Machine learning in pain research

Cracking the Chronic Pain code: A scoping review of Artificial Intelligence in Chronic Pain research

OBJECTIVE

The aim of this review is to identify gaps and provide a direction for future research in the utilization of Artificial Intelligence (AI) in chronic pain (CP) management.

METHODS

A comprehensive literature search was conducted using various databases, including Ovid MEDLINE, Web of Science Core Collection, IEEE Xplore, and ACM Digital Library. The search was limited to studies on AI in CP research, focusing on diagnosis, prognosis, clinical decision support, self-management, and rehabilitation. The studies were evaluated based on predefined inclusion criteria, including the reporting quality of AI algorithms used.

RESULTS

After the screening process, 60 studies were reviewed, highlighting AI's effectiveness in diagnosing and classifying CP while revealing gaps in the attention given to treatment and rehabilitation. It was found that the most commonly used algorithms in CP research were support vector machines, logistic regression and random forest classifiers. The review also pointed out that attention to CP mechanisms is negligible despite being the most effective way to treat CP.

CONCLUSION

The review concludes that to achieve more effective outcomes in CP management, future research should prioritize identifying CP mechanisms, CP management, and rehabilitation while leveraging a wider range of algorithms and architectures.

SIGNIFICANCE

This review highlights the potential of AI in improving the management of CP, which is a significant personal and economic burden affecting more than 30% of the world's population. The identified gaps and future research directions provide valuable insights to researchers and practitioners in the field, with the potential to improve healthcare utilization.

The usefulness of artificial intelligence in breast reconstruction: a systematic review

BACKGROUND

Artificial Intelligence (AI) offers an approach to predictive modeling. The model learns to determine specific patterns of undesirable outcomes in a dataset. Therefore, a decision-making algorithm can be built based on these patterns to prevent negative results. This systematic review aimed to evaluate the usefulness of AI in breast reconstruction.

METHODS

A systematic review was conducted in August 2022 following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. MEDLINE, EMBASE, SCOPUS, and Google Scholar online databases were queried to capture all publications studying the use of artificial intelligence in breast reconstruction.

RESULTS

A total of 23 studies were full text-screened after removing duplicates, and twelve articles fulfilled our inclusion criteria. The Machine Learning algorithms applied for neuropathic pain, lymphedema diagnosis, microvascular abdominal flap failure, donor site complications associated to muscle sparing Transverse Rectus Abdominis flap, surgical complications, financial toxicity, and patient-reported outcomes after breast surgery demonstrated that AI is a helpful tool to accurately predict patient results. In addition, one study used Computer Vision technology to assist in Deep Inferior Epigastric Perforator Artery detection for flap design, considerably reducing the preoperative time compared to manual identification.

CONCLUSIONS

In breast reconstruction, AI can help the surgeon by optimizing the perioperative patients' counseling to predict negative outcomes, allowing execution of timely interventions and reducing the postoperative burden, which leads to obtaining the most successful results and improving patient satisfaction.

Machine learning study of the extended drug-target interaction network informed by pain related voltage-gated sodium channels

ABSTRACT

Pain is a significant global health issue, and the current treatment options for pain management have limitations in terms of effectiveness, side effects, and potential for addiction. There is a pressing need for improved pain treatments and the development of new drugs. Voltage-gated sodium channels, particularly Nav1.3, Nav1.7, Nav1.8, and Nav1.9, play a crucial role in neuronal excitability and are predominantly expressed in the peripheral nervous system. Targeting these channels may provide a means to treat pain while minimizing central and cardiac adverse effects. In this study, we construct protein-protein interaction (PPI) networks based on pain-related sodium channels and develop a corresponding drug-target interaction network to identify potential lead compounds for pain management. To ensure reliable machine learning predictions, we carefully select 111 inhibitor data sets from a pool of more than 1000 targets in the PPI network. We employ 3 distinct machine learning algorithms combined with advanced natural language processing (NLP)-based embeddings, specifically pretrained transformer and autoencoder representations. Through a systematic screening process, we evaluate the side effects and repurposing potential of more than 150,000 drug candidates targeting Nav1.7 and Nav1.8 sodium channels. In addition, we assess the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of these candidates to identify leads with near-optimal characteristics. Our strategy provides an innovative platform for the pharmacological development of pain treatments, offering the potential for improved efficacy and reduced side effects.

Machine learning-based evaluation of spontaneous pain and analgesics from cellular calcium signals in the mouse primary somatosensory cortex using explainable features

Introduction

Pain that arises spontaneously is considered more clinically relevant than pain evoked by external stimuli. However, measuring spontaneous pain in animal models in preclinical studies is challenging due to methodological limitations. To address this issue, recently we developed a deep learning (DL) model to assess spontaneous pain using cellular calcium signals of the primary somatosensory cortex (S1) in awake head-fixed mice. However, DL operate like a "black box", where their decision-making process is not transparent and is difficult to understand, which is especially evident when our DL model classifies different states of pain based on cellular calcium signals. In this study, we introduce a novel machine learning (ML) model that utilizes features that were manually extracted from S1 calcium signals, including the dynamic changes in calcium levels and the cell-to-cell activity correlations.

Method

We focused on observing neural activity patterns in the primary somatosensory cortex (S1) of mice using two-photon calcium imaging after injecting a calcium indicator (GCaMP6s) into the S1 cortex neurons. We extracted features related to the ratio of up and down-regulated cells in calcium activity and the correlation level of activity between cells as input data for the ML model. The ML model was validated using a Leave-One-Subject-Out Cross-Validation approach to distinguish between non-pain, pain, and drug-induced analgesic states.

Results and discussion

The ML model was designed to classify data into three distinct categories: non-pain, pain, and drug-induced analgesic states. Its versatility was demonstrated by successfully classifying different states across various pain models, including inflammatory and neuropathic pain, as well as confirming its utility in identifying the analgesic effects of drugs like ketoprofen, morphine, and the efficacy of magnolin, a candidate analgesic compound. In conclusion, our ML model surpasses the limitations of previous DL approaches by leveraging manually extracted features. This not only clarifies the decision-making process of the ML model but also yields insights into neuronal activity patterns associated with pain, facilitating preclinical studies of analgesics with higher potential for clinical translation.

Empirical comparison of deep learning models for fNIRS pain decoding

Introduction

Pain assessment is extremely important in patients unable to communicate and it is often done by clinical judgement. However, assessing pain using observable indicators can be challenging for clinicians due to the subjective perceptions, individual differences in pain expression, and potential confounding factors. Therefore, the need for an objective pain assessment method that can assist medical practitioners. Functional near-infrared spectroscopy (fNIRS) has shown promising results to assess the neural function in response of nociception and pain. Previous studies have explored the use of machine learning with hand-crafted features in the assessment of pain.

Methods

In this study, we aim to expand previous studies by exploring the use of deep learning models Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and (CNN-LSTM) to automatically extract features from fNIRS data and by comparing these with classical machine learning models using hand-crafted features.

Results

The results showed that the deep learning models exhibited favourable results in the identification of different types of pain in our experiment using only fNIRS input data. The combination of CNN and LSTM in a hybrid model (CNN-LSTM) exhibited the highest performance (accuracy = 91.2%) in our problem setting. Statistical analysis using one-way ANOVA with Tukey's (post-hoc) test performed on accuracies showed that the deep learning models significantly improved accuracy performance as compared to the baseline models.

Discussion

Overall, deep learning models showed their potential to learn features automatically without relying on manually-extracted features and the CNN-LSTM model could be used as a possible method of assessment of pain in non-verbal patients. Future research is needed to evaluate the generalisation of this method of pain assessment on independent populations and in real-life scenarios.

Psycho-Neuroendocrinology in the Rehabilitation Field: Focus on the Complex Interplay between Stress and Pain

Chronic stress and chronic pain share neuro-anatomical, endocrinological, and biological features. However, stress prepares the body for challenging situations or mitigates tissue damage, while pain is an unpleasant sensation due to nociceptive receptor stimulation. When pain is chronic, it might lead to an allostatic overload in the body and brain due to the chronic dysregulation of the physiological systems that are normally involved in adapting to environmental challenges. Managing stress and chronic pain (CP) in neurorehabilitation presents a significant challenge for healthcare professionals and researchers, as there is no definitive and effective solution for these issues. Patients suffering from neurological disorders often complain of CP, which significantly reduces their quality of life. The aim of this narrative review is to examine the correlation between stress and pain and their potential negative impact on the rehabilitation process. Moreover, we described the most relevant interventions used to manage stress and pain in the neurological population. In conclusion, this review sheds light on the connection between chronic stress and chronic pain and their impact on the neurorehabilitation pathway. Our results emphasize the need for tailored rehabilitation protocols to effectively manage pain, improve treatment adherence, and ensure comprehensive patient care.

Multilevel Pain Assessment with Functional Near-Infrared Spectroscopy: Evaluating ΔHBO2 and ΔHHB Measures for Comprehensive Analysis

Assessing pain in non-verbal patients is challenging, often depending on clinical judgment which can be unreliable due to fluctuations in vital signs caused by underlying medical conditions. To date, there is a notable absence of objective diagnostic tests to aid healthcare practitioners in pain assessment, especially affecting critically-ill or advanced dementia patients. Neurophysiological information, i.e., functional near-infrared spectroscopy (fNIRS) or electroencephalogram (EEG), unveils the brain's active regions and patterns, revealing the neural mechanisms behind the experience and processing of pain. This study focuses on assessing pain via the analysis of fNIRS signals combined with machine learning, utilising multiple fNIRS measures including oxygenated haemoglobin (ΔHBO2) and deoxygenated haemoglobin (ΔHHB). Initially, a channel selection process filters out highly contaminated channels with high-frequency and high-amplitude artifacts from the 24-channel fNIRS data. The remaining channels are then preprocessed by applying a low-pass filter and common average referencing to remove cardio-respiratory artifacts and common gain noise, respectively. Subsequently, the preprocessed channels are averaged to create a single time series vector for both ΔHBO2 and ΔHHB measures. From each measure, ten statistical features are extracted and fusion occurs at the feature level, resulting in a fused feature vector. The most relevant features, selected using the Minimum Redundancy Maximum Relevance method, are passed to a Support Vector Machines classifier. Using leave-one-subject-out cross validation, the system achieved an accuracy of 68.51%±9.02% in a multi-class task (No Pain, Low Pain, and High Pain) using a fusion of ΔHBO2 and ΔHHB. These two measures collectively demonstrated superior performance compared to when they were used independently. This study contributes to the pursuit of an objective pain assessment and proposes a potential biomarker for human pain using fNIRS.

The Use of Artificial Intelligence to Predict the Prognosis of Patients Undergoing Central Nervous System Rehabilitation: A Narrative Review

Applications of machine learning in the healthcare field have become increasingly diverse. In this review, we investigated the integration of artificial intelligence (AI) in predicting the prognosis of patients with central nervous system disorders such as stroke, traumatic brain injury, and spinal cord injury. AI algorithms have shown promise in prognostic assessment, but challenges remain in achieving a higher prediction accuracy for practical clinical use. We suggest that accumulating more diverse data, including medical imaging and collaborative efforts among hospitals, can enhance the predictive capabilities of AI. As healthcare professionals become more familiar with AI, its role in central nervous system rehabilitation is expected to advance significantly, revolutionizing patient care.

Identifying chronic low back pain phenotypic domains and characteristics accounting for individual variation: a systematic review

ABSTRACT

Interpatient variability is frequently observed among individuals with chronic low back pain (cLBP). This review aimed at identifying phenotypic domains and characteristics that account for interpatient variability in cLBP. We searched MEDLINE ALL (through Ovid), Embase Classic and EMBASE (through Ovid), Scopus, and CINAHL Complete (through EBSCOhost) databases. Studies that aimed to identify or predict cLBP different phenotypes were included. We excluded studies that focused on specific treatments. The methodological quality was assessed using an adaptation of the Downs and Black tool. Forty-three studies were included. Although the patient and pain-related characteristics used to identify phenotypes varied considerably across studies, the following were among the most identified phenotypic domains and characteristics that account for interpatient variability in cLBP: pain-related characteristics (including location, severity, qualities, and duration) and pain impact (including disability, sleep, and fatigue), psychological domains (including anxiety and depression), behavioral domains (including coping, somatization, fear avoidance, and catastrophizing), social domains (including employment and social support), and sensory profiling (including pain sensitivity and sensitization). Despite these findings, our review showed that the evidence on pain phenotyping still requires further investigation. The assessment of the methodological quality revealed several limitations. We recommend adopting a standard methodology to enhance the generalizability of the results and the implementation of a comprehensive and feasible assessment framework to facilitate personalized treatments in clinical settings.

Parametric Modeling and Deep Learning for Enhancing Pain Assessment in Postanesthesia

OBJECTIVE

The problem of reliable and widely accepted measures of pain is still open. It follows the objective of this work as pain estimation through post-surgical trauma modeling and classification, to increase the needed reliability compared to measurements only.

METHODS

This article proposes (i) a recursive identification method to obtain the frequency response and parameterization using fractional-order impedance models (FOIM), and (ii) deep learning with convolutional neural networks (CNN) classification algorithms using time-frequency data and spectrograms. The skin impedance measurements were conducted on 12 patients throughout the postanesthesia care in a proof-of-concept clinical trial. Recursive least-squares system identification was performed using a genetic algorithm for initializing the parametric model. The online parameter estimates were compared to the self-reported level by the Numeric Rating Scale (NRS) for analysis and validation of the results. Alternatively, the inputs to CNNs were the spectrograms extracted from the time-frequency dataset, being pre-labeled in four intensities classes of pain during offline and online training with the NRS.

RESULTS

The tendency of nociception could be predicted by monitoring the changes in the FOIM parameters' values or by retraining online the network. Moreover, the tissue heterogeneity, assumed during nociception, could follow the NRS trends. The online predictions of retrained CNN have more specific trends to NRS than pain predicted by the offline population-trained CNN.

CONCLUSION

We propose tailored online identification and deep learning for artefact corrupted environment. The results indicate estimations with the potential to avoid over-dosing due to the objectivity of the information.

SIGNIFICANCE

Models and artificial intelligence (AI) allow objective and personalized nociception-antinociception prediction in the patient safety era for the design and evaluation of closed-loop analgesia controllers.

Automatic Variable Selection Algorithms in Prognostic Factor Research in Neck Pain

This study aims to compare the variable selection strategies of different machine learning (ML) and statistical algorithms in the prognosis of neck pain (NP) recovery. A total of 3001 participants with NP were included. Three dichotomous outcomes of an improvement in NP, arm pain (AP), and disability at 3 months follow-up were used. Twenty-five variables (twenty-eight parameters) were included as predictors. There were more parameters than variables, as some categorical variables had >2 levels. Eight modelling techniques were compared: stepwise regression based on unadjusted p values (stepP), on adjusted p values (stepPAdj), on Akaike information criterion (stepAIC), best subset regression (BestSubset) least absolute shrinkage and selection operator [LASSO], Minimax concave penalty (MCP), model-based boosting (mboost), and multivariate adaptive regression splines (MuARS). The algorithm that selected the fewest predictors was stepPAdj (number of predictors, p = 4 to 8). MuARS was the algorithm with the second fewest predictors selected (p = 9 to 14). The predictor selected by all algorithms with the largest coefficient magnitude was "having undergone a neuroreflexotherapy intervention" for NP (β = from 1.987 to 2.296) and AP (β = from 2.639 to 3.554), and "Imaging findings: spinal stenosis" (β = from -1.331 to -1.763) for disability. Stepwise regression based on adjusted p-values resulted in the sparsest models, which enhanced clinical interpretability. MuARS appears to provide the optimal balance between model sparsity whilst retaining high predictive performance across outcomes. Different algorithms produced similar performances but resulted in a different number of variables selected. Rather than relying on any single algorithm, confidence in the variable selection may be increased by using multiple algorithms.

Mapping the Design Space of Technology-Based Solutions for Better Chronic Pain Care: Introducing the Pain Tech Landscape

OBJECTIVES

Technology has substantial potential to transform and extend care for persons with chronic pain, a burdensome and costly condition. To catalyze the development of impactful applications of technology in this space, we developed the Pain Tech Landscape (PTL) model, which integrates pain care needs with characteristics of technological solutions.

METHODS

Our interdisciplinary group representing experts in pain and human factors research developed PTL through iterative discussions. To demonstrate one potential use of the model, we apply data generated from a narrative review of selected pain and technology journals (2000-2020) in the form of heat map overlays, to reveal where pain tech research attention has focused to date.

RESULTS

The PTL comprises three two-dimensional planes, with pain care needs on each x axis (measurement to management) and technology applications on the y axes according to a) user agency (user- to system-driven), b) usage time frame (temporary to lifelong), and c) collaboration (single-user to collaborative). Heat maps show that existing applications reside primarily in the "user-driven/management" quadrant (e.g., self-care apps). Examples of less developed areas include artificial intelligence and Internet of Things (i.e., Internet-linked household objects), and collaborative/social tools for pain management.

CONCLUSIONS

Collaborative development between the pain and tech fields in early developmental stages using the PTL as a common language could yield impactful solutions for chronic pain management. The PTL could also be used to track developments in the field over time. We encourage periodic reassessment and refinement of the PTL model, which can also be adapted to other chronic conditions.

Analysis of pain research literature through keyword Co-occurrence networks

Pain is a significant public health problem as the number of individuals with a history of pain globally keeps growing. In response, many synergistic research areas have been coming together to address pain-related issues. This work reviews and analyzes a vast body of pain-related literature using the keyword co-occurrence network (KCN) methodology. In this method, a set of KCNs is constructed by treating keywords as nodes and the co-occurrence of keywords as links between the nodes. Since keywords represent the knowledge components of research articles, analysis of KCNs will reveal the knowledge structure and research trends in the literature. This study extracted and analyzed keywords from 264,560 pain-related research articles indexed in IEEE, PubMed, Engineering Village, and Web of Science published between 2002 and 2021. We observed rapid growth in pain literature in the last two decades: the number of articles has grown nearly threefold, and the number of keywords has grown by a factor of 7. We identified emerging and declining research trends in sensors/methods, biomedical, and treatment tracks. We also extracted the most frequently co-occurring keyword pairs and clusters to help researchers recognize the synergies among different pain-related topics.

Evidence- and data-driven classification of low back pain via artificial intelligence: Protocol of the PREDICT-LBP study

In patients presenting with low back pain (LBP), once specific causes are excluded (fracture, infection, inflammatory arthritis, cancer, cauda equina and radiculopathy) many clinicians pose a diagnosis of non-specific LBP. Accordingly, current management of non-specific LBP is generic. There is a need for a classification of non-specific LBP that is both data- and evidence-based assessing multi-dimensional pain-related factors in a large sample size. The "PRedictive Evidence Driven Intelligent Classification Tool for Low Back Pain" (PREDICT-LBP) project is a prospective cross-sectional study which will compare 300 women and men with non-specific LBP (aged 18-55 years) with 100 matched referents without a history of LBP. Participants will be recruited from the general public and local medical facilities. Data will be collected on spinal tissue (intervertebral disc composition and morphology, vertebral fat fraction and paraspinal muscle size and composition via magnetic resonance imaging [MRI]), central nervous system adaptation (pain thresholds, temporal summation of pain, brain resting state functional connectivity, structural connectivity and regional volumes via MRI), psychosocial factors (e.g. depression, anxiety) and other musculoskeletal pain symptoms. Dimensionality reduction, cluster validation and fuzzy c-means clustering methods, classification models, and relevant sensitivity analyses, will classify non-specific LBP patients into sub-groups. This project represents a first personalised diagnostic approach to non-specific LBP, with potential for widespread uptake in clinical practice. This project will provide evidence to support clinical trials assessing specific treatments approaches for potential subgroups of patients with non-specific LBP. The classification tool may lead to better patient outcomes and reduction in economic costs.

Objective wearable measures correlate with self-reported chronic pain levels in people with spinal cord stimulation systems

Spinal Cord Stimulation (SCS) is a well-established therapy for treating chronic pain. However, perceived treatment response to SCS therapy may vary among people with chronic pain due to diverse needs and backgrounds. Patient Reported Outcomes (PROs) from standard survey questions do not provide the full picture of what has happened to a patient since their last visit, and digital PROs require patients to visit an app or otherwise regularly engage with software. This study aims to assess the feasibility of using digital biomarkers collected from wearables during SCS treatment to predict pain and PRO outcomes. Twenty participants with chronic pain were recruited and implanted with SCS. During the six months of the study, activity and physiological metrics were collected and data from 15 participants was used to develop a machine learning pipeline to objectively predict pain levels and categories of PRO measures. The model reached an accuracy of 0.768 ± 0.012 in predicting the pain intensity of mild, moderate, and severe. Feature importance analysis showed that digital biomarkers from the smartwatch such as heart rate, heart rate variability, step count, and stand time can contribute to modeling different aspects of pain. The results of the study suggest that wearable biomarkers can be used to predict therapy outcomes in people with chronic pain, enabling continuous, real-time monitoring of patients during the use of implanted therapies.

Towards data-driven biopsychosocial classification of non-specific chronic low back pain: a pilot study

The classification of non-specific chronic low back pain (CLBP) according to multidimensional data could guide clinical management; yet recent systematic reviews show this has not been attempted. This was a prospective cross-sectional study of participants with CLBP (n = 21) and age-, sex- and height-matched pain-free controls (n = 21). Nervous system, lumbar spinal tissue and psychosocial factors were collected. Dimensionality reduction was followed by fuzzy c-means clustering to determine sub-groups. Machine learning models (Support Vector Machine, k-Nearest Neighbour, Naïve Bayes and Random Forest) were used to determine the accuracy of classification to sub-groups. The primary analysis showed that four factors (cognitive function, depressive symptoms, general self-efficacy and anxiety symptoms) and two clusters (normal versus impaired psychosocial profiles) optimally classified participants. The error rates in classification models ranged from 4.2 to 14.2% when only CLBP patients were considered and increased to 24.2 to 37.5% when pain-free controls were added. This data-driven pilot study classified participants with CLBP into sub-groups, primarily based on psychosocial factors. This contributes to the literature as it was the first study to evaluate data-driven machine learning CLBP classification based on nervous system, lumbar spinal tissue and psychosocial factors. Future studies with larger sample sizes should validate these findings.

Exploratory analysis of 5 supervised machine learning models for predicting the efficacy of the endogenous pain inhibitory pathway in patients with musculoskeletal pain

OBJECTIVES

The identification of factors that influence the efficacy of endogenous pain inhibitory pathways remains challenging due to different protocols and populations. We explored five machine learning (ML) models to estimate the Conditioned Pain Modulation (CPM) efficacy.

DESIGN

Exploratory, cross-sectional design.

SETTING AND PARTICIPANTS

This study was conducted in an outpatient setting and included 311 patients with musculoskeletal pain.

METHODS

Data collection included sociodemographic, lifestyle, and clinical characteristics. CPM efficacy was calculated by comparing the pressure pain thresholds before and after patients submerged their non-dominant hand in a bucket of cold water (cold-pressure test) (1-4 °C). We developed five ML models: decision tree, random forest, gradient-boosted trees, logistic regression, and support vector machine.

MAIN OUTCOME MEASURES

Model performance were assessed using receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, recall, F1-score, and the Matthews Correlation Coefficient (MCC). To interpret and explain the predictions, we used SHapley Additive explanation values and Local Interpretable Model-Agnostic Explanations.

RESULTS

The XGBoost model presented the highest performance with an accuracy of 0.81 (95% CI = 0.73 to 0.89), F1 score of 0.80 (95% CI = 0.74 to 0.87), AUC of 0.81 (95% CI: 0.74 to 0.88), MCC of 0.61, and Kappa of 0.61. The model was influenced by duration of pain, fatigue, physical activity, and the number of painful areas.

CONCLUSIONS

XGBoost showed potential in predicting the CPM efficacy in patients with musculoskeletal pain on our dataset. Further research is needed to ensure the external validity and clinical utility of this model.

Machine learning analysis predicts a person's sex based on mechanical but not thermal pain thresholds

Sex differences in pain perception have been extensively studied, but precision medicine applications such as sex-specific pain pharmacology have barely progressed beyond proof-of-concept. A data set of pain thresholds to mechanical (blunt and punctate pressure) and thermal (heat and cold) stimuli applied to non-sensitized and sensitized (capsaicin, menthol) forearm skin of 69 male and 56 female healthy volunteers was analyzed for data structures contingent with the prior sex structure using unsupervised and supervised approaches. A working hypothesis that the relevance of sex differences could be approached via reversibility of the association, i.e., sex should be identifiable from pain thresholds, was verified with trained machine learning algorithms that could infer a person's sex in a 20% validation sample not seen to the algorithms during training, with balanced accuracy of up to 79%. This was only possible with thresholds for mechanical stimuli, but not for thermal stimuli or sensitization responses, which were not sufficient to train an algorithm that could assign sex better than by guessing or when trained with nonsense (permuted) information. This enabled the translation to the molecular level of nociceptive targets that convert mechanical but not thermal information into signals interpreted as pain, which could eventually be used for pharmacological precision medicine approaches to pain. By exploiting a key feature of machine learning, which allows for the recognition of data structures and the reduction of information to the minimum relevant, experimental human pain data could be characterized in a way that incorporates "non" logic that could be translated directly to the molecular pharmacological level, pointing toward sex-specific precision medicine for pain.

Experimental Exploration of Multilevel Human Pain Assessment Using Blood Volume Pulse (BVP) Signals

Critically ill patients often lack cognitive or communicative functions, making it challenging to assess their pain levels using self-reporting mechanisms. There is an urgent need for an accurate system that can assess pain levels without relying on patient-reported information. Blood volume pulse (BVP) is a relatively unexplored physiological measure with the potential to assess pain levels. This study aims to develop an accurate pain intensity classification system based on BVP signals through comprehensive experimental analysis. Twenty-two healthy subjects participated in the study, in which we analyzed the classification performance of BVP signals for various pain intensities using time, frequency, and morphological features through fourteen different machine learning classifiers. Three experiments were conducted using leave-one-subject-out cross-validation to better examine the hidden signatures of BVP signals for pain level classification. The results of the experiments showed that BVP signals combined with machine learning can provide an objective and quantitative evaluation of pain levels in clinical settings. Specifically, no pain and high pain BVP signals were classified with 96.6% accuracy, 100% sensitivity, and 91.6% specificity using a combination of time, frequency, and morphological features with artificial neural networks (ANNs). The classification of no pain and low pain BVP signals yielded 83.3% accuracy using a combination of time and morphological features with the AdaBoost classifier. Finally, the multi-class experiment, which classified no pain, low pain, and high pain, achieved 69% overall accuracy using a combination of time and morphological features with ANN. In conclusion, the experimental results suggest that BVP signals combined with machine learning can offer an objective and reliable assessment of pain levels in clinical settings.

Artificial Intelligence in Musculoskeletal Conditions

Artificial intelligence (AI) refers to computer capabilities that resemble human intelligence. AI implies the ability to learn and perform tasks that have not been specifically programmed. Moreover, it is an iterative process involving the ability of computerized systems to capture information, transform it into knowledge, and process it to produce adaptive changes in the environment. A large labeled database is needed to train the AI system and generate a robust algorithm. Otherwise, the algorithm cannot be applied in a generalized way. AI can facilitate the interpretation and acquisition of radiological images. In addition, it can facilitate the detection of trauma injuries and assist in orthopedic and rehabilitative processes. The applications of AI in musculoskeletal conditions are promising and are likely to have a significant impact on the future management of these patients.

Using artificial intelligence to improve pain assessment and pain management: a scoping review

CONTEXT

Over 20% of US adults report they experience pain on most days or every day. Uncontrolled pain has led to increased healthcare utilization, hospitalization, emergency visits, and financial burden. Recognizing, assessing, understanding, and treating pain using artificial intelligence (AI) approaches may improve patient outcomes and healthcare resource utilization. A comprehensive synthesis of the current use and outcomes of AI-based interventions focused on pain assessment and management will guide the development of future research.

OBJECTIVES

This review aims to investigate the state of the research on AI-based interventions designed to improve pain assessment and management for adult patients. We also ascertain the actual outcomes of Al-based interventions for adult patients.

METHODS

The electronic databases searched include Web of Science, CINAHL, PsycINFO, Cochrane CENTRAL, Scopus, IEEE Xplore, and ACM Digital Library. The search initially identified 6946 studies. After screening, 30 studies met the inclusion criteria. The Critical Appraisals Skills Programme was used to assess study quality.

RESULTS

This review provides evidence that machine learning, data mining, and natural language processing were used to improve efficient pain recognition and pain assessment, analyze self-reported pain data, predict pain, and help clinicians and patients to manage chronic pain more effectively.

CONCLUSIONS

Findings from this review suggest that using AI-based interventions has a positive effect on pain recognition, pain prediction, and pain self-management; however, most reports are only pilot studies. More pilot studies with physiological pain measures are required before these approaches are ready for large clinical trial.

Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia

BACKGROUND

Postoperative nausea and vomiting (PONV) is a still highly relevant problem and is known to be a distressing side effect in patients. The aim of this study was to develop a machine learning model to predict PONV up to 24 h with fentanyl-based intravenous patient-controlled analgesia (IV-PCA).

METHODS

From July 2019 and July 2020, data from 2,149 patients who received fentanyl-based IV-PCA for analgesia after non-cardiac surgery under general anesthesia were applied to develop predictive models. The rates of PONV at 1 day after surgery were measured according to patient characteristics as well as anesthetic, surgical, or PCA-related factors. All statistical analyses and computations were performed using the R software.

RESULTS

A total of 2,149 patients were enrolled in this study, 337 of whom (15.7%) experienced PONV. After applying the machine-learning algorithm and Apfel model to the test dataset to predict PONV, we found that the area under the receiver operating characteristic curve using logistic regression was 0.576 (95% confidence interval [CI], 0.520-0.633), k-nearest neighbor was 0.597 (95% CI, 0.537-0.656), decision tree was 0.561 (95% CI, 0.498-0.625), random forest was 0.610 (95% CI, 0.552-0.668), gradient boosting machine was 0.580 (95% CI, 0.520-0.639), support vector machine was 0.649 (95% CI, 0.592-0.707), artificial neural network was 0.686 (95% CI, 0.630-0.742), and Apfel model was 0.643 (95% CI, 0.596-0.690).

CONCLUSIONS

We developed and validated machine learning models for predicting PONV in the first 24 h. The machine learning model showed better performance than the Apfel model in predicting PONV.

Artificial intelligence and machine learning in pain research: a data scientometric analysis

The collection of increasing amounts of data in health care has become relevant for pain therapy and research. This poses problems for analyses with classical approaches, which is why artificial intelligence (AI) and machine learning (ML) methods are being included into pain research. The current literature on AI and ML in the context of pain research was automatically searched and manually curated. Common machine learning methods and pain settings covered were evaluated. Further focus was on the origin of the publication and technical details, such as the included sample sizes of the studies analyzed with ML. Machine learning was identified in 475 publications from 18 countries, with 79% of the studies published since 2019. Most addressed pain conditions included low back pain, musculoskeletal disorders, osteoarthritis, neuropathic pain, and inflammatory pain. Most used ML algorithms included random forests and support vector machines; however, deep learning was used when medical images were involved in the diagnosis of painful conditions. Cohort sizes ranged from 11 to 2,164,872, with a mode at n = 100; however, deep learning required larger data sets often only available from medical images. Artificial intelligence and ML, in particular, are increasingly being applied to pain-related data. This report presents application examples and highlights advantages and limitations, such as the ability to process complex data, sometimes, but not always, at the cost of big data requirements or black-box decisions.

Classification of elderly pain severity from automated video clip facial action unit analysis: A study from a Thai data repository

Data from 255 Thais with chronic pain were collected at Chiang Mai Medical School Hospital. After the patients self-rated their level of pain, a smartphone camera was used to capture faces for 10 s at a one-meter distance. For those unable to self-rate, a video recording was taken immediately after the move that causes the pain. The trained assistant rated each video clip for the pain assessment in advanced dementia (PAINAD). The pain was classified into three levels: mild, moderate, and severe. OpenFace^© was used to convert the video clips into 18 facial action units (FAUs). Five classification models were used, including logistic regression, multilayer perception, naïve Bayes, decision tree, k-nearest neighbors (KNN), and support vector machine (SVM). Out of the models that only used FAU described in the literature (FAU 4, 6, 7, 9, 10, 25, 26, 27, and 45), multilayer perception is the most accurate, at 50%. The SVM model using FAU 1, 2, 4, 7, 9, 10, 12, 20, 25, and 45, and gender had the best accuracy of 58% among the machine learning selection features. Our open-source experiment for automatically analyzing video clips for FAUs is not robust for classifying pain in the elderly. The consensus method to transform facial recognition algorithm values comparable to the human ratings, and international good practice for reciprocal sharing of data may improve the accuracy and feasibility of the machine learning's facial pain rater.

Analysis of combined clinical and diffusion basis spectrum imaging metrics to predict the outcome of chronic cervical spondylotic myelopathy following cervical decompression surgery

OBJECTIVE

Cervical spondylotic myelopathy (CSM) is the most common cause of chronic spinal cord injury, a significant public health problem. Diffusion tensor imaging (DTI) is a neuroimaging technique widely used to assess CNS tissue pathology and is increasingly used in CSM. However, DTI lacks the needed accuracy, precision, and recall to image pathologies of spinal cord injury as the disease progresses. Thus, the authors used diffusion basis spectrum imaging (DBSI) to delineate white matter injury more accurately in the setting of spinal cord compression. It was hypothesized that the profiles of multiple DBSI metrics can serve as imaging outcome predictors to accurately predict a patient's response to therapy and his or her long-term prognosis. This hypothesis was tested by using DBSI metrics as input features in a support vector machine (SVM) algorithm.

METHODS

Fifty patients with CSM and 20 healthy controls were recruited to receive diffusion-weighted MRI examinations. All spinal cord white matter was identified as the region of interest (ROI). DBSI and DTI metrics were extracted from all voxels in the ROI and the median value of each patient was used in analyses. An SVM with optimized hyperparameters was trained using clinical and imaging metrics separately and collectively to predict patient outcomes. Patient outcomes were determined by calculating changes between pre- and postoperative modified Japanese Orthopaedic Association (mJOA) scale scores.

RESULTS

Accuracy, precision, recall, and F1 score were reported for each SVM iteration. The highest performance was observed when a combination of clinical and DBSI metrics was used to train an SVM. When assessing patient outcomes using mJOA scale scores, the SVM trained with clinical and DBSI metrics achieved accuracy and an area under the curve of 88.1% and 0.95, compared with 66.7% and 0.65, respectively, when clinical and DTI metrics were used together.

CONCLUSIONS

The accuracy and efficacy of the SVM incorporating clinical and DBSI metrics show promise for clinical applications in predicting patient outcomes. These results suggest that DBSI metrics, along with the clinical presentation, could serve as a surrogate in prognosticating outcomes of patients with CSM.

Chronic back pain sub-grouped via psychosocial, brain and physical factors using machine learning

Chronic back pain (CBP) is heterogenous and identifying sub-groups could improve clinical decision making. Machine learning can build upon prior sub-grouping approaches by using a data-driven approach to overcome clinician subjectivity, however, only binary classification of pain versus no-pain has been attempted to date. In our cross-sectional study, age- and sex-matched participants with CBP (n = 4156) and pain-free controls (n = 14,927) from the UkBioBank were included. We included variables of body mass index, depression, loneliness/social isolation, grip strength, brain grey matter volumes and functional connectivity. We used fuzzy c-means clustering to derive CBP sub-groups and Support Vector Machine (SVM), Naïve Bayes, k-Nearest Neighbour (kNN) and Random Forest classifiers to determine classification accuracy. We showed that two variables (loneliness/social isolation and depression) and five clusters were optimal for creating sub-groups of CBP individuals. Classification accuracy was greater than 95% for when CBP sub-groups were assessed only, while misclassification in CBP sub-groups increased to 35-53% across classifiers when pain-free controls were added. We showed that individuals with CBP could sub-grouped and accurately classified. Future research should optimise variables by including specific spinal, psychosocial and nervous system measures associated with CBP to create more robust sub-groups that are discernible from pain-free controls.

Machine learning versus logistic regression for prognostic modelling in individuals with non-specific neck pain

PURPOSE

Prognostic models play an important clinical role in the clinical management of neck pain disorders. No study has compared the performance of modern machine learning (ML) techniques, against more traditional regression techniques, when developing prognostic models in individuals with neck pain.

METHODS

A total of 3001 participants suffering from neck pain were included into a clinical registry database. Three dichotomous outcomes of a clinically meaningful improvement in neck pain, arm pain, and disability at 3 months follow-up were used. There were 26 predictors included, five numeric and 21 categorical. Seven modelling techniques were used (logistic regression, least absolute shrinkage and selection operator [LASSO], gradient boosting [Xgboost], K nearest neighbours [KNN], support vector machine [SVM], random forest [RF], and artificial neural networks [ANN]). The primary measure of model performance was the area under the receiver operator curve (AUC) of the validation set.

RESULTS

The ML algorithm with the greatest AUC for predicting arm pain (AUC = 0.765), neck pain (AUC = 0.726), and disability (AUC = 0.703) was Xgboost. The improvement in classification AUC from stepwise logistic regression to the best performing machine learning algorithms was 0.081, 0.103, and 0.077 for predicting arm pain, neck pain, and disability, respectively.

CONCLUSION

The improvement in prediction performance between ML and logistic regression methods in the present study, could be due to the potential greater nonlinearity between baseline predictors and clinical outcome. The benefit of machine learning in prognostic modelling may be dependent on factors like sample size, variable type, and disease investigated.

A machine learning approach for the identification of kinematic biomarkers of chronic neck pain during single- and dual-task gait

BACKGROUND

Changes in gait characteristics have been reported in people with chronic neck pain (CNP).

RESEARCH QUESTION

Can we classify people with and without CNP by training machine learning models with Inertial Measurement Units (IMU)-based gait kinematic data?

METHODS

Eighteen asymptomatic individuals and 21 participants with CNP were recruited for the study and performed two gait trajectories, (1) linear walking with their head straight (single-task) and (2) linear walking with continuous head-rotation (dual-task). Kinematic data were recorded from three IMU sensors attached to the forehead, upper thoracic spine (T1), and lower thoracic spine (T12). Temporal and spectral features were extracted to generate the dataset for both single- and dual-task gait. To evaluate the most significant features and simultaneously reduce the dataset size, the Neighbourhood Component Analysis (NCA) method was utilized. Three supervised models were applied, including K-Nearest Neighbour, Support Vector Machine, and Linear Discriminant Analysis to test the performance of the most important temporal and spectral features.

RESULTS

The performance of all classifiers increased after the implementation of NCA. The best performance was achieved by NCA-Support Vector Machine with an accuracy of 86.85%, specificity of 83.30%, and sensitivity of 92.85% during the dual-task gait using only nine features.

SIGNIFICANCE

The results present a data-driven approach and machine learning-based methods to identify test conditions and features from high-dimensional data obtained during gait for the classification of people with and without CNP.

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.

Assessing Pain Research: A Narrative Review of Emerging Pain Methods, Their Technosocial Implications, and Opportunities for Multidisciplinary Approaches

Pain research traverses many disciplines and methodologies. Yet, despite our understanding and field-wide acceptance of the multifactorial essence of pain as a sensory perception, emotional experience, and biopsychosocial condition, pain scientists and practitioners often remain siloed within their domain expertise and associated techniques. The context in which the field finds itself today-with increasing reliance on digital technologies, an on-going pandemic, and continued disparities in pain care-requires new collaborations and different approaches to measuring pain. Here, we review the state-of-the-art in human pain research, summarizing emerging practices and cutting-edge techniques across multiple methods and technologies. For each, we outline foreseeable technosocial considerations, reflecting on implications for standards of care, pain management, research, and societal impact. Through overviewing alternative data sources and varied ways of measuring pain and by reflecting on the concerns, limitations, and challenges facing the field, we hope to create critical dialogues, inspire more collaborations, and foster new ideas for future pain research methods.

Machine Learning and Pathway Analysis-Based Discovery of Metabolomic Markers Relating to Chronic Pain Phenotypes

Recent scientific evidence suggests that chronic pain phenotypes are reflected in metabolomic changes. However, problems associated with chronic pain, such as sleep disorders or obesity, may complicate the metabolome pattern. Such a complex phenotype was investigated to identify common metabolomics markers at the interface of persistent pain, sleep, and obesity in 71 men and 122 women undergoing tertiary pain care. They were examined for patterns in d = 97 metabolomic markers that segregated patients with a relatively benign pain phenotype (low and little bothersome pain) from those with more severe clinical symptoms (high pain intensity, more bothersome pain, and co-occurring problems such as sleep disturbance). Two independent lines of data analysis were pursued. First, a data-driven supervised machine learning-based approach was used to identify the most informative metabolic markers for complex phenotype assignment. This pointed primarily at adenosine monophosphate (AMP), asparagine, deoxycytidine, glucuronic acid, and propionylcarnitine, and secondarily at cysteine and nicotinamide adenine dinucleotide (NAD) as informative for assigning patients to clinical pain phenotypes. After this, a hypothesis-driven analysis of metabolic pathways was performed, including sleep and obesity. In both the first and second line of analysis, three metabolic markers (NAD, AMP, and cysteine) were found to be relevant, including metabolic pathway analysis in obesity, associated with changes in amino acid metabolism, and sleep problems, associated with downregulated methionine metabolism. Taken together, present findings provide evidence that metabolomic changes associated with co-occurring problems may play a role in the development of severe pain. Co-occurring problems may influence each other at the metabolomic level. Because the methionine and glutathione metabolic pathways are physiologically linked, sleep problems appear to be associated with the first metabolic pathway, whereas obesity may be associated with the second.

Machine-Learning Analysis of Serum Proteomics in Neuropathic Pain after Nerve Injury in Breast Cancer Surgery Points at Chemokine Signaling via SIRT2 Regulation

Background: Persistent postsurgical neuropathic pain (PPSNP) can occur after intraoperative damage to somatosensory nerves, with a prevalence of 29–57% in breast cancer surgery. Proteomics is an active research field in neuropathic pain and the first results support its utility for establishing diagnoses or finding therapy strategies. Methods: 57 women (30 non-PPSNP/27 PPSNP) who had experienced a surgeon-verified intercostobrachial nerve injury during breast cancer surgery, were examined for patterns in 74 serum proteomic markers that allowed discrimination between subgroups with or without PPSNP. Serum samples were obtained both before and after surgery. Results: Unsupervised data analyses, including principal component analysis and self-organizing maps of artificial neurons, revealed patterns that supported a data structure consistent with pain-related subgroup (non-PPSPN vs. PPSNP) separation. Subsequent supervised machine learning-based analyses revealed 19 proteins (CD244, SIRT2, CCL28, CXCL9, CCL20, CCL3, IL.10RA, MCP.1, TRAIL, CCL25, IL10, uPA, CCL4, DNER, STAMPB, CCL23, CST5, CCL11, FGF.23) that were informative for subgroup separation. In cross-validated training and testing of six different machine-learned algorithms, subgroup assignment was significantly better than chance, whereas this was not possible when training the algorithms with randomly permuted data or with the protein markers not selected. In particular, sirtuin 2 emerged as a key protein, presenting both before and after breast cancer treatments in the PPSNP compared with the non-PPSNP subgroup. Conclusions: The identified proteins play important roles in immune processes such as cell migration, chemotaxis, and cytokine-signaling. They also have considerable overlap with currently known targets of approved or investigational drugs. Taken together, several lines of unsupervised and supervised analyses pointed to structures in serum proteomics data, obtained before and after breast cancer surgery, that relate to neuroinflammatory processes associated with the development of neuropathic pain after an intraoperative nerve lesion.

Improving Pain Assessment using Vital Signs and Pain Medication for patients with Sickle Cell Disease: Retrospective Study (Preprint)

Background

Sickle cell disease (SCD) is the most common inherited blood disorder affecting millions of people worldwide. Most patients with SCD experience repeated, unpredictable episodes of severe pain. These pain episodes are the leading cause of emergency department visits among patients with SCD and may last for several weeks. Arguably, the most challenging aspect of treating pain episodes in SCD is assessing and interpreting a patient’s pain intensity level.

Objective

This study aims to learn deep feature representations of subjective pain trajectories using objective physiological signals collected from electronic health records.

Methods

This study used electronic health record data collected from 496 Duke University Medical Center participants over 5 consecutive years. Each record contained measures for 6 vital signs and the patient’s self-reported pain score, with an ordinal range from 0 (no pain) to 10 (severe and unbearable pain). We also extracted 3 features related to medication: medication type, medication status (given or applied, or missed or removed or due), and total medication dosage (mg/mL). We used variational autoencoders for representation learning and designed machine learning classification algorithms to build pain prediction models. We evaluated our results using an accuracy and confusion matrix and visualized the qualitative data representations.

Results

We designed a classification model using raw data and deep representational learning to predict subjective pain scores with average accuracies of 82.8%, 70.6%, 49.3%, and 47.4% for 2-point, 4-point, 6-point, and 11-point pain ratings, respectively. We observed that random forest classification models trained on deep represented features outperformed models trained on unrepresented data for all pain rating scales. We observed that at varying Likert scales, our models performed better when provided with medication data along with vital signs data. We visualized the data representations to understand the underlying latent representations, indicating neighboring representations for similar pain scores with a higher resolution of pain ratings.

Conclusions

Our results demonstrate that medication information (the type of medication, total medication dosage, and whether the medication was given or missed) can significantly improve subjective pain prediction modeling compared with modeling with only vital signs. This study shows promise in data-driven estimated pain scores that will help clinicians with additional information about the patient’s condition, in addition to the patient’s self-reported pain scores.

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.

Predictors of Sickness Absence in a Clinical Population With Chronic Pain

Chronic pain-related sickness absence is an enormous socioeconomic burden globally. Optimized interventions are reliant on a lucid understanding of the distribution of social insurance benefits and their predictors. This register-based observational study analyzed data for a 7-year period from a population-representative sample of 44,241 chronic pain patients eligible for interdisciplinary treatment (IDT) at specialist clinics. Sequence analysis was used to describe the sickness absence over the complete period and to separate the patients into subgroups based on their social insurance benefits over the final 2 years. The predictive performance of features from various domains was then explored with machine learning-based modeling in a nested cross-validation procedure. Our results showed that patients on sickness absence increased from 17% 5 years before to 48% at the time of the IDT assessment, and then decreased to 38% at the end of follow-up. Patients were divided into 3 classes characterized by low sickness absence, sick leave, and disability pension, with eight predictors of class membership being identified. Sickness absence history was the strongest predictor of future sickness absence, while other predictors included a 2008 policy, age, confidence in recovery, and geographical location. Information on these features could guide personalized intervention in the specialized healthcare. PERSPECTIVE: This study describes sickness absence in patients who visited a Swedish pain specialist interdisciplinary treatment clinic during the period 2005 to 2016. Predictors of future sickness absence are also identified that should be considered when adapting IDT programs to the patient's needs.

A method to quantify autonomic nervous system function in healthy, able-bodied individuals

BACKGROUND

The autonomic nervous system (ANS) maintains physiological homeostasis in various organ systems via parasympathetic and sympathetic branches. ANS function is altered in common diffuse and focal conditions and heralds the beginning of environmental and disease stresses. Reliable, sensitive, and quantitative biomarkers, first defined in healthy participants, could discriminate among clinically useful changes in ANS function. This framework combines controlled autonomic testing with feature extraction during physiological responses.

METHODS

Twenty-one individuals were assessed in two morning and two afternoon sessions over two weeks. Each session included five standard clinical tests probing autonomic function: squat test, cold pressor test, diving reflex test, deep breathing, and Valsalva maneuver. Noninvasive sensors captured continuous electrocardiography, blood pressure, breathing, electrodermal activity, and pupil diameter. Heart rate, heart rate variability, mean arterial pressure, electrodermal activity, and pupil diameter responses to the perturbations were extracted, and averages across participants were computed. A template matching algorithm calculated scaling and stretching features that optimally fit the average to an individual response. These features were grouped based on test and modality to derive sympathetic and parasympathetic indices for this healthy population.

RESULTS

A significant positive correlation (p = 0.000377) was found between sympathetic amplitude response and body mass index. Additionally, longer duration and larger amplitude sympathetic and longer duration parasympathetic responses occurred in afternoon testing sessions; larger amplitude parasympathetic responses occurred in morning sessions.

CONCLUSIONS

These results demonstrate the robustness and sensitivity of an algorithmic approach to extract multimodal responses from standard tests. This novel method of quantifying ANS function can be used for early diagnosis, measurement of disease progression, or treatment evaluation.

TRIAL REGISTRATION

This study registered with Clinicaltrials.gov , identifier NCT04100486 . Registered September 24, 2019, https://www.clinicaltrials.gov/ct2/show/NCT04100486 .

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.

Predicting pain among female survivors of recent interpersonal violence: A proof-of-concept machine-learning approach

Interpersonal violence (IPV) is highly prevalent in the United States and is a major public health problem. The emergence and/or worsening of chronic pain are known sequelae of IPV; however, not all those who experience IPV develop chronic pain. To mitigate its development, it is critical to identify the factors that are associated with increased risk of pain after IPV. This proof-of-concept study used machine-learning strategies to predict pain severity and interference in 47 young women, ages 18 to 30, who experienced an incident of IPV (i.e., physical and/or sexual assault) within three months of their baseline assessment. Young women are more likely than men to experience IPV and to subsequently develop posttraumatic stress disorder (PTSD) and chronic pain. Women completed a comprehensive assessment of theory-driven cognitive and neurobiological predictors of pain severity and pain-related interference (e.g., pain, coping, disability, psychiatric diagnosis/symptoms, PTSD/trauma, executive function, neuroendocrine, and physiological stress response). Gradient boosting machine models were used to predict symptoms of pain severity and pain-related interference across time (Baseline, 1-,3-,6- follow-up assessments). Models showed excellent predictive performance for pain severity and adequate predictive performance for pain-related interference. This proof-of-concept study suggests that machine-learning approaches are a useful tool for identifying predictors of pain development in survivors of recent IPV. Baseline measures of pain, family life impairment, neuropsychological function, and trauma history were of greatest importance in predicting pain and pain-related interference across a 6-month follow-up period. Present findings support the use of machine-learning techniques in larger studies of post-IPV pain development and highlight theory-driven predictors that could inform the development of targeted early intervention programs. However, these results should be replicated in a larger dataset with lower levels of missing data.

Relative Performance of Machine Learning and Linear Regression in Predicting Quality of Life and Academic Performance of School Children in Norway: Data Analysis of a Quasi-Experimental Study

BACKGROUND

Machine learning techniques are increasingly being applied in health research. It is not clear how useful these approaches are for modeling continuous outcomes. Child quality of life is associated with parental socioeconomic status and physical activity and may be associated with aerobic fitness and strength. It is unclear whether diet or academic performance is associated with quality of life.

OBJECTIVE

The purpose of this study was to compare the predictive performance of machine learning techniques with that of linear regression in examining the extent to which continuous outcomes (physical activity, aerobic fitness, muscular strength, diet, and parental education) are predictive of academic performance and quality of life and whether academic performance and quality of life are associated.

METHODS

We modeled data from children attending 9 schools in a quasi-experimental study. We split data randomly into training and validation sets. Curvilinear, nonlinear, and heteroscedastic variables were simulated to examine the performance of machine learning techniques compared to that of linear models, with and without imputation.

RESULTS

We included data for 1711 children. Regression models explained 24% of academic performance variance in the real complete-case validation set, and up to 15% in quality of life. While machine learning techniques explained high proportions of variance in training sets, in validation, machine learning techniques explained approximately 0% of academic performance and 3% to 8% of quality of life. With imputation, machine learning techniques improved to 15% for academic performance. Machine learning outperformed regression for simulated nonlinear and heteroscedastic variables. The best predictors of academic performance in adjusted models were the child's mother having a master-level education (P<.001; β=1.98, 95% CI 0.25 to 3.71), increased television and computer use (P=.03; β=1.19, 95% CI 0.25 to 3.71), and dichotomized self-reported exercise (P=.001; β=2.47, 95% CI 1.08 to 3.87). For quality of life, self-reported exercise (P<.001; β=1.09, 95% CI 0.53 to 1.66) and increased television and computer use (P=.002; β=-0.95, 95% CI -1.55 to -0.36) were the best predictors. Adjusted academic performance was associated with quality of life (P=.02; β=0.12, 95% CI 0.02 to 0.22).

CONCLUSIONS

Linear regression was less prone to overfitting and outperformed commonly used machine learning techniques. Imputation improved the performance of machine learning, but not sufficiently to outperform regression. Machine learning techniques outperformed linear regression for modeling nonlinear and heteroscedastic relationships and may be of use in such cases. Regression with splines performed almost as well in nonlinear modeling. Lifestyle variables, including physical exercise, television and computer use, and parental education are predictive of academic performance or quality of life. Academic performance is associated with quality of life after adjusting for lifestyle variables and may offer another promising intervention target to improve quality of life in children.

Automated Pain Assessment in Children using Electrodermal Activity and Video Data Fusion via Machine Learning

Pain assessment in children continues to challenge clinicians and researchers, as subjective experiences of pain require inference through observable behaviors, both involuntary and deliberate. The presented approach supplements the subjective self-report-based method by fusing electrodermal activity (EDA) recordings with video facial expressions to develop an objective pain assessment metric. Such an approach is specifically important for assessing pain in children who are not capable of providing accurate self-pain reports, requiring nonverbal pain assessment. We demonstrate the performance of our approach using data recorded from children in post-operative recovery following laparoscopic appendectomy. We examined separately and combined the usefulness of EDA and video facial expression data as predictors of childrens self-reports of pain following surgery through recovery. Findings indicate that EDA and facial expression data independently provide above chance sensitivities and specificities, but their fusion for classifying clinically significant pain vs. clinically nonsignificant pain achieved substantial improvement, yielding 90.91% accuracy, with 100% sensitivity and 81.82% specificity. The multimodal measures capitalize upon different features of the complex pain response. Thus, this paper presents both evidence for the utility of a weighted maximum likelihood algorithm as a novel feature selection method for EDA and video facial expression data and an accurate and objective automated classification algorithm capable of discriminating clinically significant pain from clinically nonsignificant pain in children.

Machine Learning in Chronic Pain Research: A Scoping Review

Given the high prevalence and associated cost of chronic pain, it has a significant impact on individuals and society. Improvements in the treatment and management of chronic pain may increase patients’ quality of life and reduce societal costs. In this paper, we evaluate state-of-the-art machine learning approaches in chronic pain research. A literature search was conducted using the PubMed, IEEE Xplore, and the Association of Computing Machinery (ACM) Digital Library databases. Relevant studies were identified by screening titles and abstracts for keywords related to chronic pain and machine learning, followed by analysing full texts. Two hundred and eighty-seven publications were identified in the literature search. In total, fifty-three papers on chronic pain research and machine learning were reviewed. The review showed that while many studies have emphasised machine learning-based classification for the diagnosis of chronic pain, far less attention has been paid to the treatment and management of chronic pain. More research is needed on machine learning approaches to the treatment, rehabilitation, and self-management of chronic pain. As with other chronic conditions, patient involvement and self-management are crucial. In order to achieve this, patients with chronic pain need digital tools that can help them make decisions about their own treatment and care.

A common model for the breathlessness experience across cardiorespiratory disease

Chronic breathlessness occurs across many different conditions, often independently of disease severity. Yet, despite being strongly linked to adverse outcomes, the consideration of chronic breathlessness as a stand-alone therapeutic target remains limited. Here we use data-driven techniques to identify and confirm the stability of underlying features (factors) driving breathlessness across different cardiorespiratory diseases. Questionnaire data on 182 participants with main diagnoses of asthma (21.4%), COPD (24.7%), heart failure (19.2%), idiopathic pulmonary fibrosis (18.7%), other interstitial lung disease (2.7%), and "other diagnoses" (13.2%) were entered into an exploratory factor analysis (EFA). Participants were stratified based on their EFA factor scores. We then examined model stability using 6-month follow-up data and established the most compact set of measures describing the breathlessness experience. In this dataset, we have identified four stable factors that underlie the experience of breathlessness. These factors were assigned the following descriptive labels: 1) body burden, 2) affect/mood, 3) breathing burden and 4) anger/frustration. Stratifying patients by their scores across the four factors revealed two groups corresponding to high and low burden. These two groups were not related to the primary disease diagnosis and remained stable after 6 months. In this work, we identified and confirmed the stability of underlying features of breathlessness. Previous work in this domain has been largely limited to single-diagnosis patient groups without subsequent re-testing of model stability. This work provides further evidence supporting disease independent approaches to assess breathlessness.

Can subjective pain be inferred from objective physiological data? Evidence from patients with sickle cell disease

Patients with sickle cell disease (SCD) experience lifelong struggles with both chronic and acute pain, often requiring medical interventMaion. Pain can be managed with medications, but dosages must balance the goal of pain mitigation against the risks of tolerance, addiction and other adverse effects. Setting appropriate dosages requires knowledge of a patient’s subjective pain, but collecting pain reports from patients can be difficult for clinicians and disruptive for patients, and is only possible when patients are awake and communicative. Here we investigate methods for estimating SCD patients’ pain levels indirectly using vital signs that are routinely collected and documented in medical records. Using machine learning, we develop both sequential and non-sequential probabilistic models that can be used to infer pain levels or changes in pain from sequences of these physiological measures. We demonstrate that these models outperform null models and that objective physiological data can be used to inform estimates for subjective pain.

Understanding subjective human pain remains a major challenge. If objective data could be used in place of reported pain levels, it could reduce patient burdens and enable the collection of much larger data sets that could deepen our understanding of causes of pain and allow for accurate forecasting and more effective pain management. Here we apply two machine learning approaches to data from patients with sickle cell disease, who often experience debilitating pain crises. Using vital sign data routinely collected in hospital settings including respiratory rate, heart rate, and blood pressure and amidst the real-world challenges of irregular timing, missing data, and inter-patient variation, we demonstrate that these models outperform baseline models in estimating subjective pain, distinguishing between typical and atypical pain levels, and detecting changes in pain. Once trained, these types of models could be used to improve pain estimates in real time in the absence of direct pain reports.

Prioritizing Pain-Associated Targets with Machine Learning

While hundreds of genes have been associated with pain, much of the molecular mechanisms of pain remain unknown. As a result, current analgesics are limited to few clinically validated targets. Here, we trained a machine learning (ML) ensemble model to predict new targets for 17 categories of pain. The model utilizes features from transcriptomics, proteomics, and gene ontology to prioritize targets for modulating pain. We focused on identifying novel G-protein-coupled receptors (GPCRs), ion channels, and protein kinases because these proteins represent the most successful drug target families. The performance of the model to predict novel pain targets is 0.839 on average based on AUROC, while the predictions for arthritis had the highest accuracy (AUROC = 0.929). The model predicts hundreds of novel targets for pain; for example, GPR132 and GPR109B are highly ranked GPCRs for rheumatoid arthritis. Overall, gene-pain association predictions cluster into three groups that are enriched for cytokine, calcium, and GABA-related cell signaling pathways. These predictions can serve as a foundation for future experimental exploration to advance the development of safer and more effective analgesics.

From 'molecules of life' to new therapeutic approaches, an evolution marked by the advent of artificial intelligence: the cases of chronic pain and neuropathic disorders

The large families of the molecules of life are at the origin of the discovery of new compounds with which to treat disease. The arrival of artificial intelligence (AI) has considerably modified the search for innovative bioactive drugs and their therapeutic applications. Conventional approaches at different organizational research levels have emerged and, thus, AI associated with gene and cell therapies could supplant conventional pharmacotherapy and facilitate the diagnosis of pathologies. Using the examples of chronic pain and neuropathic disorders, which affect a large number of patients, I illustrate here how AI could generate new therapeutic approaches, why some compounds are seen as recreational drugs and others as medicinal drugs, and why, in some countries, psychedelic drugs are considered as potential therapeutic drugs but not in others.

Machine-learning-based knowledge discovery in rheumatoid arthritis-related registry data to identify predictors of persistent pain

Early detection of patients with chronic diseases at risk of developing persistent pain is clinically desirable for timely initiation of multimodal therapies. Quality follow-up registries may provide the necessary clinical data; however, their design is not focused on a specific research aim, which poses challenges on the data analysis strategy. Here, machine-learning was used to identify early parameters that provide information about a future development of persistent pain in rheumatoid arthritis (RA). Data of 288 patients were queried from a registry based on the Swedish Epidemiological Investigation of RA. Unsupervised data analyses identified the following 3 distinct patient subgroups: low-, median-, and high-persistent pain intensity. Next, supervised machine-learning, implemented as random forests followed by computed ABC analysis-based item categorization, was used to select predictive parameters among 21 different demographic, patient-rated, and objective clinical factors. The selected parameters were used to train machine-learned algorithms to assign patients pain-related subgroups (1000 random resamplings, 2/3 training, and 1/3 test data). Algorithms trained with 3-month data of the patient global assessment and health assessment questionnaire provided pain group assignment at a balanced accuracy of 70%. When restricting the predictors to objective clinical parameters of disease severity, swollen joint count and tender joint count acquired at 3 months provided a balanced accuracy of RA of 59%. Results indicate that machine-learning is suited to extract knowledge from data queried from pain- and disease-related registries. Early functional parameters of RA are informative for the development and degree of persistent pain.

Machine learning suggests sleep as a core factor in chronic pain

Patients with chronic pain have complex pain profiles and associated problems. Subgroup analysis can help identify key problems. We used a data-based approach to define pain phenotypes and their most relevant associated problems in 320 patients undergoing tertiary pain management. Unsupervised machine learning analysis of parameters "pain intensity," "number of pain areas," "pain duration," "activity pain interference," and "affective pain interference," implemented as emergent self-organizing maps, identified 3 patient phenotype clusters. Supervised analyses, implemented as different types of decision rules, identified "affective pain interference" and the "number of pain areas" as most relevant for cluster assignment. These appeared 698 and 637 times, respectively, in 1000 cross-validation runs among the most relevant characteristics in an item categorization approach in a computed ABC analysis. Cluster assignment was achieved with a median balanced accuracy of 79.9%, a sensitivity of 74.1%, and a specificity of 87.7%. In addition, among 59 demographic, pain etiology, comorbidity, lifestyle, psychological, and treatment-related variables, sleep problems appeared 638 and 439 times among the most important characteristics in 1000 cross-validation runs where patients were assigned to the 2 extreme pain phenotype clusters. Also important were the parameters "fear of pain," "self-rated poor health," and "systolic blood pressure." Decision trees trained with this information assigned patients to the extreme pain phenotype with an accuracy of 67%. Machine learning suggested sleep problems as key factors in the most difficult pain presentations, therefore deserving priority in the treatment of chronic pain.