pain. HD-EEG data were analysed using independent component analyses, source localization and measure projection analyses to compare neural oscillations between individuals with cLBP who experienced movement-evoked pain and pain-free controls. We report two novel findings. First, movement-evoked pain in individuals with cLBP was associated with longer reaction times, delayed peak velocity and greater movement variability. Second, movement-evoked pain was associated with an attenuated reduction in beta power in the premotor cortex and supplementary motor area. Our observations move the field forward by revealing attenuated disinhibition in prefrontal motor areas during movement-evoked pain in cLBP.

Neural Oscillations: Understanding a Neural Code of Pain

Neural oscillations play an important role in the integration and segregation of brain regions that are important for brain functions, including pain. Disturbances in oscillatory activity are associated with several disease states, including chronic pain. Studies of neural oscillations related to pain have identified several functional bands, especially alpha, beta, and gamma bands, implicated in nociceptive processing. In this review, we introduce several properties of neural oscillations that are important to understand the role of brain oscillations in nociceptive processing. We also discuss the role of neural oscillations in the maintenance of efficient communication in the brain. Finally, we discuss the role of neural oscillations in healthy and chronic pain nociceptive processing. These data and concepts illustrate the key role of regional and interregional neural oscillations in nociceptive processing underlying acute and chronic pains.

Pain phenotypes classified by machine learning using electroencephalography features

Pain is a multidimensional experience mediated by distributed neural networks in the brain. To study this phenomenon, EEGs were collected from 20 subjects with chronic lumbar radiculopathy, 20 age and gender matched healthy subjects, and 17 subjects with chronic lumbar pain scheduled to receive an implanted spinal cord stimulator. Analysis of power spectral density, coherence, and phase-amplitude coupling using conventional statistics showed that there were no significant differences between the radiculopathy and control groups after correcting for multiple comparisons. However, analysis of transient spectral events showed that there were differences between these two groups in terms of the number, power, and frequency-span of events in a low gamma band. Finally, we trained a binary support vector machine to classify radiculopathy versus healthy subjects, as well as a 3-way classifier for subjects in the 3 groups. Both classifiers performed significantly better than chance, indicating that EEG features contain relevant information pertaining to sensory states, and may be used to help distinguish between pain states when other clinical signs are inconclusive.

A perinatal stress calculator for the neonatal intensive care unit: an unobtrusive approach

OBJECTIVE

Early experience of pain and stress in the neonatal intensive care unit is known to have an effect on the neurodevelopment of the infant. However, an automated method to quantify the procedural pain or perinatal stress in premature patients does not exist.

APPROACH

In the current study, EEG and ECG data were collected for more than 3 hours from 136 patients in order to quantify stress exposure. Specifically, features extracted from the EEG and heart-rate variability in both quiet and non-quiet sleep segments were used to develop a subspace linear-discriminant analysis stress classifier.

MAIN RESULTS

The main novelty of the study lies in the absence of intrusive methods or pain elicitation protocols to develop the stress classifier. Three main findings can be reported. First, we developed different stress classifiers for the different age groups and stress intensities, obtaining an area under the curve in the range [0.78-0.93] for non-quiet sleep and [0.77-0.96] for quiet sleep. Second, a dysmature EEG was found in patients under stress. Third, an enhanced cortical connectivity and increased brain-heart communication was correlated with a higher stress load, while the autonomic activity did not seem to be associated to stress exposure.

SIGNIFICANCE

The results shed a light on the pain and stress processing in preterm neonates, suggesting that software tools to investigate dysmature EEG might be helpful to assess stress load in premature patients. These results could be the foundation to assess the impact of stress on infants' development and to tune preventive care.

Recognizing Pain in Motor Imagery EEG Recordings Using Dynamic Functional Connectivity Graphs

The goal of this paper is to investigate whether motor imagery tasks, performed under pain-free versus pain conditions, can be discriminated from electroencephalography (EEG) recordings. Four motor imagery classes of right hand, left hand, foot, and tongue are considered. A functional connectivity-based feature extraction approach along with a long short-term memory (LSTM) classifier are employed for classifying pain-free versus under-pain classes. Moreover, classification is performed in different frequency bands to study the significance of each band in differentiating motor imagery data associated with pain-free and under-pain states. When considering all frequency bands, the average classification accuracy is in the range of 77:86-80:04%. Our frequency-specific analysis shows that the gamma band results in a notably higher accuracy than other bands, indicating the importance of this band in discriminating pain/no-pain conditions during the execution of motor imagery tasks. In contrast, functional connectivity graphs extracted from delta and theta bands do not seem to provide discriminatory information between pain-free and under-pain conditions. This is the first study demonstrating that motor imagery tasks executed under pain and without pain conditions can be discriminated from EEG recordings. Our findings can provide new insights for developing effective brain computer interface-based assistive technologies for patients who are in real need of them.

A Bradycardia-Based Stress Calculator for the Neonatal Intensive Care Unit: A Multisystem Approach

Early life stress in the neonatal intensive care unit (NICU) can predispose premature infants to adverse health outcomes and neurodevelopment delays. Hands-on-care and procedural pain might induce apneas, hypoxic events, and sleep-wake disturbances, which can ultimately impact maturation, but a data-driven method based on physiological fingerprints to quantify early-life stress does not exist. This study aims to provide an automatic stress detector by investigating the relationship between bradycardias, hypoxic events and perinatal stress in NICU patients. EEG, ECG, and SpO 2 were recorded from 136 patients for at least 3 h in three different monitoring groups. In these subjects, the stress burden was assessed using the Leuven Pain Scale. Different subspace linear discriminant analysis models were designed to detect the presence or the absence of stress based on information in each bradycardic spell. The classification shows an area under the curve in the range [0.80-0.96] and a kappa score in the range [0.41-0.80]. The results suggest that stress seems to increase SpO 2 desaturations and EEG regularity as well as the interaction between the cardiovascular and neurological system. It might be possible that stress load enhances the reaction to respiratory abnormalities, which could ultimately impact the neurological and behavioral development.

Classification of Pain Event Related Potential for Evaluation of Pain Perception Induced by Electrical Stimulation

Variability in individual pain sensitivity is a major problem in pain assessment. There have been studies reported using pain-event related potential (pain-ERP) for evaluating pain perception. However, none of them has achieved high accuracy in estimating multiple pain perception levels. A major reason lies in the lack of investigation of feature extraction. The goal of this study is to assess four different pain perception levels through classification of pain-ERP, elicited by transcutaneous electrical stimulation on healthy subjects. Nonlinear methods: Higuchi's fractal dimension, Grassberger-Procaccia correlation dimension, with auto-correlation, and moving variance functions were introduced into the feature extraction. Fisher score was used to select the most discriminative channels and features. As a result, the correlation dimension with a moving variance without channel selection achieved the best accuracies of 100% for both the two-level and the three-level classification but degraded to 75% for the four-level classification. The best combined feature group is the variance-based one, which achieved accuracy of 87.5% and 100% for the four-level and three-level classification, respectively. Moreover, the features extracted from less than 20 trials could not achieve sensible accuracy, which makes it difficult for an instantaneous pain perception levels evaluation. These results show strong evidence on the possibility of objective pain assessment using nonlinear feature-based classification of pain-ERP.

EEG alpha activity increased in response to transcutaneous electrical nervous stimulation in young healthy subjects but not in the healthy elderly

Transcutaneous Electrical Nerve Stimulation (TENS) is used not only in the treatment of pain but also in the examination of sensory functions. With aging, there is decreased sensitivity to somatosensory stimuli. It is essential to examine the effect of TENS application on the sensory functions in the brain by recording the spontaneous electroencephalogram (EEG) activity and the effect of aging on the sensory functions of the brain during the application. The present study aimed to investigate the effect of the application of TENS on the brain’s electrical activity and the effect of aging on the sensory functions of the brain during application of TENS. A total of 15 young (24.2 ± 3.59) and 14 elderly (65.64 ± 4.92) subjects were included in the study. Spontaneous EEG was recorded from 32 channels during TENS application. Power spectrum analysis was performed by Fast Fourier Transform in the alpha frequency band (8–13 Hz) for all subjects. Repeated measures of analysis of variance was used for statistical analysis (p < 0.05). Young subjects had increased alpha power during the TENS application and had gradually increased alpha power by increasing the current intensity of TENS (p = 0.035). Young subjects had higher alpha power than elderly subjects in the occipital and parietal locations (p = 0.073). We can, therefore, conclude that TENS indicated increased alpha activity in young subjects. Young subjects had higher alpha activity than elderly subjects in the occipital and somatosensory areas. To our knowledge, the present study is one of the first studies examining the effect of TENS on spontaneous EEG in healthy subjects. Based on the results of the present study, TENS may be used as an objective method for the examination of sensory impairments, and in the evaluative efficiency of the treatment of pain conditions.

Nociception and the neonatal brain

Measuring brain activity in infants provides an objective surrogate approach with which to infer pain perception following noxious events. Here we discuss different approaches which can be used to measure noxious-evoked brain activity, and discuss how these measures can be used to assess the analgesic efficacy of pharmacological and non-pharmacological interventions. We review factors that can modulate noxious-evoked brain activity, which may impact infant pain experience, including gestational age, sex, prior pain, stress, and illness.

Altered neural oscillations within and between sensorimotor cortex and parietal cortex in chronic jaw pain

Pain perception is associated with priming of the motor system and the orienting of attention in healthy adults. These processes correspond with decreases in alpha and beta power in the sensorimotor and parietal cortices. The goal of the present study was to determine whether these findings extend to individuals with chronic pain. Individuals with chronic jaw pain and pain-free controls anticipated and experienced a low pain or a moderate pain-eliciting heat stimulus. Although stimuli were calibrated for each subject, stimulus temperature was not different between groups. High-density EEG data were collected during the anticipation and heat stimulation periods and were analyzed using independent component analyses, EEG source localization, and measure projection analyses. Direct directed transfer function was also estimated to identify frequency specific effective connectivity between regions. Between group differences were most evident during the heat stimulation period. We report three novel findings. First, the chronic jaw pain group had a relative increase in alpha and beta power and a relative decrease in theta and gamma power in sensorimotor cortex. Second, the chronic jaw pain group had a relative increase in power in the alpha and beta bands in parietal cortex. Third, the chronic jaw pain group had less connectivity strength in the beta and gamma bands between sensorimotor cortex and parietal cortex. Our findings show that the effect of chronic pain attenuates rather than magnifies neural responses to heat stimuli. We interpret these findings in the context of system-level changes in intrinsic sensorimotor and attentional circuits in chronic pain.

Neuroimaging-based biomarkers for pain: state of the field and current directions

Chronic pain is an endemic problem involving both peripheral and brain pathophysiology. Although biomarkers have revolutionized many areas of medicine, biomarkers for pain have remained controversial and relatively underdeveloped. With the realization that biomarkers can reveal pain-causing mechanisms of disease in brain circuits and in the periphery, this situation is poised to change. In particular, brain pathophysiology may be diagnosable with human brain imaging, particularly when imaging is combined with machine learning techniques designed to identify predictive measures embedded in complex data sets. In this review, we explicate the need for brain-based biomarkers for pain, some of their potential uses, and some of the most popular machine learning approaches that have been brought to bear. Then, we evaluate the current state of pain biomarkers developed with several commonly used methods, including structural magnetic resonance imaging, functional magnetic resonance imaging and electroencephalography. The field is in the early stages of biomarker development, but these complementary methodologies have already produced some encouraging predictive models that must be tested more extensively across laboratories and clinical populations.

The Functional Role of Response Suppression during an Urge to Relieve Pain

Being in the state of having both a strong impulse to act and a simultaneous need to withhold is commonly described as an "urge." Although urges are part of everyday life and also important to several clinical disorders, the components of urge are poorly understood. It has been conjectured that withholding an action during urge involves active response suppression. We tested that idea by designing an urge paradigm that required participants to resist an impulse to press a button and gain relief from heat (one hand was poised to press while the other arm had heat stimulation). We first used paired-pulse TMS over motor cortex (M1) to measure corticospinal excitability of the hand that could press for relief, while participants withheld movement. We observed increased short-interval intracortical inhibition, an index of M1 GABAergic interneuron activity that was maintained across seconds and specific to the task-relevant finger. A second experiment replicated this. We next used EEG to better "image" putative cortical signatures of motor suppression and pain. We found increased sensorimotor beta contralateral to the task-relevant hand while participants withheld the movement during heat. We interpret this as further evidence of a motor suppressive process. Additionally, there was beta desynchronization contralateral to the arm with heat, which could reflect a pain signature. Strikingly, participants who "suppressed" more exhibited less of a putative "pain" response. We speculate that, during urge, a suppressive state may have functional relevance for both resisting a prohibited action and for mitigating discomfort.