Feature Extraction and Selection for Pain Recognition Using Peripheral Physiological Signals

Flexible circumferential bioelectronics to enable 360-degree recording and stimulation of the spinal cord

The spinal cord is crucial for transmitting motor and sensory information between the brain and peripheral systems. Spinal cord injuries can lead to severe consequences, including paralysis and autonomic dysfunction. We introduce thin-film, flexible electronics for circumferential interfacing with the spinal cord. This method enables simultaneous recording and stimulation of dorsal, lateral, and ventral tracts with a single device. Our findings include successful motor and sensory signal capture and elicitation in anesthetized rats, a proof-of-concept closed-loop system for bridging complete spinal cord injuries, and device safety verification in freely moving rodents. Moreover, we demonstrate potential for human application through a cadaver model. This method sees a clear route to the clinic by using materials and surgical practices that mitigate risk during implantation and preserve cord integrity.

Transformer encoder with multiscale deep learning for pain classification using physiological signals

Pain, a pervasive global health concern, affects a large segment of population worldwide. Accurate pain assessment remains a challenge due to the limitations of conventional self-report scales, which often yield inconsistent results and are susceptible to bias. Recognizing this gap, our study introduces PainAttnNet, a novel deep-learning model designed for precise pain intensity classification using physiological signals. We investigate whether PainAttnNet would outperform existing models in capturing temporal dependencies. The model integrates multiscale convolutional networks, squeeze-and-excitation residual networks, and a transformer encoder block. This integration is pivotal for extracting robust features across multiple time windows, emphasizing feature interdependencies, and enhancing temporal dependency analysis. Evaluation of PainAttnNet on the BioVid heat pain dataset confirm the model's superior performance over the existing models. The results establish PainAttnNet as a promising tool for automating and refining pain assessments. Our research not only introduces a novel computational approach but also sets the stage for more individualized and accurate pain assessment and management in the future.

Monitoring Neuromuscular Activity during Exercise: A New Approach to Assessing Attentional Focus Based on a Multitasking and Multiclassification Network and an EMG Fitness Shirt

Strengthening muscles can reduce body fat, increase lean muscle mass, maintain independence while aging, manage chronic conditions, and improve balance, reducing the risk of falling. The most critical factor inducing effectiveness in strength training is neuromuscular connection by adopting attentional focus during training. However, this is troublesome for end users since numerous fitness tracking devices or applications do not provide the ability to track the effectiveness of users' workout at the neuromuscular level. A practical approach for detecting attentional focus by assessing neuromuscular activity through biosignals has not been adequately evaluated. The challenging task to make the idea work in a real-world scenario is to minimize the cost and size of the clinical device and use a recognition system for muscle contraction to ensure a good user experience. We then introduce a multitasking and multiclassification network and an EMG shirt attached with noninvasive sensing electrodes that firmly fit to the body's surface, measuring neuron muscle activity during exercise. Our study exposes subjects to standard free-weight exercises focusing on isolated and compound muscle on the upper limb. The results of the experiment show a 94.79% average precision at different maximum forces of attentional focus conditions. Furthermore, the proposed system can perform at different lifting weights of 67% and 85% of a person's 1RM to recognize individual exercise effectiveness at the muscular level, proving that adopting attentional focus with low-intensity exercise can activate more upper-limb muscle contraction.

Preliminary study: quantification of chronic pain from physiological data

Supplemental Digital Content is Available in the Text.

Preliminary evidence suggests that physiological variables collected with our low-cost pain meter are correlated with chronic pain, both for individuals and populations.

Introduction:

It is unknown if physiological changes associated with chronic pain could be measured with inexpensive physiological sensors. Recently, acute pain and laboratory-induced pain have been quantified with physiological sensors.

Objectives:

To investigate the extent to which chronic pain can be quantified with physiological sensors.

Methods:

Data were collected from chronic pain sufferers who subjectively rated their pain on a 0 to 10 visual analogue scale, using our recently developed pain meter. Physiological variables, including pulse, temperature, and motion signals, were measured at head, neck, wrist, and finger with multiple sensors. To quantify pain, features were first extracted from 10-second windows. Linear models with recursive feature elimination were fit for each subject. A random forest regression model was used for pain score prediction for the population-level model.

Results:

Predictive performance was assessed using leave-one-recording-out cross-validation and nonparametric permutation testing. For individual-level models, 5 of 12 subjects yielded intraclass correlation coefficients between actual and predicted pain scores of 0.46 to 0.75. For the population-level model, the random forest method yielded an intraclass correlation coefficient of 0.58. Bland–Altman analysis shows that our model tends to overestimate the lower end of the pain scores and underestimate the higher end.

Conclusion:

This is the first demonstration that physiological data can be correlated with chronic pain, both for individuals and populations. Further research and more extensive data will be required to assess whether this approach could be used as a “chronic pain meter” to assess the level of chronic pain in patients.

A Systematic Review of Time Series Classification Techniques Used in Biomedical Applications

Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, and ingestible and implantable sensors are increasingly used by individuals and clinicians to capture the health outcomes or behavioral and physiological characteristics of individuals. Time series classification (TSC) is very commonly used for modeling digital clinical measures. While deep learning models for TSC are very common and powerful, there exist some fundamental challenges. This review presents the non-deep learning models that are commonly used for time series classification in biomedical applications that can achieve high performance. Objective: We performed a systematic review to characterize the techniques that are used in time series classification of digital clinical measures throughout all the stages of data processing and model building. Methods: We conducted a literature search on PubMed, as well as the Institute of Electrical and Electronics Engineers (IEEE), Web of Science, and SCOPUS databases using a range of search terms to retrieve peer-reviewed articles that report on the academic research about digital clinical measures from a five-year period between June 2016 and June 2021. We identified and categorized the research studies based on the types of classification algorithms and sensor input types. Results: We found 452 papers in total from four different databases: PubMed, IEEE, Web of Science Database, and SCOPUS. After removing duplicates and irrelevant papers, 135 articles remained for detailed review and data extraction. Among these, engineered features using time series methods that were subsequently fed into widely used machine learning classifiers were the most commonly used technique, and also most frequently achieved the best performance metrics (77 out of 135 articles). Statistical modeling (24 out of 135 articles) algorithms were the second most common and also the second-best classification technique. Conclusions: In this review paper, summaries of the time series classification models and interpretation methods for biomedical applications are summarized and categorized. While high time series classification performance has been achieved in digital clinical, physiological, or biomedical measures, no standard benchmark datasets, modeling methods, or reporting methodology exist. There is no single widely used method for time series model development or feature interpretation, however many different methods have proven successful.

ATLAS: An Adaptive Transfer Learning Based Pain Assessment System: A Real Life Unsupervised Pain Assessment Solution

Undertreatment or overtreatment of pain will cause severe consequences physiologically and psychologically. Thus, researchers have made great efforts to develop automatic pain assessment approaches based on physiological signals using machine learning techniques. However, state-of-art research mainly focuses on verifying the hypothesis that physiological signals can be used to assess pain. The critical assumption of these studies is that training data and testing data have the same distribution. However, this assumption may not hold in reallife scenarios, for instance, the adoption of machine learning model by a new patient. Such real-life scenarios in which user's data is unlabeled is largely neglected in literature. This study compensates for the rift by proposing an adaptive transfer learning based pain assessment system (ATLAS), a novel adaptive learning system based on the transfer learning algorithm Transfer Components Analysis (TCA) to minimize the distance between training data and unlabeled testing data. Experiments were conducted on BioVid database, and the results showed our approach outperforms three existing traditional machine learning-based approaches and achieves an accuracy just 2.0% below the accuracy with labeled data.

Explainable AI (XAI) Applied in Machine Learning for Pain Modeling: A Review

Pain is a complex term that describes various sensations that create discomfort in various ways or types inside the human body. Generally, pain has consequences that range from mild to severe in different organs of the body and will depend on the way it is caused, which could be an injury, illness or medical procedures including testing, surgeries or therapies, etc. With recent advances in artificial-intelligence (AI) systems associated in biomedical and healthcare settings, the contiguity of physician, clinician and patient has shortened. AI, however, has more scope to interpret the pain associated in patients with various conditions by using any physiological or behavioral changes. Facial expressions are considered to give much information that relates with emotions and pain, so clinicians consider these changes with high importance for assessing pain. This has been achieved in recent times with different machine-learning and deep-learning models. To accentuate the future scope and importance of AI in medical field, this study reviews the explainable AI (XAI) as increased attention is given to an automatic assessment of pain. This review discusses how these approaches are applied for different pain types.

Key Feature Extraction Method of Electroencephalogram Signal by Independent Component Analysis for Athlete Selection and Training

Emotion is an important expression generated by human beings to external stimuli in the process of interaction with the external environment. It affects all aspects of our lives all the time. Accurate identification of human emotional states and further application in artificial intelligence can better improve and assist human life. Therefore, the research on emotion recognition has attracted the attention of many scholars in the field of artificial intelligence in recent years. Brain electrical signal conversion becomes critical, and it needs a brain electrical signal processing method to extract the effective signal to realize the human-computer interaction However, nonstationary nonlinear characteristics of EEG signals bring great challenge in characteristic signal extraction. At present, although there are many feature extraction methods, none of them can reflect the global feature of the signal. The following solutions are used to solve the above problems: (1) this paper proposed an ICA and sample entropy algorithm-based framework for feature extraction of EEG signals, which has not been applied for EEG and (2) simulation signals were used to verify the feasibility of this method, and experiments were carried out on two real-world data sets, to show the advantages of the new algorithm in feature extraction of EEG signals.

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.

Hybrid deep convolutional model-based emotion recognition using multiple physiological signals

Emotion recognition has become increasingly utilized in the medical, advertising, and military domains. Recognizing the cues of emotion from human behaviors or physiological responses is encouraging for the research community. However, extracting true characteristics from sensor data to understand emotions can be challenging due to the complex nature of these signals. Therefore, advanced feature engineering techniques are required for accurate signal recognition. This study presents a hybrid affective model that employs a transfer learning approach for emotion classification using large-frame sensor signals which employ a genuine dataset of signal fusion gathered from 30 participants using wearable sensor systems interconnected with mobile devices. The proposed approach implements several learning algorithms such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and several other shallow methods on the sensor input to handle the requirements for the traditional feature extraction process. The findings reveal that the use of deep learning methods is satisfactory in affect recognition when a great number of frames is employed, and the proposed hybrid deep model outperforms traditional neural network (overall accuracy of 54%) and deep learning approaches (overall accuracy of 76%), with an average classification accuracy of 93%. This hybrid deep model also has a higher accuracy than our previously proposed statistical autoregressive hidden Markov model (AR-HMM) approach, with 88.6% accuracy. Accuracy assessment was performed by means of several statistics measures (accuracy, precision, recall, F-measure, and RMSE).

Decoding of the coupling between the brain and facial muscle reactions in auditory stimulation

BACKGROUND

Analysis of the reactions of different organs to external stimuli is an important area of research in physiological science.

OBJECTIVE

In this paper, we investigated the correlation between the brain and facial muscle activities by information-based analysis of electroencephalogram (EEG) signals and electromyogram (EMG) signals using Shannon entropy.

METHOD

The EEG and EMG signals of thirteen subjects were recorded during rest and auditory stimulations using relaxing, pop, and rock music. Accordingly, we calculated the Shannon entropy of these signals.

RESULTS

The results showed that rock music has a greater effect on the information of EEG and EMG signals than pop music, which itself has a greater effect than relaxing music. Furthermore, a strong correlation (r= 0.9980) was found between the variations of the information of EEG and EMG signals.

CONCLUSION

The activities of the facial muscle and brain are correlated in different conditions. This technique can be utilized to investigate the correlation between the activities of different organs versus brain activity in different situations.

Virtual Reality in Home Palliative Care: Brief Report on the Effect on Cancer-Related Symptomatology

Virtual reality (VR) has been used as a complementary therapy for managing psychological and physical symptoms in cancer patients. In palliative care, the evidence about the use of VR is still inadequate. This study aims to assess the effect of an immersive VR-based intervention conducted at home on anxiety, depression, and pain over 4days and to evaluate the short-term effect of VR sessions on cancer-related symptomatology. Participants were advanced cancer patients assisted at home who were provided with a VR headset for 4days. On days one and four, anxiety and depression were measured by the Hospital Anxiety and Depression Scale (HADS) and pain by the Brief Pain Inventory (BPI). Before and after each VR session, symptoms were collected by the Edmonton Symptom Assessment Scale (ESAS). Participants wore a smart wristband measuring physiological signals associated with pain, anxiety, and depression. Fourteen patients (mean age 47.2±14.2years) were recruited. Anxiety, depression (HADS), and pain (BPI) did not change significantly between days one and four. However, the ESAS items related to pain, depression, anxiety, well-being, and shortness of breath collected immediately after the VR sessions showed a significant improvement (p<0.01). A progressive reduction in electrodermal activity has been observed comparing the recordings before, during, and after the VR sessions, although these changes were not statistically significant. This brief research report supports the idea that VR could represent a suitable complementary tool for psychological treatment in advanced cancer patients assisted at home.

Multi-Modal Pain Intensity Assessment Based on Physiological Signals: A Deep Learning Perspective

Traditional pain assessment approaches ranging from self-reporting methods, to observational scales, rely on the ability of an individual to accurately assess and successfully report observed or experienced pain episodes. Automatic pain assessment tools are therefore more than desirable in cases where this specific ability is negatively affected by various psycho-physiological dispositions, as well as distinct physical traits such as in the case of professional athletes, who usually have a higher pain tolerance as regular individuals. Hence, several approaches have been proposed during the past decades for the implementation of an autonomous and effective pain assessment system. These approaches range from more conventional supervised and semi-supervised learning techniques applied on a set of carefully hand-designed feature representations, to deep neural networks applied on preprocessed signals. Some of the most prominent advantages of deep neural networks are the ability to automatically learn relevant features, as well as the inherent adaptability of trained deep neural networks to related inference tasks. Yet, some significant drawbacks such as requiring large amounts of data to train deep models and over-fitting remain. Both of these problems are especially relevant in pain intensity assessment, where labeled data is scarce and generalization is of utmost importance. In the following work we address these shortcomings by introducing several novel multi-modal deep learning approaches (characterized by specific supervised, as well as self-supervised learning techniques) for the assessment of pain intensity based on measurable bio-physiological data. While the proposed supervised deep learning approach is able to attain state-of-the-art inference performances, our self-supervised approach is able to significantly improve the data efficiency of the proposed architecture by automatically generating physiological data and simultaneously performing a fine-tuning of the architecture, which has been previously trained on a significantly smaller amount of data.

Emotional State Recognition from Peripheral Physiological Signals Using Fused Nonlinear Features and Team-Collaboration Identification Strategy

Emotion recognition realizing human inner perception has a very important application prospect in human-computer interaction. In order to improve the accuracy of emotion recognition, a novel method combining fused nonlinear features and team-collaboration identification strategy was proposed for emotion recognition using physiological signals. Four nonlinear features, namely approximate entropy (ApEn), sample entropy (SaEn), fuzzy entropy (FuEn) and wavelet packet entropy (WpEn) are employed to reflect emotional states deeply with each type of physiological signal. Then the features of different physiological signals are fused to represent the emotional states from multiple perspectives. Each classifier has its own advantages and disadvantages. In order to make full use of the advantages of other classifiers and avoid the limitation of single classifier, the team-collaboration model is built and the team-collaboration decision-making mechanism is designed according to the proposed team-collaboration identification strategy which is based on the fusion of support vector machine (SVM), decision tree (DT) and extreme learning machine (ELM). Through analysis, SVM is selected as the main classifier with DT and ELM as auxiliary classifiers. According to the designed decision-making mechanism, the proposed team-collaboration identification strategy can effectively employ different classification methods to make decision based on the characteristics of the samples through SVM classification. For samples which are easy to be identified by SVM, SVM directly determines the identification results, whereas SVM-DT-ELM collaboratively determines the identification results, which can effectively utilize the characteristics of each classifier and improve the classification accuracy. The effectiveness and universality of the proposed method are verified by Augsburg database and database for emotion analysis using physiological (DEAP) signals. The experimental results uniformly indicated that the proposed method combining fused nonlinear features and team-collaboration identification strategy presents better performance than the existing methods.

Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features

Existing research on myoelectric control systems primarily focuses on extracting discriminative characteristics of the electromyographic (EMG) signal by designing handcrafted features. Recently, however, deep learning techniques have been applied to the challenging task of EMG-based gesture recognition. The adoption of these techniques slowly shifts the focus from feature engineering to feature learning. Nevertheless, the black-box nature of deep learning makes it hard to understand the type of information learned by the network and how it relates to handcrafted features. Additionally, due to the high variability in EMG recordings between participants, deep features tend to generalize poorly across subjects using standard training methods. Consequently, this work introduces a new multi-domain learning algorithm, named ADANN (Adaptive Domain Adversarial Neural Network), which significantly enhances (p = 0.00004) inter-subject classification accuracy by an average of 19.40% compared to standard training. Using ADANN-generated features, this work provides the first topological data analysis of EMG-based gesture recognition for the characterization of the information encoded within a deep network, using handcrafted features as landmarks. This analysis reveals that handcrafted features and the learned features (in the earlier layers) both try to discriminate between all gestures, but do not encode the same information to do so. In the later layers, the learned features are inclined to instead adopt a one-vs.-all strategy for a given class. Furthermore, by using convolutional network visualization techniques, it is revealed that learned features actually tend to ignore the most activated channel during contraction, which is in stark contrast with the prevalence of handcrafted features designed to capture amplitude information. Overall, this work paves the way for hybrid feature sets by providing a clear guideline of complementary information encoded within learned and handcrafted features.

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.

A review of feature selection methods in medical applications

Feature selection is a preprocessing technique that identifies the key features of a given problem. It has traditionally been applied in a wide range of problems that include biological data processing, finance, and intrusion detection systems. In particular, feature selection has been successfully used in medical applications, where it can not only reduce dimensionality but also help us understand the causes of a disease. We describe some basic concepts related to medical applications and provide some necessary background information on feature selection. We review the most recent feature selection methods developed for and applied in medical problems, covering prolific research fields such as medical imaging, biomedical signal processing, and DNA microarray data analysis. A case study of two medical applications that includes actual patient data is used to demonstrate the suitability of applying feature selection methods in medical problems and to illustrate how these methods work in real-world scenarios.