Machine learning-based prediction of clinical pain using multimodal neuroimaging and autonomic metrics

The need for epistemic humility in AI-assisted pain assessment

It has been difficult historically for physicians, patients, and philosophers alike to quantify pain given that pain is commonly understood as an individual and subjective experience. The process of measuring and diagnosing pain is often a fraught and complicated process. New developments in diagnostic technologies assisted by artificial intelligence promise more accurate and efficient diagnosis for patients, but these tools are known to reproduce and further entrench existing issues within the healthcare system, such as poor patient treatment and the replication of systemic biases. In this paper we present the argument that there are several ethical-epistemic issues with the potential implementation of these technologies in pain management settings. We draw on literature about self-trust and epistemic and testimonial injustice to make these claims. We conclude with a proposal that the adoption of epistemic humility on the part of both AI tool developers and clinicians can contribute to a climate of trust in and beyond the pain management context and lead to a more just approach to the implementation of AI in pain diagnosis and management.

Challenging Cognitive Load Theory: The Role of Educational Neuroscience and Artificial Intelligence in Redefining Learning Efficacy

Background/Objectives: This systematic review integrates Cognitive Load Theory (CLT), Educational Neuroscience (EdNeuro), Artificial Intelligence (AI), and Machine Learning (ML) to examine their combined impact on optimizing learning environments. It explores how AI-driven adaptive learning systems, informed by neurophysiological insights, enhance personalized education for K-12 students and adult learners. This study emphasizes the role of Electroencephalography (EEG), Functional Near-Infrared Spectroscopy (fNIRS), and other neurophysiological tools in assessing cognitive states and guiding AI-powered interventions to refine instructional strategies dynamically. Methods: This study reviews n = 103 papers related to the integration of principles of CLT with AI and ML in educational settings. It evaluates the progress made in neuroadaptive learning technologies, especially the real-time management of cognitive load, personalized feedback systems, and the multimodal applications of AI. Besides that, this research examines key hurdles such as data privacy, ethical concerns, algorithmic bias, and scalability issues while pinpointing best practices for robust and effective implementation. Results: The results show that AI and ML significantly improve Learning Efficacy due to managing cognitive load automatically, providing personalized instruction, and adapting learning pathways dynamically based on real-time neurophysiological data. Deep Learning models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Support Vector Machines (SVMs) improve classification accuracy, making AI-powered adaptive learning systems more efficient and scalable. Multimodal approaches enhance system robustness by mitigating signal variability and noise-related limitations by combining EEG with fMRI, Electrocardiography (ECG), and Galvanic Skin Response (GSR). Despite these advances, practical implementation challenges remain, including ethical considerations, data security risks, and accessibility disparities across learner demographics. Conclusions: AI and ML are epitomes of redefinition potentials that solid ethical frameworks, inclusive design, and scalable methodologies must inform. Future studies will be necessary for refining pre-processing techniques, expanding the variety of datasets, and advancing multimodal neuroadaptive learning for developing high-accuracy, affordable, and ethically responsible AI-driven educational systems. The future of AI-enhanced education should be inclusive, equitable, and effective across various learning populations that would surmount technological limitations and ethical dilemmas.

Pattern Identification in Patients with Functional Dyspepsia Using Brain-Body Bio-Signals: Protocol of a Clinical Trial for AI Algorithm Development

Background: Functional dyspepsia (FD) is a common functional gastrointestinal disorder characterized by chronic digestive symptoms without identifiable structural abnormalities. FD affects approximately 8-46% of the population, leading to significant socioeconomic burdens due to reduced quality of life and productivity. Traditional medicine utilizes differential diagnosis through comprehensive examinations, which include observing and questioning, abdominal examination, and pulse diagnosis for functional gastrointestinal disorders. However, challenges persist in the standardization and objectivity of diagnostic protocols. Methods: This study aims to develop an artificial intelligence-based algorithm to predict identified patterns in patients with functional dyspepsia by integrating brain-body bio-signals, including brain activity measured by functional near-infrared spectroscopy, pulse wave, skin conductance response, and electrocardiography. We will conduct an observational cross-sectional study comprising 100 patients diagnosed according to the Rome IV criteria, collecting bio-signal data alongside differential diagnoses performed by licensed Korean medicine doctors. The study protocol was reviewed and approved by the Institutional Review Board of Kyung Hee University Hospital at Gangdong on 25 January 2024 (IRB no. KHNMCOH 2023-12-003-003) and was registered in the Korean Clinical Trial Registry (KCT0009275). Results: By creating AI algorithms based on bio-signals and integrating them into clinical practice, the objectivity and reliability of traditional diagnostics are expected to be enhanced. Conclusions: The integration of bio-signal analysis into the diagnostic process for patients with FD will improve clinical practices and support the broader acceptance of traditional-medicine diagnostic processes in healthcare.

Development and Evaluation of a GPT4-Based Orofacial Pain Clinical Decision Support System

Background: Orofacial pain (OFP) encompasses a complex array of conditions affecting the face, mouth, and jaws, often leading to significant diagnostic challenges and high rates of misdiagnosis. Artificial intelligence, particularly large language models like GPT4 (OpenAI, San Francisco, CA, USA), offers potential as a diagnostic aid in healthcare settings. Objective: To evaluate the diagnostic accuracy of GPT4 in OFP cases as a clinical decision support system (CDSS) and compare its performance against treating clinicians, expert evaluators, medical students, and general practitioners. Methods: A total of 100 anonymized patient case descriptions involving diverse OFP conditions were collected. GPT4 was prompted to generate primary and differential diagnoses for each case using the International Classification of Orofacial Pain (ICOP) criteria. Diagnoses were compared to gold-standard diagnoses established by treating clinicians, and a scoring system was used to assess accuracy at three hierarchical ICOP levels. A subset of 24 cases was also evaluated by two clinical experts, two final-year medical students, and two general practitioners for comparative analysis. Diagnostic performance and interrater reliability were calculated. Results: GPT4 achieved the highest accuracy level (ICOP level 3) in 38% of cases, with an overall diagnostic performance score of 157 out of 300 points (52%). The model provided accurate differential diagnoses in 80% of cases (400 out of 500 points). In the subset of 24 cases, the model's performance was comparable to non-expert human evaluators but was surpassed by clinical experts, who correctly diagnosed 54% of cases at level 3. GPT4 demonstrated high accuracy in specific categories, correctly diagnosing 81% of trigeminal neuralgia cases at level 3. Interrater reliability between GPT4 and human evaluators was low (κ = 0.219, p < 0.001), indicating variability in diagnostic agreement. Conclusions: GPT4 shows promise as a CDSS for OFP by improving diagnostic accuracy and offering structured differential diagnoses. While not yet outperforming expert clinicians, GPT4 can augment diagnostic workflows, particularly in primary care or educational settings. Effective integration into clinical practice requires adherence to rigorous guidelines, thorough validation, and ongoing professional oversight to ensure patient safety and diagnostic reliability.

Improving neuropathic pain treatment - by rigorous stratification from bench to bedside

Chronic pain is a constantly recurring and persistent illness, presenting a formidable healthcare challenge for patients and physicians alike. Current first-line analgesics offer only low-modest efficacy when averaged across populations, further contributing to this debilitating disease burden. Moreover, many recent trials for novel analgesics have not met primary efficacy endpoints, which is particularly striking considering the pharmacological advances have provided a range of highly relevant new drug targets. Heterogeneity within chronic pain cohorts is increasingly understood to play a critical role in these failures of treatment and drug discovery, with some patients deriving substantial benefits from a given intervention while it has little-to-no effect on others. As such, current treatment failures may not result from a true lack of efficacy, but rather a failure to target individuals whose pain is driven by mechanisms which it therapeutically modulates. This necessitates a move towards phenotypical stratification of patients to delineate responders and non-responders in a mechanistically driven manner. In this article, we outline a bench-to-bedside roadmap for this transition to mechanistically informed personalised pain medicine. We emphasise how the successful identification of novel analgesics is dependent on rigorous experimental design as well as the validity of models and translatability of outcome measures between the animal model and patients. Subsequently, we discuss general and specific aspects of human trial design to address heterogeneity in patient populations to increase the chance of identifying effective analgesics. Finally, we show how stratification approaches can be brought into clinical routine to the benefit of patients.

Reinforced pain catastrophizing during menstrual phase among women with primary dysmenorrhea is mediated by cerebral blood flow in the medial prefrontal cortex

Pain catastrophizing is a prominent psychological factor that is strongly correlated with pain. Although the complex properties of pain catastrophizing vary across different pain phases, the contribution of chronic pain to its progression from a general trait to a higher state remains unclear. This study aimed to examine the neural mechanisms and degree to which pain catastrophizing is reinforced in the context of primary dysmenorrhea (PDM), one of the most prevalent gynaecological complaints experienced by women of reproductive age. Altogether, 29 women with moderate-to-severe PDM were included in this study. Arterial spin labelling was used to quantify the cerebral blood flow (CBF) in each participant in both the pain-free and painful phases. The pain catastrophizing scale (PCS) was completed in two phases, and the Short-Form McGill Pain Questionnaire was completed in the painful phase. Compared with pain catastrophizing in the pain-free phase (PCSpf), pain catastrophizing in the painful phase (PCSp) is higher and positively correlated with the composite factor of menstrual pain. CBF analysis indicated that the PCSp is positively associated with CBF in the frontal cortex, hippocampus and amygdala. The reinforcement of pain catastrophizing correlates with CBF in the prefrontal cortex. Specifically, the medial prefrontal cortex, which correlates with pain state, plays a crucial role in mediating the reinforcing effect of pain in the PCSp. These results promote the mechanical comprehension of pain catastrophizing management in individuals with chronic pain.

Advances and challenges in neuroimaging-based pain biomarkers

Identifying neural biomarkers of pain has long been a central theme in pain neuroscience. Here, we review the state-of-the-art candidates for neural biomarkers of acute and chronic pain. We classify these potential neural biomarkers into five categories based on the nature of their target variables, including neural biomarkers of (1) within-individual perception, (2) between-individual sensitivity, and (3) discriminability for acute pain, as well as (4) assessment and (5) prospective neural biomarkers for chronic pain. For each category, we provide a synthesized review of candidate biomarkers developed using neuroimaging techniques including functional magnetic resonance imaging (fMRI), structural magnetic resonance imaging (sMRI), and electroencephalography (EEG). We also discuss the conceptual and practical challenges in developing neural biomarkers of pain. Addressing these challenges, optimal biomarkers of pain can be developed to deepen our understanding of how the brain represents pain and ultimately help alleviate patients' suffering and improve their well-being.

An approach to the detection of pain from autonomic and cortical correlates

OBJECTIVE

To assess the value of combining brain and autonomic measures to discriminate the subjective perception of pain from other sensory-cognitive activations.

METHODS

20 healthy individuals received 2 types of tonic painful stimulation delivered to the hand: electrical stimuli and immersion in 10 Celsius degree (°C) water, which were contrasted with non-painful immersion in 15 °C water, and stressful cognitive testing. High-density electroencephalography (EEG) and autonomic measures (pupillary, electrodermal and cardiovascular) were continuously recorded, and the accuracy of pain detection based on combinations of electrophysiological features was assessed using machine learning procedures.

RESULTS

Painful stimuli induced a significant decrease in contralateral EEG alpha power. Cardiac, electrodermal and pupillary reactivities occurred in both painful and stressful conditions. Classification models, trained on leave-one-out cross-validation folds, showed low accuracy (61-73%) of cortical and autonomic features taken independently, while their combination significantly improved accuracy to 93% in individual reports.

CONCLUSIONS

Changes in cortical oscillations reflecting somatosensory salience and autonomic changes reflecting arousal can be triggered by many activating signals other than pain; conversely, the simultaneous occurrence of somatosensory activation plus strong autonomic arousal has great probability of reflecting pain uniquely.

SIGNIFICANCE

Combining changes in cortical and autonomic reactivities appears critical to derive accurate indexes of acute pain perception.

Artificial Intelligence-Driven Diagnostic Processes and Comprehensive Multimodal Models in Pain Medicine

Pain diagnosis remains a challenging task due to its subjective nature, the variability in pain expression among individuals, and the difficult assessment of the underlying biopsychosocial factors. In this complex scenario, artificial intelligence (AI) can offer the potential to enhance diagnostic accuracy, predict treatment outcomes, and personalize pain management strategies. This review aims to dissect the current literature on computer-aided diagnosis methods. It also discusses how AI-driven diagnostic strategies can be integrated into multimodal models that combine various data sources, such as facial expression analysis, neuroimaging, and physiological signals, with advanced AI techniques. Despite the significant advancements in AI technology, its widespread adoption in clinical settings faces crucial challenges. The main issues are ethical considerations related to patient privacy, biases, and the lack of reliability and generalizability. Furthermore, there is a need for high-quality real-world validation and the development of standardized protocols and policies to guide the implementation of these technologies in diverse clinical settings.

Current Trends in Modalities of Pain Assessment: A Narrative Review

Pain is a common complaint among a spectrum of diseases. Although an ideal objective method of pain assessment is lacking, several validated tools are available for use in clinical research and practice. The tool considerations are based upon the parameters to be assessed and factors specific to patient, disease, and availability of instruments. This review classifies and brings the key aspects of currently available pain assessment tools on a single platform to ease the selection process for researchers/practitioners. The tools utilized for pain assessment were collected from articles available in PubMed and Google Scholar databases and classified into the following domains: unidimensional, multi-dimensional, investigation-based, and computerized algorithm-based tools. Their purpose of use and limitations are reviewed. The unidimensional scales are used to describe only the characteristics of pain, like intensity (e.g. numerical rating scale), type (e.g. neuropathic pain questionnaire), or pattern. In contrast, multi-dimensional tools, like Mc Gill Questionnaire, assess not only pain as an individual symptom but also its influence on physical functioning and general well-being. However, certain components like ethnicity, age, cognitive impairment, sedation, and emotion become a limiting factor in selecting the scale. In addition to these scales, a potential role of parameters such as biopotentials/markers has also been shown in pain assessment. Last, artificial intelligence is also being applied in evaluation of pain. Pain measurement is subjective in nature as assessed through questionnaires and observational tools. Currently, multi-dimensional approaches of pain assessment are available, which can lead to precision pain management.

The effects of virtual reality neuroscience-based therapy on clinical and neuroimaging outcomes in patients with chronic back pain: a randomized clinical trial

ABSTRACT

Chronic pain remains poorly managed. The integration of immersive technologies (ie, virtual reality [VR]) with neuroscience-based principles may provide effective pain treatment by targeting cognitive and affective neural processes that maintain pain and therefore potentially changing neurobiological circuits associated with pain chronification and amplification. We tested the effectiveness of a novel VR neuroscience-based therapy (VRNT) to improve pain-related outcomes in n = 31 participants with chronic back pain, evaluated against usual care (waitlist control; n = 30) in a 2-arm randomized clinical trial ( NCT04468074) . We also conducted pre-treatment and post-treatment MRI to test whether VRNT affects brain networks previously linked to chronic pain and treatment effects. Compared with the control condition, VRNT led to significantly reduced pain intensity (g = 0.63) and pain interference (g = 0.84) at post-treatment vs pre-treatment, with effects persisting at 2-week follow-up. These improvements were partially mediated by reduced kinesiophobia and pain catastrophizing. Several secondary clinical outcomes were also improved by VRNT, including disability, quality of life, sleep, and fatigue. In addition, VRNT was associated with increases in dorsomedial prefrontal functional connectivity with the superior somatomotor, anterior prefrontal and visual cortices, and decreased white matter fractional anisotropy in the corpus callosum adjacent to the anterior cingulate, relative to the control condition. Thus, VRNT showed preliminary efficacy in significantly reducing pain and improving overall functioning, possibly through changes in somatosensory and prefrontal brain networks.

A review of deep learning-based information fusion techniques for multimodal medical image classification

Multimodal medical imaging plays a pivotal role in clinical diagnosis and research, as it combines information from various imaging modalities to provide a more comprehensive understanding of the underlying pathology. Recently, deep learning-based multimodal fusion techniques have emerged as powerful tools for improving medical image classification. This review offers a thorough analysis of the developments in deep learning-based multimodal fusion for medical classification tasks. We explore the complementary relationships among prevalent clinical modalities and outline three main fusion schemes for multimodal classification networks: input fusion, intermediate fusion (encompassing single-level fusion, hierarchical fusion, and attention-based fusion), and output fusion. By evaluating the performance of these fusion techniques, we provide insight into the suitability of different network architectures for various multimodal fusion scenarios and application domains. Furthermore, we delve into challenges related to network architecture selection, handling incomplete multimodal data management, and the potential limitations of multimodal fusion. Finally, we spotlight the promising future of Transformer-based multimodal fusion techniques and give recommendations for future research in this rapidly evolving field.

Predicting Chronic Pain and Treatment Outcomes Using Machine Learning Models Based on High-dimensional Clinical Data From a Large Retrospective Cohort

PURPOSE

To identify factors and indicators that affect chronic pain and pain relief, and to develop predictive models using machine learning.

METHODS

We analyzed the data of 67,028 outpatient cases and 11,310 valid samples with pain from a large retrospective cohort. We used decision tree, random forest, AdaBoost, neural network, and logistic regression to discover significant indicators and to predict pain and treatment relief.

FINDINGS

The random forest model had the highest accuracy, F1 value, precision, and recall rates for predicting pain relief. The main factors affecting pain and treatment relief included body mass index, blood pressure, age, body temperature, heart rate, pulse, and neutrophil/lymphocyte × platelet ratio. The logistic regression model had high sensitivity and specificity for predicting pain occurrence.

IMPLICATIONS

Machine learning models can be used to analyze the risk factors and predictors of chronic pain and pain relief, and to provide personalized and evidence-based pain management.

Artificial intelligence: a new cutting-edge tool in spine surgery

The purpose of this narrative review was to comprehensively elaborate the various components of artificial intelligence (AI), their applications in spine surgery, practical concerns, and future directions. Over the years, spine surgery has been continuously transformed in various aspects, including diagnostic strategies, surgical approaches, procedures, and instrumentation, to provide better-quality patient care. Surgeons have also augmented their surgical expertise with rapidly growing technological advancements. AI is an advancing field that has the potential to revolutionize many aspects of spine surgery. We performed a comprehensive narrative review of the various aspects of AI and machine learning in spine surgery. To elaborate on the current role of AI in spine surgery, a review of the literature was performed using PubMed and Google Scholar databases for articles published in English in the last 20 years. The initial search using the keywords "artificial intelligence" AND "spine," "machine learning" AND "spine," and "deep learning" AND "spine" extracted a total of 78, 60, and 37 articles and 11,500, 4,610, and 2,270 articles on PubMed and Google Scholar. After the initial screening and exclusion of unrelated articles, duplicates, and non-English articles, 405 articles were identified. After the second stage of screening, 93 articles were included in the review. Studies have shown that AI can be used to analyze patient data and provide personalized treatment recommendations in spine care. It also provides valuable insights for planning surgeries and assisting with precise surgical maneuvers and decisionmaking during the procedures. As more data become available and with further advancements, AI is likely to improve patient outcomes.

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.

Applications of Artificial Intelligence in Pain Medicine

PURPOSE OF REVIEW

This review explores the current applications of artificial intelligence (AI) in the field of pain medicine with a focus on machine learning.

RECENT FINDINGS

Utilizing a literature search conducted through the PubMed database, several current trends were identified, including the use of AI as a tool for diagnostics, predicting pain progression, predicting treatment response, and performance of therapy and pain management. Results of these studies show promise for the improvement of patient outcomes. Current gaps in the research and subsequent directions for future study involve AI in optimizing and improving nerve stimulation and more thoroughly predicting patients' responses to treatment.

A Randomized Controlled Neuroimaging Trial of Cognitive Behavioral Therapy for Fibromyalgia Pain

OBJECTIVE

Fibromyalgia (FM) is characterized by pervasive pain-related symptomatology and high levels of negative affect. Mind-body treatments such as cognitive behavioral therapy (CBT) appear to foster improvement in FM via reductions in pain-related catastrophizing, a set of negative, pain-amplifying cognitive and emotional processes. However, the neural underpinnings of CBT's catastrophizing-reducing effects remain uncertain. This randomized controlled mechanistic trial was designed to assess CBT's effects on pain catastrophizing and its underlying brain circuitry.

METHODS

Of 114 enrolled participants, 98 underwent a baseline neuroimaging assessment and were randomized to 8 weeks of individual CBT or a matched FM education control (EDU) condition.

RESULTS

Compared with EDU, CBT produced larger decreases in pain catastrophizing post treatment (P < 0.05) and larger reductions in pain interference and symptom impact. Decreases in pain catastrophizing played a significant role in mediating those functional improvements in the CBT group. At baseline, brain functional connectivity between the ventral posterior cingulate cortex (vPCC), a key node of the default mode network (DMN), and somatomotor and salience network regions was increased during catastrophizing thoughts. Following CBT, vPCC connectivity to somatomotor and salience network areas was reduced.

CONCLUSION

Our results suggest clinically important and CBT-specific associations between somatosensory/motor- and salience-processing brain regions and the DMN in chronic pain. These patterns of connectivity may contribute to individual differences (and treatment-related changes) in somatic self-awareness. CBT appears to provide clinical benefits at least partially by reducing pain-related catastrophizing and producing adaptive alterations in DMN functional connectivity.

Cooperative Learning for Personalized Context-Aware Pain Assessment From Wearable Data

Despite the promising performance of automated pain assessment methods, current methods suffer from performance generalization due to the lack of relatively large, diverse, and annotated pain datasets. Further, the majority of current methods do not allow responsible interaction between the model and user, and do not take different internal and external factors into consideration during the model's design and development. This article aims to provide an efficient cooperative learning framework for the lack of annotated data while facilitating responsible user communication and taking individual differences into consideration during the development of pain assessment models. Our results using body and muscle movement data, collected from wearable devices, demonstrate that the proposed framework is effective in leveraging both the human and the machine to efficiently learn and predict pain.

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.

Digital Biomarker Applications Across the Spectrum of Opioid Use Disorder

Opioid use disorder (OUD) is one of the most pressing public health problems of the past decade, with over eighty thousand overdose related deaths in 2021 alone. Digital technologies to measure and respond to disease states encompass both on- and off-body sensors. Such devices can be used to detect and monitor end-user physiologic or behavioral measurements (i.e. digital biomarkers) that correlate with events of interest, health, or pathology. Recent work has demonstrated the potential of digital biomarkers to be used as a tools in the prevention, risk mitigation, and treatment of opioid use disorder (OUD). Multiple physiologic adaptations occur over the course of opioid use, and represent potential targets for digital biomarker based monitoring strategies. This review explores the current evidence (and potential) for digital biomarkers monitoring across the spectrum of opioid use. Technologies to detect opioid administration, withdrawal, hyperalgesia and overdose will be reviewed. Driven by empirically derived algorithms, these technologies have important implications for supporting the safe prescribing of opioids, reducing harm in active opioid users, and supporting those in recovery from OUD.

The Effects of Virtual Reality Neuroscience-based Therapy on Clinical and Neuroimaging Outcomes in Patients with Chronic Back Pain: A Randomized Clinical Trial

Chronic pain remains poorly managed. The integration of innovative immersive technologies (i.e., virtual reality (VR)) with recent neuroscience-based principles that position the brain as the key organ of chronic pain may provide a more effective pain treatment than traditional behavioral therapies. By targeting cognitive and affective processes that maintain pain and potentially directly changing neurobiological circuits associated with pain chronification and amplification, VR-based pain treatment has the potential for significant and long-lasting pain relief. We tested the effectiveness of a novel VR neuroscience-based therapy (VRNT) to improve pain-related outcomes in n = 31 participants with chronic back pain, evaluated against usual care (n = 30) in a 2-arm randomized clinical trial ( NCT04468074) . We also conducted pre- and post-treatment MRI to test whether VRNT affects brain networks previously linked to chronic pain and treatment effects. Compared to the control condition, VRNT led to significantly reduced pain intensity (g = 0.63) and pain interference (g = 0.84) at post-treatment vs. pre-treatment, with effects persisting at 2-week follow-up. The improvements were partially mediated by reduced kinesiophobia and pain catastrophizing. Several secondary clinical outcomes were also improved, including disability, quality of life, sleep, and fatigue. In addition, VRNT was associated with modest increases in functional connectivity of the somatomotor and default mode networks and decreased white matter fractional anisotropy in the corpus callosum adjacent to anterior cingula, relative to the control condition. This, VRNT showed preliminary efficacy in significantly reducing pain and improving overall functioning, possibly via changes in somatosensory and prefrontal brain networks.

The Peripheral Nerve Surgeon's Role in the Management of Neuropathic Pain

Neuropathic pain (NP) underlies significant morbidity and disability worldwide. Although pharmacologic and functional therapies attempt to address this issue, they remain incompletely effective for many patients. Peripheral nerve surgeons have a range of techniques for intervening on NP. The aim of this review is to enable practitioners to identify patients with NP who might benefit from surgical intervention. The workup for NP includes patient history and specific physical examination maneuvers, as well as imaging and diagnostic nerve blocks. Once diagnosed, there is a range of options surgeons can utilize based on specific causes of NP. These techniques include nerve decompression, nerve reconstruction, nerve ablative techniques, and implantable nerve-modulating devices. In addition, there is an emerging role for preoperative involvement of peripheral nerve surgeons for cases known to carry a high risk of inducing postoperative NP. Lastly, we describe the ongoing work that will enable surgeons to expand their armamentarium to better serve patients with NP.

Predicting Pain in People With Sickle Cell Disease in the Day Hospital Using the Commercial Wearable Apple Watch: Feasibility Study

BACKGROUND

Sickle cell disease (SCD) is a genetic red blood cell disorder associated with severe complications including chronic anemia, stroke, and vaso-occlusive crises (VOCs). VOCs are unpredictable, difficult to treat, and the leading cause of hospitalization. Recent efforts have focused on the use of mobile health technology to develop algorithms to predict pain in people with sickle cell disease. Combining the data collection abilities of a consumer wearable, such as the Apple Watch, and machine learning techniques may help us better understand the pain experience and find trends to predict pain from VOCs.

OBJECTIVE

The aim of this study is to (1) determine the feasibility of using the Apple Watch to predict the pain scores in people with sickle cell disease admitted to the Duke University SCD Day Hospital, referred to as the Day Hospital, and (2) build and evaluate machine learning algorithms to predict the pain scores of VOCs with the Apple Watch.

METHODS

Following approval of the institutional review board, patients with sickle cell disease, older than 18 years, and admitted to Day Hospital for a VOC between July 2021 and September 2021 were approached to participate in the study. Participants were provided with an Apple Watch Series 3, which is to be worn for the duration of their visit. Data collected from the Apple Watch included heart rate, heart rate variability (calculated), and calories. Pain scores and vital signs were collected from the electronic medical record. Data were analyzed using 3 different machine learning models: multinomial logistic regression, gradient boosting, and random forest, and 2 null models, to assess the accuracy of pain scores. The evaluation metrics considered were accuracy (F₁-score), area under the receiving operating characteristic curve, and root-mean-square error (RMSE).

RESULTS

We enrolled 20 patients with sickle cell disease, all of whom identified as Black or African American and consisted of 12 (60%) females and 8 (40%) males. There were 14 individuals diagnosed with hemoglobin type SS (70%). The median age of the population was 35.5 (IQR 30-41) years. The median time each individual spent wearing the Apple Watch was 2 hours and 17 minutes and a total of 15,683 data points were collected across the population. All models outperformed the null models, and the best-performing model was the random forest model, which was able to predict the pain scores with an accuracy of 84.5%, and a RMSE of 0.84.

CONCLUSIONS

The strong performance of the model in all metrics validates feasibility and the ability to use data collected from a noninvasive device, the Apple Watch, to predict the pain scores during VOCs. It is a novel and feasible approach and presents a low-cost method that could benefit clinicians and individuals with sickle cell disease in the treatment of VOCs.

Optimizing and Accelerating the Development of Precision Pain Treatments for Chronic Pain: IMMPACT Review and Recommendations

Large variability in the individual response to even the most-efficacious pain treatments is observed clinically, which has led to calls for a more personalized, tailored approach to treating patients with pain (ie, "precision pain medicine"). Precision pain medicine, currently an aspirational goal, would consist of empirically based algorithms that determine the optimal treatments, or treatment combinations, for specific patients (ie, targeting the right treatment, in the right dose, to the right patient, at the right time). Answering this question of "what works for whom" will certainly improve the clinical care of patients with pain. It may also support the success of novel drug development in pain, making it easier to identify novel treatments that work for certain patients and more accurately identify the magnitude of the treatment effect for those subgroups. Significant preliminary work has been done in this area, and analgesic trials are beginning to utilize precision pain medicine approaches such as stratified allocation on the basis of prespecified patient phenotypes using assessment methodologies such as quantitative sensory testing. Current major challenges within the field include: 1) identifying optimal measurement approaches to assessing patient characteristics that are most robustly and consistently predictive of inter-patient variation in specific analgesic treatment outcomes, 2) designing clinical trials that can identify treatment-by-phenotype interactions, and 3) selecting the most promising therapeutics to be tested in this way. This review surveys the current state of precision pain medicine, with a focus on drug treatments (which have been most-studied in a precision pain medicine context). It further presents a set of evidence-based recommendations for accelerating the application of precision pain methods in chronic pain research. PERSPECTIVE: Given the considerable variability in treatment outcomes for chronic pain, progress in precision pain treatment is critical for the field. An array of phenotypes and mechanisms contribute to chronic pain; this review summarizes current knowledge regarding which treatments are most effective for patients with specific biopsychosocial characteristics.

Identification of Resting-State Network Functional Connectivity and Brain Structural Signatures in Fibromyalgia Using a Machine Learning Approach

Abnormal resting-state functional connectivity (rs-FC) and brain structure have emerged as pathological hallmarks of fibromyalgia (FM). This study investigated and compared the accuracy of network rs-FC and brain structural features in identifying FM with a machine learning (ML) approach. Twenty-six FM patients and thirty healthy controls were recruited. Clinical presentation was measured by questionnaires. After MRI acquisitions, network rs-FC z-score and network-based gray matter volume matrices were exacted and preprocessed. The performance of feature selection and classification methods was measured. Correlation analyses between predictive features in final models and clinical data were performed. The combination of the recursive feature elimination (RFE) selection method and support vector machine (rs-FC data) or logistic regression (structural data), after permutation importance feature selection, showed high performance in distinguishing FM patients from pain-free controls, in which the rs-FC ML model outperformed the structural ML model (accuracy: 0.91 vs. 0.86, AUC: 0.93 vs. 0.88). The combined rs-FC and structural ML model showed the best performance (accuracy: 0.95, AUC: 0.95). Additionally, several rs-FC features in the final ML model correlated with FM's clinical data. In conclusion, ML models based on rs-FC and brain structural MRI features could effectively differentiate FM patients from pain-free subjects.

Automatic detection of pain using machine learning

Pain is one of the most common symptoms reported by individuals presenting to hospitals and clinics and is associated with significant disability and economic impacts; however, the ability to quantify and monitor pain is modest and typically accomplished through subjective self-report. Since pain is associated with stereotypical physiological alterations, there is potential for non-invasive, objective pain measurements through biosensors coupled with machine learning algorithms. In the current study, a physiological dataset associated with acute pain induction in healthy adults was leveraged to develop an algorithm capable of detecting pain in real-time and in natural field environments. Forty-one human subjects were exposed to acute pain through the cold pressor test while being monitored using electrocardiography. A series of respiratory and heart rate variability features in the time, frequency, and nonlinear domains were calculated and used to develop logistic regression classifiers of pain for two scenarios: (1) laboratory/clinical use with an F1 score of 81.9% and (2) field/ambulatory use with an F1 score of 79.4%. The resulting pain algorithms could be leveraged to quantify acute pain using data from a range of sources, such as ECG data in clinical settings or pulse plethysmography data in a growing number of consumer wearables. Given the high prevalence of pain worldwide and the lack of objective methods to quantify it, this approach has the potential to identify and better mitigate individual pain.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

Correcting cardiorespiratory noise in resting-state functional MRI data acquired in critically ill patients

Resting-state functional MRI is being used to develop diagnostic, prognostic and therapeutic biomarkers for critically ill patients with severe brain injuries. In studies of healthy volunteers and non-critically ill patients, prospective cardiorespiratory data are routinely collected to remove non-neuronal fluctuations in the resting-state functional MRI signal during analysis. However, the feasibility and utility of collecting cardiorespiratory data in critically ill patients on a clinical MRI scanner are unknown. We concurrently acquired resting-state functional MRI (repetition time = 1250 ms) and cardiac and respiratory data in 23 critically ill patients with acute severe traumatic brain injury and in 12 healthy control subjects. We compared the functional connectivity results from two approaches that are commonly used to correct cardiorespiratory noise: (i) denoising with cardiorespiratory data (i.e. image-based method for retrospective correction of physiological motion effects in functional MRI) and (ii) standard bandpass filtering. Resting-state functional MRI data in 7 patients could not be analysed due to imaging artefacts. In 6 of the remaining 16 patients (37.5%), cardiorespiratory data were either incomplete or corrupted. In patients (n = 10) and control subjects (n = 10), the functional connectivity results corrected with the image-based method for retrospective correction of physiological motion effects in functional MRI did not significantly differ from those corrected with bandpass filtering of 0.008-0.125 Hz. Collectively, these findings suggest that, in critically ill patients with severe traumatic brain injury, there is limited feasibility and utility to denoising the resting-state functional MRI signal with prospectively acquired cardiorespiratory data.

The missing mechanistic link: Improving behavioral treatment efficacy for pediatric chronic pain

Pediatric chronic pain is a significant global issue, with biopsychosocial factors contributing to the complexity of the condition. Studies have explored behavioral treatments for pediatric chronic pain, but these treatments have mixed efficacy for improving functional and psychological outcomes. Furthermore, the literature lacks an understanding of the biobehavioral mechanisms contributing to pediatric chronic pain treatment response. In this mini review, we focus on how neuroimaging has been used to identify biobehavioral mechanisms of different conditions and how this modality can be used in mechanistic clinical trials to identify markers of treatment response for pediatric chronic pain. We propose that mechanistic clinical trials, utilizing neuroimaging, are warranted to investigate how to optimize the efficacy of behavioral treatments for pediatric chronic pain patients across pain types and ages.

Role of Artificial Intelligence and Machine Learning in the prediction of the pain: A scoping systematic review

Artificial Intelligence in healthcare is growing quickly in diagnostics and treatment management. Despite the quantity and variety of studies its role in clinical care is not clear. To identify the evidence gaps and characteristics of the Artificial Intelligence and Machine Learning techniques in predicting/diagnosing the pain? Pubmed/Embase were searched from the inception to October 2021 for articles without any language restrictions specifically addressing the following: the accuracy of AI in pain considering Brain Imaging, Patient-reported measures, and Electrophysiology, the ability of AI to differentiate stratify severity/types of pain, the ability of AI to predict pain and lastly the most accurate AI technique for given inputs. All the included studies were on humans. Eight hundred forty abstracts were reviewed, and 23 articles were finally included. Identified records were independently screened and relevant data was extracted. We performed conceptual synthesis by grouping the studies using available concepts of AL/ML techniques in diagnosing pain. Then we summarized the number of features/physiological measurements. Structured tabulation synthesis was used to show patterns predictions along with a narrative commentary. A total of 23 articles, published between 2015 and 2020 from 12 countries were included. Most studies were experimental in design. The most common design was cross sectional. Chronic or acute pains were predicted more often. Compared to control, the pain prediction was in the range of 57%-96% by AI techniques. Support Vector Machine and deep learning showed higher accuracy for classifying pain. From this study, it can be inferred that AI/ML can be used to differentiate healthy controls from patients. It can also facilitate categorizing them into new and different clinical subgroups. Lastly, it can predict future pain. The limitations are with respect to studies done after the search period. AL/ ML has a supportive role in pain diagnostics.

Functional brain reconfiguration during sustained pain

Pain is constructed through complex interactions among multiple brain systems, but it remains unclear how functional brain networks are reconfigured over time while experiencing pain. Here, we investigated the time-varying changes in the functional brain networks during 20 min capsaicin-induced sustained orofacial pain. In the early stage, the orofacial areas of the primary somatomotor cortex were separated from other areas of the somatosensory cortex and integrated with subcortical and frontoparietal regions, constituting an extended brain network of sustained pain. As pain decreased over time, the subcortical and frontoparietal regions were separated from this brain network and connected to multiple cerebellar regions. Machine-learning models based on these network features showed significant predictions of changes in pain experience across two independent datasets (n = 48 and 74). This study provides new insights into how multiple brain systems dynamically interact to construct and modulate pain experience, advancing our mechanistic understanding of sustained pain.

Mindfulness-Based Stress Reduction, Cognitive Behavioral Therapy, and Acupuncture in Chronic Low Back Pain: Protocol for Two Linked Randomized Controlled Trials

BACKGROUND

Nonpharmacologic mind-body therapies have demonstrated efficacy in low back pain. However, the mechanisms underlying these therapies remain to be fully elucidated.

OBJECTIVE

In response to these knowledge gaps, the Stanford Center for Low Back Pain-a collaborative, National Institutes of Health P01-funded, multidisciplinary research center-was established to investigate the common and distinct biobehavioral mechanisms of three mind-body therapies for chronic low back pain: cognitive behavioral therapy (CBT) that is used to treat pain, mindfulness-based stress reduction (MBSR), and electroacupuncture. Here, we describe the design and implementation of the center structure and the associated randomized controlled trials for characterizing the mechanisms of chronic low back pain treatments.

METHODS

The multidisciplinary center is running two randomized controlled trials that share common resources for recruitment, enrollment, study execution, and data acquisition. We expect to recruit over 300 chronic low back pain participants across two projects and across different treatment arms within each project. The first project will examine pain-CBT compared with MBSR and a wait-list control group. The second project will examine real versus sham electroacupuncture. We will use behavioral, psychophysical, physical measure, and neuroimaging techniques to characterize the central pain modulatory and emotion regulatory systems in chronic low back pain at baseline and longitudinally. We will characterize how these interventions impact these systems, characterize the longitudinal treatment effects, and identify predictors of treatment efficacy.

RESULTS

Participant recruitment began on March 17, 2015, and will end in March 2023. Recruitment was halted in March 2020 due to COVID-19 and resumed in December 2021.

CONCLUSIONS

This center uses a comprehensive approach to study chronic low back pain. Findings are expected to significantly advance our understanding in (1) the baseline and longitudinal mechanisms of chronic low back pain, (2) the common and distinctive mechanisms of three mind-body therapies, and (3) predictors of treatment response, thereby informing future delivery of nonpharmacologic chronic low back pain treatments.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02503475; https://clinicaltrials.gov/ct2/show/NCT02503475.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/37823.

Toward a digital citizen lab for capturing data about alternative ways of self-managing chronic pain: An attitudinal user study

Background

Myriad psychosocial and cultural factors influence personal ways of coping with chronic pain (CP). Mobile health (mHealth) apps facilitate creation of citizen laboratories outside clinical frameworks. However, issues of safety, privacy and technostress must be addressed. This attitudinal user study aimed to assess whether persons with persistent pain (PwPP) would be open to sharing qualitative and quantitative data about their self-management of CP via mHealth platforms.

Methods

In March 2020, we invited PwPPs, their personal or medical caregivers, or those interested in the development of an app for researching alternative ways of self-managing CP to complete an anonymous survey. We formulated an attitudinal survey within the theoretical framework of stress to estimate whether the novelty, unpredictability, and risks of data-sharing via mHealth apps concerned users. Descriptive statistics (% Part/Group) were used to interpret the survey, and open comments were reflectively analyzed to identify emerging themes.

Results

Of 202 responses (June 2021), 127 identified as PwPPs (average age 43.86 ± 14.97; 100/127 female), and listed several primary and secondary CP diagnoses. In almost 90% of PwPPs, physical and emotional wellbeing were affected by CP. More than 90% of PwPPs used alternative therapies (acupuncture, homeopathy, massage therapy, etc.). Attitude toward mHealth apps were positive even though nearly half of PwPPs were unfamiliar with them. More than 72% of respondents were open to using a health-related app as a research tool for data collection in real life situations. Comprehensive data collection (especially about psychosocial factors) was the most important requirement. More respondents (especially medical professionals) were concerned about health hazards of misinformation communicated via health-related information and communication systems (maximum 80%) than about privacy (maximum 40%). Qualitative analyses revealed several promises and impediments to creation of data-sharing platforms for CP.

Conclusions

This study shows a general willingness among PwPPs to become partners in studying alternative pain management. Despite a generally positive attitude toward the concept of sharing complex personal data to advance research, heterogeneity of attitudes shaped by personal experiences must be considered. Our study underlines the need for any digital strategy for CP research to be person-centered and flexible.

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.

Biophysical Model: A Promising Method in the Study of the Mechanism of Propofol: A Narrative Review

The physiological and neuroregulatory mechanism of propofol is largely based on very limited knowledge. It is one of the important puzzling issues in anesthesiology and is of great value in both scientific and clinical fields. It is acknowledged that neural networks which are comprised of a number of neural circuits might be involved in the anesthetic mechanism. However, the mechanism of this hypothesis needs to be further elucidated. With the progress of artificial intelligence, it is more likely to solve this problem through using artificial neural networks to perform temporal waveform data analysis and to construct biophysical computational models. This review focuses on current knowledge regarding the anesthetic mechanism of propofol, an intravenous general anesthetic, by constructing biophysical computational models.

Artificial Intelligence and Computer Aided Diagnosis in Chronic Low Back Pain: A Systematic Review

Low Back Pain (LBP) is currently the first cause of disability in the world, with a significant socioeconomic burden. Diagnosis and treatment of LBP often involve a multidisciplinary, individualized approach consisting of several outcome measures and imaging data along with emerging technologies. The increased amount of data generated in this process has led to the development of methods related to artificial intelligence (AI), and to computer-aided diagnosis (CAD) in particular, which aim to assist and improve the diagnosis and treatment of LBP. In this manuscript, we have systematically reviewed the available literature on the use of CAD in the diagnosis and treatment of chronic LBP. A systematic research of PubMed, Scopus, and Web of Science electronic databases was performed. The search strategy was set as the combinations of the following keywords: “Artificial Intelligence”, “Machine Learning”, “Deep Learning”, “Neural Network”, “Computer Aided Diagnosis”, “Low Back Pain”, “Lumbar”, “Intervertebral Disc Degeneration”, “Spine Surgery”, etc. The search returned a total of 1536 articles. After duplication removal and evaluation of the abstracts, 1386 were excluded, whereas 93 papers were excluded after full-text examination, taking the number of eligible articles to 57. The main applications of CAD in LBP included classification and regression. Classification is used to identify or categorize a disease, whereas regression is used to produce a numerical output as a quantitative evaluation of some measure. The best performing systems were developed to diagnose degenerative changes of the spine from imaging data, with average accuracy rates >80%. However, notable outcomes were also reported for CAD tools executing different tasks including analysis of clinical, biomechanical, electrophysiological, and functional imaging data. Further studies are needed to better define the role of CAD in LBP care.

Comparison of test–retest reliability of BOLD and pCASL fMRI in a two-center study

Background

The establishment of test–retest reliability and reproducibility (TRR) is an important part of validating any research tool, including functional magnetic resonance imaging (fMRI). The primary objective of this study is to investigate the reliability of pseudo-Continuous Arterial Spin Labeling (pCASL) and Blood Oxygen Level Dependent (BOLD) fMRI data acquired across two different scanners in a sample of healthy adults. While single site/single scanner studies have shown acceptable repeatability, TRR of both in a practical multisite study occurring in two facilities spread out across the country with weeks to months between scans is critically needed.

Methods

Ten subjects were imaged with similar 3 T MRI scanners at the University of Pittsburgh and Massachusetts General Hospital. Finger-tapping and Resting-state data were acquired for both techniques. Analysis of the resting state data for functional connectivity was performed with the Functional Connectivity Toolbox, while analysis of the finger tapping data was accomplished with FSL. pCASL Blood flow data was generated using AST Toolbox. Activated areas and networks were identified via pre-defined atlases and dual-regression techniques. Analysis for TRR was conducted by comparing pCASL and BOLD images in terms of Intraclass correlation coefficients, Dice Similarity Coefficients, and repeated measures ANOVA.

Results

Both BOLD and pCASL scans showed strong activation and correlation between the two locations for the finger tapping tasks. Functional connectivity analyses identified elements of the default mode network in all resting scans at both locations. Multivariate repeated measures ANOVA showed significant variability between subjects, but no significant variability for location. Global CBF was very similar between the two scanning locations, and repeated measures ANOVA showed no significant differences between the two scanning locations.

Conclusions

The results of this study show that when similar scanner hardware and software is coupled with identical data analysis protocols, consistent and reproducible functional brain images can be acquired across sites. The variability seen in the activation maps is greater for pCASL versus BOLD images, as expected, however groups maps are remarkably similar despite the low number of subjects. This demonstrates that multi-site fMRI studies of task-based and resting state brain activity is feasible.

Abnormal Anatomical and Functional Connectivity of the Thalamo-sensorimotor Circuit in Chronic Low Back Pain: Resting-state Functional Magnetic Resonance Imaging and Diffusion Tensor Imaging Study

Thalamocortical dysfunction is thought to underlie the pathophysiology of chronic pain revealed by electroencephalographic studies. The thalamus serves as a primary relay center to transmit sensory information and motor impulses via dense connections with the somatosensory and motor cortex. In this study, diffusion tensor imaging (DTI) (probabilistic tractography) and resting-state functional magnetic resonance imaging (functional connectivity) were used to characterize the anatomical and functional integrity of the thalamo-sensorimotor pathway in chronic low back pain (cLBP). Fifty-four patients with cLBP and 54 healthy controls were included. The results suggested significantly increased anatomical connectivity of the left thalamo-motor pathway characterized by probabilistic tractography in patients with cLBP. Moreover, there was significantly altered resting-state functional connectivity (rsFC) of bilateral thalamo-motor/somatosensory pathways in patients with cLBP as compared to healthy controls. We also detected a significant correlation between pain intensity during the MRI scan and rsFC of the right thalamo-somatosensory pathway in cLBP. Our findings highlight the involvement of the thalamo-sensorimotor circuit in the pathophysiology of cLBP.

Intelligent monitoring of noxious stimulation during anaesthesia based on heart rate variability analysis

Research based on medical signals has received significant attention in recent years. If the patients' states can be accurately monitored based on medical signals, it greatly benefits both doctors and patients. This paper proposes a method to extract signal features from heart rate variability signals and classify patients' states using the long short-term memory network and enable effective monitoring of noxious stimulation. For data processing, the heart rate variability signal is decomposed and recombined by the empirical mode decomposition method, and the signal features of the noxious stimulation are extracted by the sliding time window method. Compared with the average accuracy of direct classifications, the classification accuracy based on the proposed method is proved more accurate. The model based on the extracted features proposed can realize the classification of consciousness and general anaesthesia with an accuracy rate of more than 90% and accurately estimate the occurrence of tracheal intubation stimulation. Furthermore, this study shows that combining the deep learning neural network with the extracted more effective signal features under different states and stresses can classify the states with high accuracy. Therefore, it is promising to apply the deep learning method in researching the autonomic nervous system.

The neurologic pain signature responds to nonsteroidal anti-inflammatory treatment vs placebo in knee osteoarthritis

Supplemental Digital Content is Available in the Text.

fMRI-based measures, validated for nociceptive pain, respond to acute osteoarthritis pain, are not sensitive to placebo, and are mild-to-moderately sensitive to naproxen.

Introduction:

Many drug trials for chronic pain fail because of high placebo response rates in primary endpoints. Neurophysiological measures can help identify pain-linked pathophysiology and treatment mechanisms. They can also help guide early stop/go decisions, particularly if they respond to verum treatment but not placebo. The neurologic pain signature (NPS), an fMRI-based measure that tracks evoked pain in 40 published samples and is insensitive to placebo in healthy adults, provides a potentially useful neurophysiological measure linked to nociceptive pain.

Objectives:

This study aims to validate the NPS in knee osteoarthritis (OA) patients and test the effects of naproxen on this signature.

Methods:

In 2 studies (50 patients, 64.6 years, 75% females), we (1) test the NPS and other control signatures related to negative emotion in knee OA pain patients; (2) test the effect of placebo treatments; and (3) test the effect of naproxen, a routinely prescribed nonsteroidal anti-inflammatory drug in OA.

Results:

The NPS was activated during knee pain in OA (d = 1.51, P < 0.001) and did not respond to placebo (d = 0.12, P = 0.23). A single dose of naproxen reduced NPS responses (vs placebo, NPS d = 0.34, P = 0.03 and pronociceptive NPS component d = 0.38, P = 0.02). Naproxen effects were specific for the NPS and did not appear in other control signatures.

Conclusion:

This study provides preliminary evidence that fMRI-based measures, validated for nociceptive pain, respond to acute OA pain, do not appear sensitive to placebo, and are mild-to-moderately sensitive to naproxen.

Machine Learning in Pain Medicine: An Up-To-Date Systematic Review

INTRODUCTION

Pain is the unpleasant sensation and emotional experience that leads to poor quality of life for millions of people worldwide. Considering the complexity in understanding the principles of pain and its significant impact on individuals and society, research focuses to deliver innovative pain relief methods and techniques. This review explores the clinical uses of machine learning (ML) for the diagnosis, classification, and management of pain.

METHODS

A systematic review of the current literature was conducted using the PubMed database library.

RESULTS

Twenty-six papers related to pain and ML research were included. Most of the studies used ML for effectively classifying the patients' level of pain, followed by use of ML for the prediction of manifestation of pain and for pain management. A less common reason for performing ML analysis was for the diagnosis of pain. The different approaches are thoroughly discussed.

CONCLUSION

ML is increasingly used in pain medicine and appears to be more effective compared to traditional statistical approaches in the diagnosis, classification, and management of pain.

Resting-state functional connectivity patterns are associated with worst pain duration in community-dwelling older adults

INTRODUCTION

An individual's chronic pain history is associated with brain morphometric alterations; but little is known about the association between pain history and brain function.

OBJECTIVES

This cross-sectional study aimed at determining how worst musculoskeletal pain intensity (WPINT) moderated the association between worst musculoskeletal pain duration (WPDUR) and brain resting-state magnetic resonance imaging functional connectivity (RSFC) in community-dwelling older adults (60-94 years, 75% females, 97% right-handed).

METHODS

Resting-state magnetic resonance imaging functional connectivity between region of interests was linearly regressed on WPDUR and WPINT. Predictions were compared with a control group's average RSFC (61-85 years, 47% females, 95% right-handed).

RESULTS

Three significant patterns emerged: (1) the positive association between WPDUR and RSFC between the medial prefrontal cortex, in the anterior salience network (SN), and bilateral lateral Brodmann area 6, in the visuospatial network (VSN), in participants with more severe chronic pain, resulting in abnormally lower RSFC for shorter WPDUR; (2) the negative association between WPDUR and RSFC between right VSN occipitotemporal cortex (lateral BA37 and visual V5) and bilateral VSN lateral Brodmann area 6, independently of WPINT, resulting in abnormally higher and lower RSFC for shorter and longer WPDUR, respectively; and (3) the positive association between WPDUR and the left hemisphere's salience network-default mode network connectivity (between the hippocampus and both dorsal insula and ventral or opercular BA44), independently of WPINT, resulting in abnormally higher RSFC for longer WPDUR.

CONCLUSION

Musculoskeletal effects on brain functional networks of general healthy individuals could accumulate until being observable at older ages. Results invite to examinations of these effects' impact on function and memory.

Machine learning approaches applied in spinal pain research

The purpose of this narrative review is to provide a critical reflection of how analytical machine learning approaches could provide the platform to harness variability of patient presentation to enhance clinical prediction. The review includes a summary of current knowledge on the physiological adaptations present in people with spinal pain. We discuss how contemporary evidence highlights the importance of not relying on single features when characterizing patients given the variability of physiological adaptations present in people with spinal pain. The advantages and disadvantages of current analytical strategies in contemporary basic science and epidemiological research are reviewed and we consider how analytical machine learning approaches could provide the platform to harness the variability of patient presentations to enhance clinical prediction of pain persistence or recurrence. We propose that machine learning techniques can be leveraged to translate a potentially heterogeneous set of variables into clinically useful information with the potential to enhance patient management.

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.

Prediction of pain intensity with uterine morphological features and brain microstructural and functional properties in women with primary dysmenorrhea

Primary dysmenorrhea (PDM), defined as painful menstrual cramps of uterine origin, could cause brain structural and functional changes after long-term menstrual pain. Here, we aimed to investigate the predictive value of uterine morphological features and microstructural/functional properties of the brain extracted from periovulatory phases for the intensity of menstrual pain as rated by women with PDM during their subsequent menstrual period. Forty-five women with PDM were recruited and classified into the high and mild pain intensity groups. Pelvic MRI was employed to extract the uterine texture features. White matter diffusion properties, grey matter and functional connectivity features were extracted as brain features. Multivariate logistic regression models with iteration optimization were built for classifying different pain intensity groups. Texture features from myometrium and uterine junction zone had outstanding prediction performance with an area under the receiver operating characteristic (AUC) of 0.96 (P < 0.05, permutation test), and diffusion properties along the thalamic fiber bundles were the most discriminative features with AUC of 0.95. Applying features from uterus and brain together, we could gain better prediction performance. Our results indicated that accumulated differences in menstrual pain were associated not only with uterine structure but also diffusion properties of thalamic-related fiber tracts, suggesting that treatment options of PDM patients may be expanded from only being able to manage pain in the uterus focusing on the functional/structural modifications of the pain processing system.

Regional brain morphology predicts pain relief in trigeminal neuralgia

•

Regional brain gray matter morphology robustly predict TN radiosurgery response.

•

Surface area ML model was 96.7% accurate, 100.0% sensitive, and 89.1% specific.

•

Top predictor for surface area model was contralateral superior frontal gyrus.

•

Cortical thickness ML model was 90.5% accurate, 93.5% sensitive, and 83.7% specific.

•

Top predictor for cortical thickness model was contralateral isthmus cingulate gyrus.

Background

Trigeminal neuralgia, a severe chronic neuropathic pain disorder, is widely believed to be amenable to surgical treatments. Nearly 20% of patients, however, do not have adequate pain relief after surgery. Objective tools for personalized pre-treatment prognostication of pain relief following surgical interventions can minimize unnecessary surgeries and thus are of substantial benefit for patients and clinicians.

Purpose

To determine if pre-treatment regional brain morphology-based machine learning models can prognosticate 1 year response to Gamma Knife radiosurgery for trigeminal neuralgia.

Methods

We used a data-driven approach that combined retrospective structural neuroimaging data and support vector machine-based machine learning to produce robust multivariate prediction models of pain relief following Gamma Knife radiosurgery for trigeminal neuralgia. Surgical response was defined as ≥ 75% pain relief 1 year post-treatment. We created two prediction models using pre-treatment regional brain gray matter morphology (cortical thickness or surface area) to distinguish responders from non-responders to radiosurgery. Feature selection was performed through sequential backwards selection algorithm. Model out-of-sample generalizability was estimated via stratified 10-fold cross-validation procedure and permutation testing.

Results

In 51 trigeminal neuralgia patients (35 responders, 16 non-responders), machine learning models based on pre-treatment regional brain gray matter morphology (14 regional surface areas or 13 regional cortical thicknesses) provided robust a priori prediction of surgical response. Cross-validation revealed the regional surface area model was 96.7% accurate, 100.0% sensitive, and 89.1% specific while the regional cortical thickness model was 90.5% accurate, 93.5% sensitive, and 83.7% specific. Permutation testing revealed that both models performed beyond pure chance (p < 0.001). The best predictor for regional surface area model and regional cortical thickness model was contralateral superior frontal gyrus and contralateral isthmus cingulate gyrus, respectively.

Conclusions

Our findings support the use of machine learning techniques in subsequent investigations of chronic neuropathic pain. Furthermore, our multivariate framework provides foundation for future development of generalizable, artificial intelligence-driven tools for chronic neuropathic pain treatments.

Prediction of Differential Pharmacologic Response in Chronic Pain Using Functional Neuroimaging Biomarkers and Support Vector Machine Algorithm - An Exploratory Study

Objective

There is increasing demand for prediction of chronic pain treatment outcomes using machine‐learning models, in order to improve suboptimal pain management. In this exploratory study, we used baseline brain functional connectivity patterns from chronic pain patients with fibromyalgia (FM) to predict whether a patient would respond differentially to either milnacipran or pregabalin, 2 drugs approved by the US Food and Drug Administration for the treatment of FM.

Methods

FM patients participated in 2 separate double‐blind, placebo‐controlled crossover studies, one evaluating milnacipran (n = 15) and one evaluating pregabalin (n = 13). Functional magnetic resonance imaging during rest was performed before treatment to measure intrinsic functional brain connectivity in several brain regions involved in pain processing. A support vector machine algorithm was used to classify FM patients as responders, defined as those with a ≥20% improvement in clinical pain, to either milnacipran or pregabalin.

Results

Connectivity patterns involving the posterior cingulate cortex (PCC) and dorsolateral prefrontal cortex (DLPFC) individually classified pregabalin responders versus milnacipran responders with 77% accuracy. Performance of this classification improved when both PCC and DLPFC connectivity patterns were combined, resulting in a 92% classification accuracy. These results were not related to confounding factors, including head motion, scanner sequence, or hardware status. Connectivity patterns failed to differentiate drug nonresponders across the 2 studies.

Conclusion

Our findings indicate that brain functional connectivity patterns used in a machine‐learning framework differentially predict clinical response to pregabalin and milnacipran in patients with chronic pain. These findings highlight the promise of machine learning in pain prognosis and treatment prediction.

Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes: The 2019 Literature Year in Review

Data science continues to be recognized and used within healthcare due to the increased availability of large data sets and advanced analytics. It can be challenging for nurse leaders to remain apprised of this rapidly changing landscape. In this article, we describe our findings from a scoping literature review of papers published in 2019 that use data science to explore, explain, and/or predict 15 phenomena of interest to nurses. Fourteen of the 15 phenomena were associated with at least one paper published in 2019. We identified the use of many contemporary data science methods (eg, natural language processing, neural networks) for many of the outcomes. We found many studies exploring Readmissions and Pressure Injuries. The topics of Artificial Intelligence/Machine Learning Acceptance, Burnout, Patient Safety, and Unit Culture were poorly represented. We hope that the studies described in this article help readers: (1) understand the breadth and depth of data science's ability to improve clinical processes and patient outcomes that are relevant to nurses and (2) identify gaps in the literature that are in need of exploration.

Breathlessness in COPD: linking symptom clusters with brain activity

Background

Current models of breathlessness often fail to explain disparities between patients' experiences of breathlessness and objective measures of lung function. While a mechanistic understanding of this discordance has thus far remained elusive, factors such as mood, attention and expectation have all been implicated as important modulators of breathlessness. Therefore, we have developed a model to better understand the relationships between these factors using unsupervised machine learning techniques. Subsequently we examined how expectation-related brain activity differed between these symptom-defined clusters of participants.

Methods

A cohort of 91 participants with mild-to-moderate chronic obstructive pulmonary disease (COPD) underwent functional brain imaging, self-report questionnaires and clinical measures of respiratory function. Unsupervised machine learning techniques of exploratory factor analysis and hierarchical cluster modelling were used to model brain–behaviour–breathlessness links.

Results

We successfully stratified participants across four key factors corresponding to mood, symptom burden and two capability measures. Two key groups resulted from this stratification, corresponding to high and low symptom burden. Compared with the high symptom burden group, the low symptom burden group demonstrated significantly greater brain activity within the anterior insula, a key region thought to be involved in monitoring internal bodily sensations (interoception).

Conclusions

This is the largest functional neuroimaging study of COPD to date, and is the first to provide a clear model linking brain, behaviour and breathlessness expectation. Furthermore, it was possible to stratify participants into groups, which then revealed differences in brain activity patterns. Together, these findings highlight the value of multimodal models of breathlessness in identifying behavioural phenotypes and for advancing understanding of differences in breathlessness burden.

Towards individualised treatments for chronic breathlessness with functional neuroimaging: revealing the factors underlying the breathlessness experience in COPDhttps://bit.ly/3a8fXPt