BioVid Heat Pain Database Research Articles

Logistic Regression Based Model for Pain Intensity Level Detection from Biomedical Signal

Hospitals today make the effort to assess acute pain with self-report assessments such as the quantitative pain the level of intensity Index and visual input index. However, because these techniques rely on patient input, they are imprecise. Thus, an objective, statistical approach to ongoing pain monitoring is necessary. In computer vision research, identifying pain intensity is a difficult challenge to solve. However, current subjective pain evaluation is unreliable because it heavily relies on the patient's response. In order to improve the standardization of pain evaluation, automated pain identification using physiological data might provide essential objective information. In the present study, we provide an objective pain recognition approach based on physiological signals that can extract novel features from electromyography (EMG), electrodermal activity (EDA), and electrocardiogram (ECG) data that have not previously been utilized for pain recognition. Utilizing the Bio-Vid Heat Pain Database (Part A) for evaluation and clinical validation, the proposed machine learning logistic regression-based method performs significantly better than previous techniques recorded in the literature for both the electrodermal activity (EDA) and fusion approaches, with average performances of 82.36% and 83.20% for the binary classification experiment that discriminates within the baseline and the pain tolerance level (T0 vs. T4). Our result shows that it outperforms most of the previously proposed methods in related works.

A Comprehensive Study on Pain Assessment from Multimodal Sensor Data.

Pain assessment is a critical aspect of healthcare, influencing timely interventions and patient well-being. Traditional pain evaluation methods often rely on subjective patient reports, leading to inaccuracies and disparities in treatment, especially for patients who present difficulties to communicate due to cognitive impairments. Our contributions are three-fold. Firstly, we analyze the correlations of the data extracted from biomedical sensors. Then, we use state-of-the-art computer vision techniques to analyze videos focusing on the facial expressions of the patients, both per-frame and using the temporal context. We compare them and provide a baseline for pain assessment methods using two popular benchmarks: UNBC-McMaster Shoulder Pain Expression Archive Database and BioVid Heat Pain Database. We achieved an accuracy of over 96% and over 94% for the F1 Score, recall and precision metrics in pain estimation using single frames with the UNBC-McMaster dataset, employing state-of-the-art computer vision techniques such as Transformer-based architectures for vision tasks. In addition, from the conclusions drawn from the study, future lines of work in this area are discussed.

Design and Evaluation of Deep Learning Models for Continuous Acute Pain Detection Based on Phasic Electrodermal Activity.

The current method for assessing pain in clinical practice is subjective and relies on self-reported scales. An objective and accurate method of pain assessment is needed for physicians to prescribe the proper medication dosage, which could reduce addiction to opioids. Hence, many works have used electrodermal activity (EDA) as a suitable signal for detecting pain. Previous studies have used machine learning and deep learning to detect pain responses, but none have used a sequence-to-sequence deep learning approach to continuously detect acute pain from EDA signals, as well as accurate detection of pain onset. In this study, we evaluated deep learning models including 1-dimensional convolutional neural networks (1D-CNN), long short-term memory networks (LSTM), and three hybrid CNN-LSTM architectures for continuous pain detection using phasic EDA features. We used a database consisting of 36 healthy volunteers who underwent pain stimuli induced by a thermal grill. We extracted the phasic component, phasic drivers, and time-frequency spectrum of the phasic EDA (TFS-phEDA), which was found to be the most discerning physiomarker. The best model was a parallel hybrid architecture of a temporal convolutional neural network and a stacked bi-directional and uni-directional LSTM, which obtained a F1-score of 77.8% and was able to correctly detect pain in 15-second signals. The model was evaluated using 37 independent subjects from the BioVid Heat Pain Database and outperformed other approaches in recognizing higher pain levels compared to baseline with an accuracy of 91.5%. The results show the feasibility of continuous pain detection using deep learning and EDA.

Explainable Artificial Intelligence (XAI) in Pain Research: Understanding the Role of Electrodermal Activity for Automated Pain Recognition.

Artificial intelligence and especially deep learning methods have achieved outstanding results for various applications in the past few years. Pain recognition is one of them, as various models have been proposed to replace the previous gold standard with an automated and objective assessment. While the accuracy of such models could be increased incrementally, the understandability and transparency of these systems have not been the main focus of the research community thus far. Thus, in this work, several outcomes and insights of explainable artificial intelligence applied to the electrodermal activity sensor data of the PainMonit and BioVid Heat Pain Database are presented. For this purpose, the importance of hand-crafted features is evaluated using recursive feature elimination based on impurity scores in Random Forest (RF) models. Additionally, Gradient-weighted class activation mapping is applied to highlight the most impactful features learned by deep learning models. Our studies highlight the following insights: (1) Very simple hand-crafted features can yield comparative performances to deep learning models for pain recognition, especially when properly selected with recursive feature elimination. Thus, the use of complex neural networks should be questioned in pain recognition, especially considering their computational costs; and (2) both traditional feature engineering and deep feature learning approaches rely on simple characteristics of the input time-series data to make their decision in the context of automated pain recognition.

Pain Recognition With Physiological Signals Using Multi-Level Context Information

Automatic pain recognition is essential in healthcare. In previous studies, automatic pain recognition methods preferentially apply the features extracted from physiological signals for conventional models. This method provides good performance but mainly relies on medical expertise for feature extraction of physiological signals. This paper presents a deep learning approach based on physiological signals that have the role of both feature extraction and classification, regardless of medical expertise. We propose multi-level context information for each physiological signal discriminating between pain and painlessness. Our experimental results prove that multi-level context information has more significant performances than uni-level context information based on Part A of the BioVid Heat Pain database and the Emopain 2021 dataset. For Part A of the BioVid Heat Pain database, our experimental results for pain recognition tasks include: Pain 0 and Pain 1, Pain 0 and Pain 2, Pain 0 and Pain 3, and Pain 0 and Pain 4. In the classification task between Pain 0 and Pain 4, the results achieve an average accuracy of 84.8 ± 13.3% for 87 subjects and 87.8 ± 11.4% for 67 subjects in a Leave-One-Subject-Out cross-validation evaluation. The proposed method adopts the ability of deep learning to outperform conventional methods on physiological signals.

Automatic Estimation of Self-Reported Pain by Trajectory Analysis in the Manifold of Fixed Rank Positive Semi-Definite Matrices.

We propose an automatic method to estimate self-reported pain based on facial landmarks extracted from videos. For each video sequence, we decompose the face into four different regions and the pain intensity is measured by modeling the dynamics of facial movement using the landmarks of these regions. A formulation based on Gram matrices is used for representing the trajectory of landmarks on the Riemannian manifold of symmetric positive semi-definite matrices of fixed rank. A curve fitting algorithm is used to smooth the trajectories and temporal alignment is performed to compute the similarity between the trajectories on the manifold. A Support Vector Regression classifier is then trained to encode extracted trajectories into pain intensity levels consistent with self-reported pain intensity measurement. Finally, a late fusion of the estimation for each region is performed to obtain the final predicted pain level. The proposed approach is evaluated on two publicly available datasets, the UNBCMcMaster Shoulder Pain Archive and the Biovid Heat Pain dataset. We compared our method to the state-of-the-art on both datasets using different testing protocols, showing the competitiveness of the proposed approach.

Real-Time Classification of Pain Level Using Zygomaticus and Corrugator EMG Features

The real-time recognition of pain level is required to perform an accurate pain assessment of patients in the intensive care unit, infants, and other subjects who may not be able to communicate verbally or even express the sensation of pain. Facial expression is a key pain-related behavior that may unlock the answer to an objective pain measurement tool. In this work, a machine learning-based pain level classification system using data collected from facial electromyograms (EMG) is presented. The dataset was acquired from part of the BioVid Heat Pain database to evaluate facial expression from an EMG corrugator and EMG zygomaticus and an EMG signal processing and data analysis flow is adapted for continuous pain estimation. The extracted pain-associated facial electromyography (fEMG) features classification is performed by K-nearest neighbor (KNN) by choosing the value of k which depends on the nonlinear models. The presentation of the accuracy estimation is performed, and considerable growth in classification accuracy is noticed when the subject matter from the features is omitted from the analysis. The ML algorithm for the classification of the amount of pain experienced by patients could deliver valuable evidence for health care providers and aid treatment assessment. The proposed classification algorithm has achieved a 99.4% accuracy for classifying the pain tolerance level from the baseline (P0 versus P4) without the influence of a subject bias. Moreover, the result on the classification accuracy clearly shows the relevance of the proposed approach.

Machine Learning-Based Pain Intensity Estimation: Where Pattern Recognition Meets Chaos Theory—An Example Based on the BioVid Heat Pain Database

In general, classification tasks can differ significantly in their task complexity. For instance, image-based differentiation between vehicles and pedestrians is most likely expected to be less complex than CT-scan-based differentiation between several lung diseases. Intuitively, based on a human point of view, one can identify some classification tasks as more complex than other classification tasks. Moreover, based on expert knowledge and/or task-specific meta information, one could attempt to estimate the complexity ranks of specific classification tasks. In this work, based on the publicly available BioVid Heat Pain Database (BVDB), we experimentally confirm the intuitive assumption that the task of automated pain intensity recognition (PIR) is very challenging. Inspired by the field of chaos theory, we show that the BVDB-specific PIR task can not only be seen as highly complex, but is even identified as a classification task of chaotic nature. To this end, we apply Hao’s working definition for chaotic systems and provide an experiment-based chaos check method. To validate our approach, as a non-complex counterpart, we include a task of handwritten numerals distinction. Our study provides two main contributions, i.e.: i) an enhanced understanding for the still present and – more importantly – substantial gap between the ground truth and the predictions reported by different research groups in combination with automated PIR tasks; and ii) an approach for a numerical complexity check based on chaos theory. Different research directions are discussed for future work. Note that improving PIR accuracy performance is not part of the study objective.

ALTERNATIVE METHOD FOR PAIN ASSESSMENT USING EMG AND GSR

Most of the existing pain estimation techniques depend on the response of the subject through verbal or nonverbal communication which does not suit infants, senseless and injured persons, and subjects with cognitive impairment. To bridge this gap, researchers have explored the potential of facial video- and image-based pain recognition methods. However, it provides limited classification performance with complex computation and costly frameworks including a large storage capacity. The dependence of autonomic nervous system (ANS) activities on stimulus like pain provides an alternative pathway to assess pain subjected to external stimuli through ANS-related biosignals. In this article, processing and analysis technique of electromyogram and galvanic skin response signals for assessment of pain for noncooperative subjects are presented and validated against BioVid heat pain database. Different intensities of pain are considered and characterized with the statistical features extracted from the said biosignals. It is noticed that the accuracy level of pain estimation increases with the rise in pain intensity. For highest pain level, 80% detection accuracy is achieved which outperforms the performances of facial expression-based pain assessment techniques.

Automated Nociceptive Pain Assessment Using Physiological Signals and a Hybrid Deep Learning Network

Postoperative pain management has become a major medical and nursing challenge. Nowadays, hospitals have taken initiatives to measure acute pain using self-report measures like the Visual Analogue Scale and Numeric Pain Intensity Scale. But these methods are inaccurate as it depends on patient’s input. Therefore, there is a requirement for an objective, quantitative method to monitor pain continuously. In this work, an automated acute nociceptive pain recognition system was proposed to objectively measure nociceptive pain using physiological signals and a hybrid Deep Learning network. The hybrid deep learning network constitutes a shallow CNN network that extracts the essential information of the pain from the physiological signals and the extracted feature matrix is fed to the LSTM network for feature concatenation. This process realizes the mapping of nociceptive pain from input data to detection. This work utilizes the BioVid Heat Pain database. A Unimodal hybrid CNN_LSTM network (using ECG signals) has achieved 68.70 percent, 62.61 percent, 67.86 percent, and 75.21 percent of classification accuracy for classification events (BL1 Vs PA1, BL1 Vs PA2, BL1 Vs PA3, and BL1 Vs PA4). Similarly, for classification events (BL1 Vs PA1, BL1 Vs PA2, BL1 Vs PA3, and BL1 Vs PA4), the unimodal hybrid CNN_LSTM network (using EDA signals) achieved 85.65 percent, 74.47 percent, 80.80 percent, and 80.17 percent of classification accuracy. Finally, for classification events (BL1 Vs PA1, BL1 Vs PA2, BL1 Vs PA3, and BL1 Vs PA4), the CNN_LSTM multimodal hybrid network (using both ECG and EDA signals) achieved 93.91 percent, 86.97 percent, 90.75 percent, and 94.12 percent of the classification accuracy, respectively.

Two-Stream Attention Network for Pain Recognition from Video Sequences.

Several approaches have been proposed for the analysis of pain-related facial expressions. These approaches range from common classification architectures based on a set of carefully designed handcrafted features, to deep neural networks characterised by an autonomous extraction of relevant facial descriptors and simultaneous optimisation of a classification architecture. In the current work, an end-to-end approach based on attention networks for the analysis and recognition of pain-related facial expressions is proposed. The method combines both spatial and temporal aspects of facial expressions through a weighted aggregation of attention-based neural networks’ outputs, based on sequences of Motion History Images (MHIs) and Optical Flow Images (OFIs). Each input stream is fed into a specific attention network consisting of a Convolutional Neural Network (CNN) coupled to a Bidirectional Long Short-Term Memory (BiLSTM) Recurrent Neural Network (RNN). An attention mechanism generates a single weighted representation of each input stream (MHI sequence and OFI sequence), which is subsequently used to perform specific classification tasks. Simultaneously, a weighted aggregation of the classification scores specific to each input stream is performed to generate a final classification output. The assessment conducted on both the BioVid Heat Pain Database (Part A) and SenseEmotion Database points at the relevance of the proposed approach, as its classification performance is on par with state-of-the-art classification approaches proposed in the literature.

Exploring Deep Physiological Models for Nociceptive Pain Recognition

Standard feature engineering involves manually designing measurable descriptors based on some expert knowledge in the domain of application, followed by the selection of the best performing set of designed features for the subsequent optimisation of an inference model. Several studies have shown that this whole manual process can be efficiently replaced by deep learning approaches which are characterised by the integration of feature engineering, feature selection and inference model optimisation into a single learning process. In the following work, deep learning architectures are designed for the assessment of measurable physiological channels in order to perform an accurate classification of different levels of artificially induced nociceptive pain. In contrast to previous works, which rely on carefully designed sets of hand-crafted features, the current work aims at building competitive pain intensity inference models through autonomous feature learning, based on deep neural networks. The assessment of the designed deep learning architectures is based on the BioVid Heat Pain Database (Part A) and experimental validation demonstrates that the proposed uni-modal architecture for the electrodermal activity (EDA) and the deep fusion approaches significantly outperform previous methods reported in the literature, with respective average performances of and for the binary classification experiment consisting of the discrimination between the baseline and the pain tolerance level ( vs. ) in a Leave-One-Subject-Out (LOSO) cross-validation evaluation setting. Moreover, the experimental results clearly show the relevance of the proposed approaches, which also offer more flexibility in the case of transfer learning due to the modular nature of deep neural networks.

Wireless ECG Monitoring System using IoT based Signal Conditioning Module For Real Time Signal Acquisition

Recently, in human health care scenario most of the people are suffering by arrhythmia which is a type of the cardiovascular diseases and it occurs during a person has irregular or abnormal heart rate. To diagnose such condition, there should be continuous monitoring of electrocardiogram signal irrespective of the location confined to the subject and the appropriate physician. In this research, wireless ECG monitoring system using AD8232 signal conditioning module for real time signal acquisition was proposed. The proposed system performs continuous ECG signal monitoring that integrates Wi-Fi technology which acquires the ECG signal and transmit it to cloud wirelessly. Also, feature extraction algorithm has been developed to extract features such as RMSSD, SDNN, Mean RR, Ratio SR and slope of linear regression of IBI from ECG signal of BioVid Heat pain database for different pain levels. The same feature extraction algorithm can be applied on real time ECG signal to extract the features. From the results, it is clear that the proposed system is advantageous for the physicians to provide the right health care to the subject without being in close proximity.

Prediction of pain intensity using multimedia data

Increased medical expenditure, improper treatment, decreased productivity and above all inadequate pain, assessment is the global challenging problem, causing a substantial burden on the individual, their family, and society which often leads to loss of interest in life. The facial expression variation generally reflects clue for the occurrence of pain. This offers a vital aspect for non-verbal patients who are not in a position to rate their pain intensity level. The hypothesis proposes the developing of a multimodal machine based tool which will assess pain intensity. A framework has been designed to meet up with these specific issues which involve extracting features from the face and genes involved in pain. Patients suffering from pain require a comprehensive assessment to be conducted for proper diagnosis. The contributions of this paper are fourfold: Firstly, this paper provides an efficient approach to computational pain quantification. Secondly, it investigates the medical practitioner perception to pain along with the readings of the various tools available. Thirdly, the psychological aspect is taken into consideration to predict how pain is perceived by observers and experts (physicians). Fourthly, genes involved in pain and no pain conditions are taken and classified. Three large databases of spontaneous pain expressions are used i.e., McMaster UNBC Pain Archive database, self-prepared database and the other BioVid heat pain database of pain to verify the accuracy and robustness of the system. The methodology achieves 87% accuracy rate for classification of frames amid four levels of pain intensity. Designing intelligent computing systems with the given methodology will certainly improve the quality of life of patients.