A tool for classifying individuals with chronic back pain: using multivariate pattern analysis with functional magnetic resonance imaging data

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.

Functional brain mapping in patients with chronic back pain shows age-related differences

ABSTRACT

Low back pain is the most common pain condition and cause for disability in older adults. Older adults suffering from low back pain are more disabled than their healthy peers, are more predisposed to frailty, and tend to be undertreated. The cause of increased prevalence and severity of this chronic pain condition in older adults is unknown. Here, we draw on accumulating data demonstrating a critical role for brain limbic and sensory circuitries in the emergence and experience of chronic low back pain (CLBP) and the availability of resting-state brain activity data collected at different sites to study how brain activity patterns predictive of CLBP differ between age groups. We apply a data-driven multivariate searchlight analysis to amplitude of low-frequency fluctuation brain maps to classify patients with CLBP with >70% accuracy. We observe that the brain activity pattern including the paracingulate gyrus, insula/secondary somatosensory area, inferior frontal, temporal, and fusiform gyrus predicted CLBP. When separated by age groups, brain patterns predictive of older patients with CLBP showed extensive involvement of limbic brain areas including the ventromedial prefrontal cortex, the nucleus accumbens, and hippocampus, whereas only anterior insula paracingulate and fusiform gyrus predicted CLBP in the younger patients. In addition, we validated the relationships between back pain intensity ratings and CLBP brain activity patterns in an independent data set not included in our initial patterns' identification. Our results are the first to directly address how aging affects the neural signature of CLBP and point to an increased role of limbic brain areas in older patients with CLBP.

Dissociation between individual differences in self-reported pain intensity and underlying fMRI brain activation

Pain is an individual experience. Previous studies have highlighted changes in brain activation and morphology associated with within- and interindividual pain perception. In this study we sought to characterize brain mechanisms associated with between-individual differences in pain in a sample of healthy adolescent and adult participants (N = 101). Here we show that pain ratings varied widely across individuals and that individuals reported changes in pain evoked by small differences in stimulus intensity in a manner congruent with their pain sensitivity, further supporting the utility of subjective reporting as a measure of the true individual experience. Furthermore, brain activation related to interindividual differences in pain was not detected, despite clear sensitivity of the Blood Oxygenation Level-Dependent (BOLD) signal to small differences in noxious stimulus intensities within individuals. These findings suggest fMRI may not be a useful objective measure to infer reported pain intensity.

Pain modalities in the body and brain: Current knowledge and future perspectives

Development and validation of pain biomarkers has become a major issue in pain research. Recent advances in multimodal data acquisition have allowed researchers to gather multivariate and multilevel whole-body measurements in patients with pain conditions, and data analysis techniques such as machine learning have led to novel findings in neural biomarkers for pain. Most studies have focused on the development of a biomarker to predict the severity of pain with high precision and high specificity, however, a similar approach to discriminate different modalities of pain is lacking. Identification of more accurate and specific pain biomarkers will require an in-depth understanding of the modality specificity of pain. In this review, we summarize early and recent findings on the modality specificity of pain in the brain, with a focus on distinct neural activity patterns between chronic clinical and acute experimental pain, direct, social, and vicarious pain, and somatic and visceral pain. We also suggest future directions to improve our current strategy of pain management using our knowledge of modality-specific aspects of pain.

Patients with chronic pain exhibit individually unique cortical signatures of pain encoding

Chronic pain is characterised by an ongoing and fluctuating intensity over time. Here, we investigated how the trajectory of the patients' endogenous pain is encoded in the brain. In repeated functional MRI (fMRI) sessions, 20 patients with chronic back pain and 20 patients with chronic migraine were asked to continuously rate the intensity of their endogenous pain. Linear mixed effects models were used to disentangle cortical processes related to pain intensity and to pain intensity changes. At group level, we found that the intensity of pain in patients with chronic back pain is encoded in the anterior insular cortex, the frontal operculum, and the pons; the change of pain in chronic back pain and chronic migraine patients is mainly encoded in the anterior insular cortex. At the individual level, we identified a more complex picture where each patient exhibited their own signature of endogenous pain encoding. The diversity of the individual cortical signatures of chronic pain encoding results bridge between clinical observations and neuroimaging; they add to the understanding of chronic pain as a complex and multifaceted disease.

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.

Discovery and validation of biomarkers to aid the development of safe and effective pain therapeutics: challenges and opportunities

Pain medication plays an important role in the treatment of acute and chronic pain conditions, but some drugs, opioids in particular, have been overprescribed or prescribed without adequate safeguards, leading to an alarming rise in medication-related overdose deaths. The NIH Helping to End Addiction Long-term (HEAL) Initiative is a trans-agency effort to provide scientific solutions to stem the opioid crisis. One component of the initiative is to support biomarker discovery and rigorous validation in collaboration with industry leaders to accelerate high-quality clinical research into neurotherapeutics and pain. The use of objective biomarkers and clinical trial end points throughout the drug discovery and development process is crucial to help define pathophysiological subsets of pain, evaluate target engagement of new drugs and predict the analgesic efficacy of new drugs. In 2018, the NIH-led Discovery and Validation of Biomarkers to Develop Non-Addictive Therapeutics for Pain workshop convened scientific leaders from academia, industry, government and patient advocacy groups to discuss progress, challenges, gaps and ideas to facilitate the development of biomarkers and end points for pain. The outcomes of this workshop are outlined in this Consensus Statement.

Distinguishing pain from nociception, salience, and arousal: How autonomic nervous system activity can improve neuroimaging tests of specificity

Pain is a subjective, multidimensional experience that is distinct from nociception. A large body of work has focused on whether pain processing is supported by specific, dedicated brain circuits. Despite advances in human neuroscience and neuroimaging analysis, dissociating acute pain from other sensations has been challenging since both pain and non-pain stimuli evoke salience and arousal responses throughout the body and in overlapping brain circuits. In this review, we discuss these challenges and propose that brain-body interactions in pain can be leveraged in order to improve tests for pain specificity. We review brain and bodily responses to pain and nociception and extant efforts toward identifying pain-specific brain networks. We propose that autonomic nervous system activity should be used as a surrogate measure of salience and arousal to improve these efforts and enable researchers to parse out pain-specific responses in the brain, and demonstrate the feasibility of this approach using example fMRI data from a thermal pain paradigm. This new approach will improve the accuracy and specificity of functional neuroimaging analyses and help to overcome current difficulties in assessing pain specific responses in the human brain.

Using Deep Learning and Resting-State fMRI to Classify Chronic Pain Conditions

Chronic pain is known as a complex disease due to its comorbidities with other symptoms and the lack of effective treatments. As a consequence, chronic pain seems to be under-diagnosed in more than 75% of patients. At the same time, the advance in brain imaging, the popularization of machine learning techniques and the development of new diagnostic tools based on these technologies have shown that these tools could be an option in supporting decision-making of healthcare professionals. In this study, we computed functional brain connectivity using resting-state fMRI data from one hundred and fifty participants to assess the performance of different machine learning models, including deep learning (DL) neural networks in classifying chronic pain patients and pain-free controls. The best result was obtained by training a convolutional neural network fed with data preprocessed using the MSDL probabilistic atlas and using the dynamic time warping (DTW) as connectivity measure. DL models had a better performance compared to other less costly models such as support vector machine (SVM) and RFC, with balanced accuracy ranged from 69 to 86%, while the area under the curve (ROC) ranged from 0.84 to 0.93. Also, DTW overperformed correlation as connectivity measure. These findings support the notion that resting-state fMRI data could be used as a potential biomarker of chronic pain conditions.

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

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

Delineating conditions and subtypes in chronic pain using neuroimaging

Differentiating subtypes of chronic pain still remains a challenge—both from a subjective and objective point of view. Personalized medicine is the current goal of modern medical care and is limited by the subjective nature of patient self-reporting of symptoms and behavioral evaluation. Physiology-focused techniques such as genome and epigenetic analyses inform the delineation of pain groups; however, except under rare circumstances, they have diluted effects that again, share a common reliance on behavioral evaluation. The application of structural neuroimaging towards distinguishing pain subtypes is a growing field and may inform pain-group classification through the analysis of brain regions showing hypertrophic and atrophic changes in the presence of pain. Analytical techniques such as machine-learning classifiers have the capacity to process large volumes of data and delineate diagnostically relevant information from neuroimaging analysis. The issue of defining a “brain type” is an emerging field aimed at interpreting observed brain changes and delineating their clinical identity/significance. In this review, 2 chronic pain conditions (migraine and irritable bowel syndrome) with similar clinical phenotypes are compared in terms of their structural neuroimaging findings. Independent investigations are compared with findings from application of machine-learning algorithms. Findings are discussed in terms of differentiating patient subgroups using neuroimaging data in patients with chronic pain and how they may be applied towards defining a personalized pain signature that helps segregate patient subgroups (eg, migraine with and without aura, with or without nausea; irritable bowel syndrome vs other functional gastrointestinal disorders).

Association Between Sensorimotor Impairments and Functional Brain Changes in Patients With Low Back Pain: A Critical Review

Low back pain (LBP) coincides with sensorimotor impairments, for example, reduced lumbosacral tactile and proprioceptive acuity and postural control deficits. Recent functional magnetic resonance imaging studies suggest that sensorimotor impairments in LBP may be associated with brain changes. However, no consensus exists regarding the relationship between functional brain changes and sensorimotor behavior in LBP. Therefore, this review critically discusses the available functional magnetic resonance imaging studies on brain activation related to nonnociceptive somatosensory stimulation and motor performance in individuals with LBP. Four electronic databases were searched, yielding nine relevant studies. Patients with LBP showed reduced sensorimotor-related brain activation and a reorganized lumbar spine representation in higher-order (multi)sensory processing and motor regions, including primary and secondary somatosensory cortices, supplementary motor area, and superior temporal gyrus. These results may support behavioral findings of sensorimotor impairments in LBP. In addition, patients with LBP displayed widespread increased sensorimotor-evoked brain activation in regions often associated with abnormal pain processing. Overactivation in these regions could indicate an overresponsiveness to sensory inputs that signal potential harm to the spine, thereby inducing overgeneralized protective responses. Hence, functional brain changes could contribute to the development and recurrence of LBP. However, future studies investigating the causality between sensorimotor-related brain function and LBP are imperative.

Artificial intelligence and machine learning | applications in musculoskeletal physiotherapy

INTRODUCTION

Artificial intelligence (AI) is a field of mathematical engineering which has potential to enhance healthcare through new care delivery strategies, informed decision making and facilitation of patient engagement. Machine learning (ML) is a form of narrow artificial intelligence which can be used to automate decision making and make predictions based upon patient data.

PURPOSE

This review outlines key applications of supervised and unsupervised machine learning in musculoskeletal medicine; such as diagnostic imaging, patient measurement data, and clinical decision support. The current literature base is examined to identify areas where ML performs equal to or more accurately than human levels.

IMPLICATIONS

Potential is apparent for intelligent machines to enhance various areas of physiotherapy practice through automization of tasks which involve data analysis, classification and prediction. Changes to service provision through applications of ML, should encourage physiotherapists to increase their awareness of and experiences with emerging technologies. Data literacy should be a component of professional development plans to assist physiotherapists in the application of ML and the preparation of information technology systems to use these techniques.

Cerebral mechanism of celecoxib for treating knee pain: study protocol for a randomized controlled parallel trial

Background

Celecoxib is frequently prescribed to treat knee osteoarthritis (KOA), but how celecoxib influences the activity of the central nervous system to alleviate chronic pain remains unclear.

Methods

One hundred eight patients with KOA will be enrolled in this study. Patients will be allocated randomly to three groups: the celecoxib group, the placebo group, and the waiting list group. The patients in the celecoxib group will orally take celecoxib 200 mg once daily and the patients in placebo group with placebo 200 mg every day for 2 weeks. Functional magnetic resonance imaging scan will be performed on all patients at baseline and the end of interventions to detect the cerebral activity changes. The short form of McGill pain questionnaire and the Visual Analog Scale will be used as the primary endpoints to evaluate the improvement of knee pain. The secondary endpoints include the Western Ontario and McMaster osteoarthritis index (WOMAC), the Attention Test Scale, the Pain Assessment of Sphygmomanometer, the Self-rating Anxiety Scale, the Self-rating Depression Scale, and 12-Item Short Form Health Survey (SF-12).

Discussion

The results will investigate the influence of celecoxib treatment on cerebral activity of patients with KOA and the possible relationship between the cerebral activity changes and improvement of clinical variables so as to explore the central mechanism of celecoxib in treating knee pain.

Trial registration

ChiCTR-IOR-17012365. Registered on August 14, 2017.

Electronic supplementary material

The online version of this article (10.1186/s13063-018-3111-8) contains supplementary material, which is available to authorized users.

Brain systems at the intersection of chronic pain and self-regulation

Chronic pain is a multidimensional experience with cognitive, affective, and somatosensory components that can be modified by expectations and learning. Individual differences in cognitive and affective processing, as well as contextual aspects of the pain experience, render chronic pain an inherently personal experience. Such individual differences are supported by the heterogeneity of brain representations within and across chronic pain pathologies. In this review, we discuss the complexity of brain representations of pain, and, with respect to this complexity, identify common elements of network-level disruptions in chronic pain. Specifically, we identify prefrontal-limbic circuitry and the default mode network as key elements of functional disruption. We then discuss how these disrupted circuits can be targeted through self-regulation and related cognitive strategies to alleviate chronic pain. We conclude with a proposal for how to develop personalized multivariate models of pain representation in the brain and target them with real-time neurofeedback, so that patients can explore and practice self-regulatory techniques with maximal efficiency.

Classification and characterisation of brain network changes in chronic back pain: A multicenter study

Background. Chronic pain is a common, often disabling condition thought to involve a combination of peripheral and central neurobiological factors. However, the extent and nature of changes in the brain is poorly understood.

Methods. We investigated brain network architecture using resting-state fMRI data in chronic back pain patients in the UK and Japan (41 patients, 56 controls), as well as open data from USA. We applied machine learning and deep learning (conditional variational autoencoder architecture) methods to explore classification of patients/controls based on network connectivity. We then studied the network topology of the data, and developed a multislice modularity method to look for consensus evidence of modular reorganisation in chronic back pain.

Results. Machine learning and deep learning allowed reliable classification of patients in a third, independent open data set with an accuracy of 63%, with 68% in cross validation of all data. We identified robust evidence of network hub disruption in chronic pain, most consistently with respect to clustering coefficient and betweenness centrality. We found a consensus pattern of modular reorganisation involving extensive, bilateral regions of sensorimotor cortex, and characterised primarily by negative reorganisation - a tendency for sensorimotor cortex nodes to be less inclined to form pairwise modular links with other brain nodes. Furthermore, these regions were found to display increased connectivity with the pregenual anterior cingulate cortex, a region known to be involved in endogenous pain control. In contrast, intraparietal sulcus displayed a propensity towards positive modular reorganisation, suggesting that it might have a role in forming modules associated with the chronic pain state.

Conclusion. The results provide evidence of consistent and characteristic brain network changes in chronic pain, characterised primarily by extensive reorganisation of the network architecture of the sensorimotor cortex.

Classification and characterisation of brain network changes in chronic back pain: A multicenter study

Background. Chronic pain is a common, often disabling condition thought to involve a combination of peripheral and central neurobiological factors. However, the extent and nature of changes in the brain is poorly understood. Methods. We investigated brain network architecture using resting-state fMRI data in chronic back pain patients in the UK and Japan (41 patients, 56 controls), as well as open data from USA. We applied machine learning and deep learning (conditional variational autoencoder architecture) methods to explore classification of patients/controls based on network connectivity. We then studied the network topology of the data, and developed a multislice modularity method to look for consensus evidence of modular reorganisation in chronic back pain. Results. Machine learning and deep learning allowed reliable classification of patients in a third, independent open data set with an accuracy of 63%, with 68% in cross validation of all data. We identified robust evidence of network hub disruption in chronic pain, most consistently with respect to clustering coefficient and betweenness centrality. We found a consensus pattern of modular reorganisation involving extensive, bilateral regions of sensorimotor cortex, and characterised primarily by negative reorganisation - a tendency for sensorimotor cortex nodes to be less inclined to form pairwise modular links with other brain nodes. In contrast, intraparietal sulcus displayed a propensity towards positive modular reorganisation, suggesting that it might have a role in forming modules associated with the chronic pain state. Conclusion. The results provide evidence of consistent and characteristic brain network changes in chronic pain, characterised primarily by extensive reorganisation of the network architecture of the sensorimotor cortex.

Musculoskeletal signs in female homecare personnel: A longitudinal epidemiological study

BACKGROUND:

In Sweden, homecare services take care of elderly and disabled people, work that often requires heavy lifting and forward bending, resulting in high prevalences of pain and work accidents.

OBJECTIVE:

Using an eight-year follow-up, this study determines the prognostic importance of certain musculoskeletal signs reported in earlier studies [1, 2] with respect to aspects of pain and perceived disability.

METHODS:

Baseline data has been reported in earlier studies of 607 women [1–3]. This study uses a postal questionnaire survey and reports the results of eight years post initial study.

RESULTS:

Segmental pain at L4-L5 and/or L5-S1 levels was associated with higher low back pain intensity and disability at the eight-year follow-up. A decrease in low back pain intensity over eight years was larger for those with segmental pain. The important signs in the longitudinal analyses of pain aspects and disability were lumbar spinal mobility and segmental pain at L4-L5 and L5-S1 levels, but the explained variations were low.

CONCLUSION:

Evaluation of low lumbar segmental pain provocation and mobility should be considered in routine clinical assessments, as this type of evaluation provides prognostic pain and disability information over time.

Biomarkers for Musculoskeletal Pain Conditions: Use of Brain Imaging and Machine Learning

Chronic musculoskeletal pain condition often shows poor correlations between tissue abnormalities and clinical pain. Therefore, classification of pain conditions like chronic low back pain, osteoarthritis, and fibromyalgia depends mostly on self report and less on objective findings like X-ray or magnetic resonance imaging (MRI) changes. However, recent advances in structural and functional brain imaging have identified brain abnormalities in chronic pain conditions that can be used for illness classification. Because the analysis of complex and multivariate brain imaging data is challenging, machine learning techniques have been increasingly utilized for this purpose. The goal of machine learning is to train specific classifiers to best identify variables of interest on brain MRIs (i.e., biomarkers). This report describes classification techniques capable of separating MRI-based brain biomarkers of chronic pain patients from healthy controls with high accuracy (70-92%) using machine learning, as well as critical scientific, practical, and ethical considerations related to their potential clinical application. Although self-report remains the gold standard for pain assessment, machine learning may aid in the classification of chronic pain disorders like chronic back pain and fibromyalgia as well as provide mechanistic information regarding their neural correlates.

Multivariate pattern analysis utilizing structural or functional MRI-In individuals with musculoskeletal pain and healthy controls: A systematic review

OBJECTIVE

The purpose of this systematic review is to systematically review the evidence relating to findings generated by multivariate pattern analysis (MVPA) following structural or functional magnetic resonance imaging (fMRI) to determine if this analysis is able to: a) Discriminate between individuals with musculoskeletal pain and healthy controls, b) Predict pain perception in healthy individuals stimulated with a noxious stimulus compared to those stimulated with a non-noxious stimulus.

METHODS

MEDLINE, CINAHL, Embase, PEDro, Google Scholar, Cochrane library and Web of Science were systematically screened for relevant literature using different combinations of keywords regarding structural and functional MRI analysed with MVPA, both in individuals with musculoskeletal pain and healthy controls. Reference lists of included articles were hand-searched for additional literature. Eligible articles were assessed on risk of bias and reviewed by two independent researchers.

RESULTS

The search query returned 18 articles meeting the inclusion criteria. Methodological quality varied from poor to good. Seven studies investigated the ability of machine-learning algorithms to differentiate patient groups from healthy control participants. Overall, the review demonstrated that MVPA can discriminate between individuals with MSK pain and healthy controls with an overall accuracy ranging from 53% to 94%. Twelve studies utilized healthy control participants (using them as their own controls), during experimental pain paradigms aimed to investigate the ability of machine-learning to differentiate individuals stimulated with noxious stimuli from those stimulated with non-noxious stimuli, with 'pain' detection rates ranging from 60% to 94%. However, significant heterogeneity in patient conditions, study methodology and brain imaging techniques resulted in various findings that make study comparisons and formal conclusions challenging.

CONCLUSION

There is preliminary and emerging evidence that MVPA analyses of structural or functional MRI are able to discriminate between patients and healthy controls, and also discriminate between noxious and non-noxious stimulation. No prospective studies were found in this review to allow determination of the prognostic or diagnostic capabilities or treatment responsiveness of these analyses. Future studies would also benefit from combining various behavioural, genotype and phenotype data into analyses to assist with development of sensitive and specific signatures that could guide future individualized patient treatment options and evaluate how treatments exert their effects.

[Development and content of the behavioral therapy module of the MiSpEx intervention: Randomized, controlled trial on chronic nonspecific low back pain]

Back pain is a complex phenomenon that goes beyond a simple medical diagnosis. The aetiology and chronification of back pain can be best described as an interaction between biological, psychological, and social processes. However, to date, multimodal prevention and intervention programs for back pain that target all three aetiological factors have demonstrated limited effectiveness. This lack of supportive evidence for multimodal programmes in the treatment of back pain could be due to the fact that few programs are suitable for long-term and unsupervised use in everyday life. Moreover, in combining the elements from various therapies, little attention has been paid to the mechanisms underlying the synergistic effects of the separate components. In this contribution, we will describe the development of a new multimodal intervention for back pain that set out to address these limitations. To this end, the biological elements of neuromuscular adaptation is supplemented with cognitive behavioral and psychophysiological techniques in an intervention that can be followed at home as well as in clinics, and that is suitable for all grades of pain. The efficacy of this intervention will be tested in a multicentric randomized controlled longitudinal trial (n = 714) at five time points over a period of 6 months. Here we will describe the development and the content of this new intervention.

Abnormal Brain Responses to Action Observation in Complex Regional Pain Syndrome

Patients with complex regional pain syndrome (CRPS) display various abnormalities in central motor function, and their pain is intensified when they perform or just observe motor actions. In this study, we examined the abnormalities of brain responses to action observation in CRPS. We analyzed 3-T functional magnetic resonance images from 13 upper limb CRPS patients (all female, ages 31-58 years) and 13 healthy, age- and sex-matched control subjects. The functional magnetic resonance imaging data were acquired while the subjects viewed brief videos of hand actions shown in the first-person perspective. A pattern-classification analysis was applied to characterize brain areas where the activation pattern differed between CRPS patients and healthy subjects. Brain areas with statistically significant group differences (q < .05, false discovery rate-corrected) included the hand representation area in the sensorimotor cortex, inferior frontal gyrus, secondary somatosensory cortex, inferior parietal lobule, orbitofrontal cortex, and thalamus. Our findings indicate that CRPS impairs action observation by affecting brain areas related to pain processing and motor control.

PERSPECTIVE

This article shows that in CRPS, the observation of others' motor actions induces abnormal neural activity in brain areas essential for sensorimotor functions and pain. These results build the cerebral basis for action-observation impairments in CRPS.

Legal and ethical issues of using brain imaging to diagnose pain

Pain, by definition, is a subjective experience, and as such its presence has usually been based on a self-report. However, limitations of self-reports for pain diagnostics, particularly for legal and insurance purposes, has led some to consider a brain-imaging-based objective measure of pain. This review will provide an overview of (1) differences between pain and nociception, (2) intersubject variability in pain perception and the associated brain structures and functional circuits, and (3) capabilities and limitations of current brain-imaging technologies. I then discuss how these factors impact objective proxies of pain. Finally, the ethical, privacy, and legal implications of a brain-imaging-based objective measure of pain are considered as potential future technological developments necessary to create a so-called "painometer test."

The Brain Is Faster than the Hand in Split-Second Intentions to Respond to an Impending Hazard: A Simulation of Neuroadaptive Automation to Speed Recovery to Perturbation in Flight Attitude

The goal of this research is to test the potential for neuroadaptive automation to improve response speed to a hazardous event by using a brain-computer interface (BCI) to decode perceptual-motor intention. Seven participants underwent four experimental sessions while measuring brain activity with magnetoencephalograpy. The first three sessions were of a simple constrained task in which the participant was to pull back on the control stick to recover from a perturbation in attitude in one condition and to passively observe the perturbation in the other condition. The fourth session consisted of having to recover from a perturbation in attitude while piloting the plane through the Grand Canyon constantly maneuvering to track over the river below. Independent component analysis was used on the first two sessions to extract artifacts and find an event related component associated with the onset of the perturbation. These two sessions were used to train a decoder to classify trials in which the participant recovered from the perturbation (motor intention) vs. just passively viewing the perturbation. The BCI-decoder was tested on the third session of the same simple task and found to be able to significantly distinguish motor intention trials from passive viewing trials (mean = 69.8%). The same BCI-decoder was then used to test the fourth session on the complex task. The BCI-decoder significantly classified perturbation from no perturbation trials (73.3%) with a significant time savings of 72.3 ms (Original response time of 425.0-352.7 ms for BCI-decoder). The BCI-decoder model of the best subject was shown to generalize for both performance and time savings to the other subjects. The results of our off-line open loop simulation demonstrate that BCI based neuroadaptive automation has the potential to decode motor intention faster than manual control in response to a hazardous perturbation in flight attitude while ignoring ongoing motor and visual induced activity related to piloting the airplane.

Fear avoidance beliefs in back pain-free subjects are reflected by amygdala-cingulate responses

In most individuals suffering from chronic low back pain, psychosocial factors, specifically fear avoidance beliefs (FABs), play central roles in the absence of identifiable organic pathology. On a neurobiological level, encouraging research has shown brain system correlates of somatic and psychological factors during the transition from (sub) acute to chronic low back pain. The characterization of brain imaging signatures in pain-free individuals before any injury will be of high importance regarding the identification of relevant networks for low back pain (LBP) vulnerability. Fear-avoidance beliefs serve as strong predictors of disability and chronification in LBP and current research indicates that back pain related FABs already exist in the general and pain-free population. Therefore, we aimed at investigating possible differential neural functioning between high- and low fear-avoidant individuals in the general population using functional magnetic resonance imaging. Results revealed that pain-free individuals without a history of chronic pain episodes could be differentiated in amygdala activity and connectivity to the pregenual anterior cingulate cortex by their level of back pain related FABs. These results shed new light on brain networks underlying psychological factors that may become relevant for enhanced disability in a future LBP episode.

Neuroimaging of chronic pain

Chronic pain is an important public health problem, and there is a need to understand the mechanisms that lead to pain chronification. From a neurobiological perspective, the mechanisms contributing to the transition from acute to subacute and chronic pain are heterogeneous and are thought to take place at various levels of the peripheral and central nervous system. In the past decade, brain imaging studies have shed light on neural correlates of pain perception and pain modulation, but they have also begun to disentangle neural mechanisms that underlie chronic pain. This review summarizes important and recent findings in pain research using magnetic resonance tomography. Especially new developments in functional, structural and neurochemical imaging such as resting-state connectivity and γ-aminobutyric acid (GABA) spectroscopy, which have advanced our understanding of chronic pain and which can potentially be integrated in clinical practice, will be discussed.

Comparison of machine classification algorithms for fibromyalgia: neuroimages versus self-report

Recent studies have posited that machine learning (ML) techniques accurately classify individuals with and without pain solely based on neuroimaging data. These studies claim that self-report is unreliable, making "objective" neuroimaging classification methods imperative. However, the relative performance of ML on neuroimaging and self-report data have not been compared. This study used commonly reported ML algorithms to measure differences between "objective" neuroimaging data and "subjective" self-report (ie, mood and pain intensity) in their ability to discriminate between individuals with and without chronic pain. Structural magnetic resonance imaging data from 26 individuals (14 individuals with fibromyalgia and 12 healthy controls) were processed to derive volumes from 56 brain regions per person. Self-report data included visual analog scale ratings for pain intensity and mood (ie, anger, anxiety, depression, frustration, and fear). Separate models representing brain volumes, mood ratings, and pain intensity ratings were estimated across several ML algorithms. Classification accuracy of brain volumes ranged from 53 to 76%, whereas mood and pain intensity ratings ranged from 79 to 96% and 83 to 96%, respectively. Overall, models derived from self-report data outperformed neuroimaging models by an average of 22%. Although neuroimaging clearly provides useful insights for understanding neural mechanisms underlying pain processing, self-report is reliable and accurate and continues to be clinically vital.

PERSPECTIVE

The present study compares neuroimaging, self-reported mood, and self-reported pain intensity data in their ability to classify individuals with and without fibromyalgia using ML algorithms. Overall, models derived from self-reported mood and pain intensity data outperformed structural neuroimaging models.