Diverse frequency band-based convolutional neural networks for tonic cold pain assessment using EEG

Decoding Pain: A Comprehensive Review of Computational Intelligence Methods in Electroencephalography-Based Brain-Computer Interfaces

Objective pain evaluation is crucial for determining appropriate treatment strategies in clinical settings. Studies have demonstrated the potential of using brain-computer interface (BCI) technology for pain classification and detection. Collating knowledge and insights from prior studies, this review explores the extensive work on pain detection based on electroencephalography (EEG) signals. It presents the findings, methodologies, and advancements reported in 20 peer-reviewed articles that utilize machine learning and deep learning (DL) approaches for EEG-based pain detection. We analyze various ML and DL techniques, support vector machines, random forests, k-nearest neighbors, and convolution neural network recurrent neural networks and transformers, and their effectiveness in decoding pain neural signals. The motivation for combining AI with BCI technology lies in the potential for significant advancements in the real-time responsiveness and adaptability of these systems. We reveal that DL techniques effectively analyze EEG signals and recognize pain-related patterns. Moreover, we discuss advancements and challenges associated with EEG-based pain detection, focusing on BCI applications in clinical settings and functional requirements for effective pain classification systems. By evaluating the current research landscape, we identify gaps and opportunities for future research to provide valuable insights for researchers and practitioners.

A Review on Deep Learning for Quality of Life Assessment Through the Use of Wearable Data

Quality of Life (QoL) assessment has evolved over time, encompassing diverse aspects of human existence beyond just health. This paper presents a comprehensive review of the integration of Deep Learning (DL) techniques in QoL assessment, focusing on the analysis of wearable data. QoL, as defined by the World Health Organisation, encompasses physical, mental, and social well-being, making it a multifaceted concept. Traditional QoL assessment methods, often reliant on subjective reports or informal questioning, face challenges in quantification and standardization. To address these challenges, DL, a branch of machine learning inspired by the human brain, has emerged as a promising tool. DL models can analyze vast and complex datasets, including patient-reported outcomes, medical images, and physiological signals, enabling a deeper understanding of factors influencing an individual's QoL. Notably, wearable sensory devices have gained prominence, offering real-time data on vital signs and enabling remote healthcare monitoring. This review critically examines DL's role in QoL assessment through the use of wearable data, with particular emphasis on the subdomains of physical and psychological well-being. By synthesizing current research and identifying knowledge gaps, this review provides valuable insights for researchers, clinicians, and policymakers aiming to enhance QoL assessment with DL. Ultimately, the paper contributes to the adoption of advanced technologies to improve the well-being and QoL of individuals from diverse backgrounds.

Decoding of pain during heel lancing in human neonates with EEG signal and machine learning approach

Currently, pain assessment using electroencephalogram signals and machine learning methods in clinical studies is of great importance, especially for those who cannot express their pain. Since newborns are among the high-risk group and always experience pain at the beginning of birth, in this research, the severity of newborns has been investigated and evaluated. Other studies related to the annoyance of newborns have used the EEG signal of newborns alone; therefore, in this study, the intensity of newborn pain was measured using the electroencephalogram signal of 107 infants who were stimulated by the heel lance in three levels: no pain, low pain and moderate pain were recorded as a single trial and evaluated. The support vector machine (SVM), K-Nearest Neighbors (KNN) and Ensemble bagging classifiers were trained using the K-fold cross-validation method and features of the brain's time-frequency domain. The results were obtained with accuracies of 72.8 ± 2, 84.4 ± 1.3 and 82.9 ± 1.6%, respectively. Also, in examining the problem of distinguishing pain and no pain, the electroencephalogram signal of 74 infants was evaluated, and similar to the three-class mode, with the 10-fold validation method, we reached the highest accuracy of 100% in Bagging classifier and 98.6 ± 0.1 accuracy in KNN and SVM classifiers.

FBANet: An Effective Data Mining Method for Food Olfactory EEG Recognition

At present, the sensory evaluation of food mostly depends on artificial sensory evaluation and machine perception, but artificial sensory evaluation is greatly interfered with by subjective factors, and machine perception is difficult to reflect human feelings. In this article, a frequency band attention network (FBANet) for olfactory electroencephalogram (EEG) was proposed to distinguish the difference in food odor. First, the olfactory EEG evoked experiment was designed to collect the olfactory EEG, and the preprocessing of olfactory EEG, such as frequency division, was completed. Second, the FBANet consisted of frequency band feature mining and frequency band feature self-attention, in which frequency band feature mining can effectively mine multiband features of olfactory EEG with different scales, and frequency band feature self-attention can integrate the extracted multiband features and realize classification. Finally, compared with other advanced models, the performance of the FBANet was evaluated. The results show that FBANet was better than the state-of-the-art techniques. In conclusion, FBANet effectively mined the olfactory EEG data information and distinguished the differences between the eight food odors, which proposed a new idea for food sensory evaluation based on multiband olfactory EEG analysis.

A Spatiotemporal Deep Learning Framework for Scalp EEG-Based Automated Pain Assessment in Children

OBJECTIVE

Common pain assessment approaches such as self-evaluation and observation scales are inappropriate for children as they require patients to have reasonable communication ability. Subjective, inconsistent, and discontinuous pain assessment in children may reduce therapeutic effectiveness and thus affect their later life.

METHODS

To address the need for suitable assessment measures, this paper proposes a spatiotemporal deep learning framework for scalp electroencephalogram (EEG)-based automated pain assessment in children. The dataset comprises scalp EEG data recorded from 33 pediatric patients with an arterial puncture as a pain stimulus. Two electrode reduction plans in line with clinical findings are proposed. Combining three-dimensional hand-crafted features and preprocessed raw signals, the proposed transformer-based pain assessment network (STPA-Net) integrates both spatial and temporal information.

RESULTS

STPA-Net achieves superior performance with a subject-independent accuracy of 87.83% for pain recognition, and outperforms other state-of-the-art approaches. The effectiveness of electrode combinations is explored to analyze pain-related cortical activities and correspondingly reduce cost. The two proposed electrode reduction plans both demonstrate competitive pain assessment performance qualitatively and quantitatively.

CONCLUSION AND SIGNIFICANCE

This study is the first to develop a scalp EEG-based automated pain assessment for children adopting a method that is objective, standardized, and consistent. The findings provide a potential reference for future clinical research.

Validation of Cross-Individual Pain Assessment with Individual Recognition Model from Electroencephalogram

Cross-individual pain assessment models based on electroencephalography (EEG) allow pain assessment in individuals who cannot report pain (e.g., unresponsive patients). The main obstacle to the generalisation of pain assessment models is the individual variation of brain responses to pain. Hence, we took the individual variation into account in cross-individual model development. We developed two convolutional neural networks (CNN) sharing an encoder architecture. One CNN predicts pain, while the other predicts the identity of an individual. We performed a leave-one-out (LOO) test with the exclusion of each subject and applied evidence accumulation to it for validating the pain prediction model's performance, where the binary classifier involves the states of pain (Hot) and resting state (Eyes-open). The mean accuracy produced by the LOO tests was 57.81% (max: 73.33%), and the mean accuracy of evidence accumulation achieved 69.75% (max: 100.00%). The individual recognition model achieved an accuracy of 99.63%. Nevertheless, when we acquired the most similar subject to a novel subject using the individual recognition model, where the most similar subject was used to train a subject-wise pain prediction model. The accuracy of predicting the pain-related conditions of the novel subject by the subject-wise model was only 53.73% (max: 79.50%). Therefore, the approach to utilising the features related to individual variation extracted by the CNN model needs more investigation for improving cross-individual pain assessment.Clinical relevance- This model can be applied to assess pain from EEG signals at the bedside with future improvement, which can help caretakers of unresponsive patients.

Automatic assessment of pain based on deep learning methods: A systematic review

BACKGROUND AND OBJECTIVE

The automatic assessment of pain is vital in designing optimal pain management interventions focused on reducing suffering and preventing the functional decline of patients. In recent years, there has been a surge in the adoption of deep learning algorithms by researchers attempting to encode the multidimensional nature of pain into meaningful features. This systematic review aims to discuss the models, the methods, and the types of data employed in establishing the foundation of a deep learning-based automatic pain assessment system.

METHODS

The systematic review was conducted by identifying original studies searching digital libraries, namely Scopus, IEEE Xplore, and ACM Digital Library. Inclusion and exclusion criteria were applied to retrieve and select those of interest, published until December 2021.

RESULTS

A total of one hundred and ten publications were identified and categorized by the number of information channels used (unimodal versus multimodal approaches) and whether the temporal dimension was also used.

CONCLUSIONS

This review demonstrates the importance of multimodal approaches for automatic pain estimation, especially in clinical settings, and also reveals that significant improvements are observed when the temporal exploitation of modalities is included. It provides suggestions regarding better-performing deep architectures and learning methods. Also, it provides suggestions for adopting robust evaluation protocols and interpretation methods to provide objective and comprehensible results. Furthermore, the review presents the limitations of the available pain databases for optimally supporting deep learning model development, validation, and application as decision-support tools in real-life scenarios.

Personalized Deep Bi-LSTM RNN Based Model for Pain Intensity Classification Using EDA Signal

Automatic pain intensity assessment from physiological signals has become an appealing approach, but it remains a largely unexplored research topic. Most studies have used machine learning approaches built on carefully designed features based on the domain knowledge available in the literature on the time series of physiological signals. However, a deep learning framework can automate the feature engineering step, enabling the model to directly deal with the raw input signals for real-time pain monitoring. We investigated a personalized Bidirectional Long short-term memory Recurrent Neural Networks (BiLSTM RNN), and an ensemble of BiLSTM RNN and Extreme Gradient Boosting Decision Trees (XGB) for four-category pain intensity classification. We recorded Electrodermal Activity (EDA) signals from 29 subjects during the cold pressor test. We decomposed EDA signals into tonic and phasic components and augmented them to original signals. The BiLSTM-XGB model outperformed the BiLSTM classification performance and achieved an average F1-score of 0.81 and an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.93 over four pain states: no pain, low pain, medium pain, and high pain. We also explored a concatenation of the deep-learning feature representations and a set of fourteen knowledge-based features extracted from EDA signals. The XGB model trained on this fused feature set showed better performance than when it was trained on component feature sets individually. This study showed that deep learning could let us go beyond expert knowledge and benefit from the generated deep representations of physiological signals for pain assessment.

Classification of Tonic Pain Experience based on Phase Connectivity in the Alpha Frequency Band of the Electroencephalogram using Convolutional Neural Networks

The complexity of brain activity involved in the generation of the experience of pain makes it hard to identify neural markers able to predict pain states. The within and between subjects variability of pain hinders the predictive potential of machine learning models trained across participants. This challenge can be tackled by implementing deep learning classifiers based on convolutional neural networks (CNNs). We targeted phase-based connectivity in the alpha band recorded with electroencephalography (EEG) during resting states and sensory conditions (eyes open [O] and closed [C] as resting states, and warm [W] and hot [H] water as sensory conditions). Connectivity features were extracted and re-organized as square matrices, because CNNs are effective in detecting the patterns from 2D data. To assess the classifier performance we implemented two complementary approaches: we 1) trained and tested the classifier with data from all participants, and 2) using a leave-one-out approach, that is excluding one participant at a time during training while using their data as a test set. The accuracy of binary classification between pain condition (H) and eyes open resting state (O) was 94.16% with the first approach, and 61.01 % with the leave-one-out approach. Clinical relevance-Further validation of the CNN classifier may help caregivers track the rehabilitation of chronic pain patients and dynamically modify the therapy. Further refinement of the model may allow its application in critical care setting with unresponsive patients to identify pain-like states otherwise incommunicable to medical personnel.

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.

Experimental Exploration of Objective Human Pain Assessment Using Multimodal Sensing Signals

Optimization of pain assessment and treatment is an active area of research in healthcare. The purpose of this research is to create an objective pain intensity estimation system based on multimodal sensing signals through experimental studies. Twenty eight healthy subjects were recruited at Northeastern University. Nine physiological modalities were utilized in this research, namely facial expressions (FE), electroencephalography (EEG), eye movement (EM), skin conductance (SC), and blood volume pulse (BVP), electromyography (EMG), respiration rate (RR), skin temperature (ST), blood pressure (BP). Statistical analysis and machine learning algorithms were deployed to analyze the physiological data. FE, EEG, SC, BVP, and BP proved to be able to detect different pain states from healthy subjects. Multi-modalities proved to be promising in detecting different levels of painful states. A decision-level multi-modal fusion also proved to be efficient and accurate in classifying painful states.

A Personalized Spatial-Temporal Cold Pain Intensity Estimation Model Based on Facial Expression

OBJECTIVE

Pain assessment is of great importance in both clinical research and patient care. Facial expression analysis is becoming a key part of pain detection because it is convenient, automatic, and real-time. The aim of this study is to present a cold pain intensity estimation experiment, investigate the importance of the spatial-temporal information on facial expression based cold pain, and study the performance of the personalized model as well as the generalized model.

METHODS

A cold pain experiment was carried out and facial expressions from 29 subjects were extracted. Three different architectures (Inception V3, VGG-LSTM, and Convolutional LSTM) were used to estimate three intensities of cold pain: No pain, Moderate pain, and Severe Pain. Architectures with Sequential information were compared with single-frame architecture, showing the importance of spatial-temporal information on pain estimation. The performances of the personalized model and the generalized model were also compared.

RESULTS

A mean F1 score of 79.48% was achieved using Convolutional LSTM based on the personalized model.

CONCLUSION

This study demonstrates the potential for the estimation of cold pain intensity from facial expression analysis and shows that the personalized spatial-temporal framework has better performance in cold pain intensity estimation.

SIGNIFICANCE

This cold pain intensity estimator could allow convenient, automatic, and real-time use to provide continuous objective pain intensity estimations of subjects and patients.

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.

Exploration of physiological sensors, features, and machine learning models for pain intensity estimation

In current clinical settings, typically pain is measured by a patient’s self-reported information. This subjective pain assessment results in suboptimal treatment plans, over-prescription of opioids, and drug-seeking behavior among patients. In the present study, we explored automatic objective pain intensity estimation machine learning models using inputs from physiological sensors. This study uses BioVid Heat Pain Dataset. We extracted features from Electrodermal Activity (EDA), Electrocardiogram (ECG), Electromyogram (EMG) signals collected from study participants subjected to heat pain. We built different machine learning models, including Linear Regression, Support Vector Regression (SVR), Neural Networks and Extreme Gradient Boosting for continuous value pain intensity estimation. Then we identified the physiological sensor, feature set and machine learning model that give the best predictive performance. We found that EDA is the most information-rich sensor for continuous pain intensity prediction. A set of only 3 features from EDA signals using SVR model gave an average performance of 0.93 mean absolute error (MAE) and 1.16 root means square error (RMSE) for the subject-independent model and of 0.92 MAE and 1.13 RMSE for subject-dependent. The MAE achieved with signal-feature-model combination is less than 1 unit on 0 to 4 continues pain scale, which is smaller than the MAE achieved by the methods reported in the literature. These results demonstrate that it is possible to estimate pain intensity of a patient using a computationally inexpensive machine learning model with 3 statistical features from EDA signal which can be collected from a wrist biosensor. This method paves a way to developing a wearable pain measurement device.

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.

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.

Sensor Technologies to Manage the Physiological Traits of Chronic Pain: A Review

Non-oncologic chronic pain is a common high-morbidity impairment worldwide and acknowledged as a condition with significant incidence on quality of life. Pain intensity is largely perceived as a subjective experience, what makes challenging its objective measurement. However, the physiological traces of pain make possible its correlation with vital signs, such as heart rate variability, skin conductance, electromyogram, etc., or health performance metrics derived from daily activity monitoring or facial expressions, which can be acquired with diverse sensor technologies and multisensory approaches. As the assessment and management of pain are essential issues for a wide range of clinical disorders and treatments, this paper reviews different sensor-based approaches applied to the objective evaluation of non-oncological chronic pain. The space of available technologies and resources aimed at pain assessment represent a diversified set of alternatives that can be exploited to address the multidimensional nature of pain.