Machine learning in pain research

A machine learning-based framework for predicting postpartum chronic pain: a retrospective study

BACKGROUND

Postpartum chronic pain is prevalent, affecting many women after delivery. Machine learning algorithms have been widely used in predicting postoperative conditions. We investigated the prevalence of and risk factors for postpartum chronic pain, and aimed to develop a machine learning model for its prediction.

METHODS

Pregnant women in our tertiary hospital were screened from July 2021 to June 2022. Postoperative pain intensity was assessed using the numerical rating scale at 1, 3, and 6 months after delivery. Six machine learning algorithms were benchmarked using the nested resampling method, and their performance was evaluated based on classification error (CE). The algorithm with the best performance evaluation was used to establish the model for predicting chronic pain 6 months after delivery. Shapley additive explanations analysis was used to assess the contribution of each variable to the model.

RESULTS

A total of 1,398 postpartum women were included for analysis, among whom 383 developed chronic pain 6 months after delivery. The least absolute shrinkage selection operator identified five relevant factors: numerical rating scale at 3 days after delivery, body mass index before delivery, newborn weight, multiparous delivery, and back pain during gestation. The CEs for the algorithms were as follows: K-nearest neighbor, 0.212; logistic regression, 0.342; linear discriminant analysis, 0.343; naive Bayes, 0.346; ranger, 0.219; and extreme gradient boosting model, 0.147. The extreme gradient boosting model exhibited the best performance (CE = 0.147, F1 = 0.851) and was selected for model establishment. Visualization using Shapley additive explanations facilitated the interpretation of the influence of the five variables in the model.

CONCLUSIONS

The extreme gradient boosting algorithm, which incorporates five risk factors, demonstrated strong performance in predicting postpartum chronic pain.

TRIAL REGISTRATION

https//www.chictr.org.cn/ (ChiCTR2300070514).

Enhancing Chronic Pain Nursing Diagnosis Through Machine Learning: A Performance Evaluation

This study proposes an evaluation of the efficacy of machine learning algorithms in classifying chronic pain based on Italian nursing notes, contributing to the integration of artificial intelligence tools in healthcare within an Italian linguistic context. The research aimed to validate the nursing diagnosis of chronic pain and explore the potential of artificial intelligence (AI) in enhancing clinical decision-making in Italian healthcare settings. Three machine learning algorithms-XGBoost, gradient boosting, and BERT-were optimized through a grid search approach to identify the most suitable hyperparameters for each model. Therefore, the performance of the algorithms was evaluated and compared using Cohen's κ coefficient. This statistical measure assesses the level of agreement between the predicted classifications and the actual data labels. Results demonstrated XGBoost's superior performance, whereas BERT showed potential in handling complex Italian language structures despite data volume and domain specificity limitations. The study highlights the importance of algorithm selection in clinical applications and the potential of machine learning in healthcare, specifically addressing the challenges of Italian medical language processing. This work contributes to the growing field of artificial intelligence in nursing, offering insights into the challenges and opportunities of implementing machine learning in Italian clinical practice. Future research could explore integrating multimodal data, combining text analysis with physiological signals and imaging data, to create more comprehensive and accurate chronic pain classification models tailored to the Italian healthcare system.

Integrating multidimensional data analytics for precision diagnosis of chronic low back pain

Low back pain (LBP) is a leading cause of disability worldwide, with up to 25% of cases become chronic (cLBP). Whilst multi-factorial, the relative importance of contributors to cLBP remains unclear. We leveraged a comprehensive multi-dimensional data-set and machine learning-based variable importance selection to identify the most effective modalities for differentiating whether a person has cLBP. The dataset included questionnaire data, clinical and functional assessments, and spino-pelvic magnetic resonance imaging (MRI), encompassing a total of 144 parameters from 1,161 adults with (n = 512) and without cLBP (n = 649). Boruta and random forest were utilised for variable importance selection and cLBP classification respectively. A multimodal model including questionnaire, clinical, and MRI data was the most effective in differentiating people with and without cLBP. From this, the most robust variables (n = 9) were psychosocial factors, neck and hip mobility, as well as lower lumbar disc herniation and degeneration. This finding persisted in an unseen holdout dataset. Beyond demonstrating the importance of a multi-dimensional approach to cLBP, our findings will guide the development of targeted diagnostics and personalized treatment strategies for cLBP patients.

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.

Assessing signs of central sensitization: A critical review of physiological measures in experimentally induced secondary hyperalgesia

BACKGROUND AND OBJECTIVES

Central sensitization (CS) is believed to play a role in many chronic pain conditions. Direct non-invasive recording from single nociceptive neurons is not feasible in humans, complicating CS establishment. This review discusses how secondary hyperalgesia (SHA), considered a manifestation of CS, affects physiological measures in healthy individuals and if these measures could indicate CS. It addresses controversies about heat sensitivity changes, the role of tactile afferents in mechanical hypersensitivity and detecting SHA through electrical stimuli. Additionally, it reviews the potential of neurophysiological measures to indicate CS presence.

DATABASES AND DATA TREATMENT

Four databases, PubMed, ScienceDirect, Scopus and Cochrane Library, were searched using terms linked to 'hyperalgesia'. The search was limited to research articles in English conducted in humans until 2023.

RESULTS

Evidence for heat hyperalgesia in the SHA area is sparse and seems to depend on the experimental method used. Minimal or no involvement of tactile afferents in SHA was found. At the spinal level, the threshold of the nociceptive withdrawal reflex (RIII) is consistently reduced during experimentally induced SHA. The RIII area and the spinal somatosensory potential (N13-SEP) amplitude are modulated only with long-lasting nociceptive input. At the brain level, pinprick-evoked potentials within the SHA area are increased.

CONCLUSIONS

Mechanical pinprick hyperalgesia is the most reliable behavioural readout for SHA, while the RIII threshold is the most sensitive neurophysiological readout. Due to scarce data on reliability, sensitivity and specificity, none of the revised neurophysiological methods is currently suitable for CS identification at the individual level.

SIGNIFICANCE

Gathering evidence for CS in humans is a crucial research focus, especially with the increasing interest in concepts such as 'central sensitization-like pain' or 'nociplastic pain'. This review clarifies which readouts, among the different behavioural and neurophysiological proxies tested in experimental settings, can be used to infer the presence of CS in humans.

Is Functioning of Older Adults with Chronic Musculoskeletal Pain Related to Health Literacy?

We investigated the relationship between health literacy (HL) and functioning among older adults with and without chronic musculoskeletal pain (CMP). In a cross-sectional study, we assessed 121 older adults with CMP and 53 without pain using WHODAS 2.0 for functioning and the Newest Vital Sign for HL assessment. Cluster analysis identified groups based on functioning levels. A decision tree model was developed, to account for nonlinear interactions. We found a relationship of inadequate HL with lower functioning in older adults with CMP, particularly when aged over 70 and those younger but with lower education levels. Findings highlight the importance of screening HL among older adults with CMP and considering it for tailoring interventions.

Generalisation of EEG-Based Pain Biomarker Classification for Predicting Central Neuropathic Pain in Subacute Spinal Cord Injury

Background: The objective was to test the generalisability of electroencephalography (EEG) markers of future pain using two independent datasets. Methods: Datasets, A [N = 20] and B [N = 35], were collected from participants with subacute spinal cord injury who did not have neuropathic pain at the time of recording. In both datasets, some participants developed pain within six months, (PDP) will others did not (PNP). EEG features were extracted based on either band power or Higuchi fractal dimension (HFD). Three levels of generalisability were tested: (1) classification PDP vs. PNP in datasets A and B separately; (2) classification between groups in datasets A and B together; and (3) classification where one dataset (A or B) was used for training and testing, and the other for validation. A novel normalisation method was applied to HFD features. Results: Training and testing of individual datasets achieved classification accuracies of >80% using either feature set, and classification of joint datasets (A and B) achieved a maximum accuracy of 86.4% (HFD, support vector machine (SVM)). With normalisation and feature reduction (principal components), the validation accuracy was 66.6%. Conclusions: An SVM classifier with HFD features showed the best robustness, and normalisation improved the accuracy of predicting future neuropathic pain well above the chance level.

Unraveling the physiological and psychosocial signatures of pain by machine learning

BACKGROUND

Pain is a complex subjective experience, strongly impacting health and quality of life. Despite many attempts to find effective solutions, present treatments are generic, often unsuccessful, and present significant side effects. Designing individualized therapies requires understanding of multidimensional pain experience, considering physical and emotional aspects. Current clinical pain assessments, relying on subjective one-dimensional numeric self-reports, fail to capture this complexity.

METHODS

To this aim, we exploited machine learning to disentangle physiological and psychosocial components shaping the pain experience. Clinical, psychosocial, and physiological data were collected from 118 chronic pain and healthy participants undergoing 40 pain trials (4,697 trials).

FINDINGS

To understand the objective response to nociception, we classified pain from the physiological signals (accuracy >0.87), extracting the most important biomarkers. Then, using multilevel mixed-effects models, we predicted the reported pain, quantifying the mismatch between subjective level and measured physiological response. From these models, we introduced two metrics: TIP (subjective index of pain) and Φ (physiological index). These represent possible added value in the clinical process, capturing psychosocial and physiological pain dimensions, respectively. Patients with high TIP are characterized by frequent sick leave from work and increased clinical depression and anxiety, factors associated with long-term disability and poor recovery, and are indicated for alternative treatments, such as psychological ones. By contrast, patients with high Φ show strong nociceptive pain components and could benefit more from pharmacotherapy.

CONCLUSIONS

TIP and Φ, explaining the multidimensionality of pain, might provide a new tool potentially leading to targeted treatments, thereby reducing the costs of inefficient generic therapies.

FUNDING

RESC-PainSense, SNSF-MOVE-IT197271.

Machine learning and biological validation identify sphingolipids as potential mediators of paclitaxel-induced neuropathy in cancer patients

Background

Chemotherapy-induced peripheral neuropathy (CIPN) is a serious therapy-limiting side effect of commonly used anticancer drugs. Previous studies suggest that lipids may play a role in CIPN. Therefore, the present study aimed to identify the particular types of lipids that are regulated as a consequence of paclitaxel administration and may be associated with the occurrence of post-therapeutic neuropathy.

Methods

High-resolution mass spectrometry lipidomics was applied to quantify d=255 different lipid mediators in the blood of n=31 patients drawn before and after paclitaxel therapy for breast cancer treatment. A variety of supervised statistical and machine-learning methods was applied to identify lipids that were regulated during paclitaxel therapy or differed among patients with and without post-therapeutic neuropathy.

Results

Twenty-seven lipids were identified that carried relevant information to train machine learning algorithms to identify, in new cases, whether a blood sample was drawn before or after paclitaxel therapy with a median balanced accuracy of up to 90%. One of the top hits, sphinganine-1-phosphate (SA1P), was found to induce calcium transients in sensory neurons via the transient receptor potential vanilloid 1 (TRPV1) channel and sphingosine-1-phosphate receptors.SA1P also showed different blood concentrations between patients with and without neuropathy.

Conclusions

Present findings suggest a role for sphinganine-1-phosphate in paclitaxel-induced biological changes associated with neuropathic side effects. The identified SA1P, through its receptors, may provide a potential drug target for co-therapy with paclitaxel to reduce one of its major and therapy-limiting side effects.

Funding

This work was supported by the Deutsche Forschungsgemeinschaft (German Research Foundation, DFG, Grants SFB1039 A09 and Z01) and by the Fraunhofer Foundation Project: Neuropathic Pain as well as the Fraunhofer Cluster of Excellence for Immune-Mediated Diseases (CIMD). This work was also supported by the Leistungszentrum Innovative Therapeutics (TheraNova) funded by the Fraunhofer Society and the Hessian Ministry of Science and Arts. Jörn Lötsch was supported by the Deutsche Forschungsgemeinschaft (DFG LO 612/16-1).

Sensors and Devices Guided by Artificial Intelligence for Personalized Pain Medicine

Personalized pain medicine aims to tailor pain treatment strategies for the specific needs and characteristics of an individual patient, holding the potential for improving treatment outcomes, reducing side effects, and enhancing patient satisfaction. Despite existing pain markers and treatments, challenges remain in understanding, detecting, and treating complex pain conditions. Here, we review recent engineering efforts in developing various sensors and devices for addressing challenges in the personalized treatment of pain. We summarize the basics of pain pathology and introduce various sensors and devices for pain monitoring, assessment, and relief. We also discuss advancements taking advantage of rapidly developing medical artificial intelligence (AI), such as AI-based analgesia devices, wearable sensors, and healthcare systems. We believe that these innovative technologies may lead to more precise and responsive personalized medicine, greatly improved patient quality of life, increased efficiency of medical systems, and reducing the incidence of addiction and substance use disorders.

Resting-state frontal electroencephalography (EEG) biomarkers for detecting the severity of chronic neuropathic pain

Increasing evidence is present to enable pain measurement by using frontal channel EEG-based signals with spectral analysis and phase-amplitude coupling. To identify frontal channel EEG-based biomarkers for quantifying pain severity, we investigated band-power features to more complex features and employed various machine learning algorithms to assess the viability of these features. We utilized a public EEG dataset obtained from 36 patients with chronic pain during an eyes-open resting state and performed correlation analysis between clinically labelled pain scores and EEG features from Fp1 and Fp2 channels (EEG band-powers, phase-amplitude couplings (PAC), and its asymmetry features). We also conducted regression analysis with various machine learning models to predict patients' pain intensity. All the possible feature sets combined with five machine learning models (Linear Regression, random forest and support vector regression with linear, non-linear and polynomial kernels) were intensively checked, and regression performances were measured by adjusted R-squared value. We found significant correlations between beta power asymmetry (r = -0.375), gamma power asymmetry (r = -0.433) and low beta to low gamma coupling (r = -0.397) with pain scores while band power features did not show meaningful results. In the regression analysis, Support Vector Regression with a polynomial kernel showed the best performance (R squared value = 0.655), enabling the regression of pain intensity within a clinically usable error range. We identified the four most selected features (gamma power asymmetry, PAC asymmetry of theta to low gamma, low beta to low/high gamma). This study addressed the importance of complex features such as asymmetry and phase-amplitude coupling in pain research and demonstrated the feasibility of objectively observing pain intensity using the frontal channel-based EEG, that are clinically crucial for early intervention.

Uncertainty quantification in neural-network based pain intensity estimation

Improper pain management leads to severe physical or mental consequences, including suffering, a negative impact on quality of life, and an increased risk of opioid dependency. Assessing the presence and severity of pain is imperative to prevent such outcomes and determine the appropriate intervention. However, the evaluation of pain intensity is a challenging task because different individuals experience pain differently. To overcome this, many researchers in the field have employed machine learning models to evaluate pain intensity objectively using physiological signals. However, these efforts have primarily focused on pain point estimation, disregarding inherent uncertainty and variability in the data and model. A point estimate, which provides only partial information, is not sufficient for sound clinical decision-making. This study proposes a neural network-based method for objective pain interval estimation, and quantification of uncertainty. Our approach, which enables objective pain intensity estimation with desired confidence probabilities, affords clinicians a better understanding of a person's pain intensity. We explored three distinct algorithms: the bootstrap method, lower and upper bound estimation (LossL) optimized by genetic algorithm, and modified lower and upper bound estimation (LossS) optimized by gradient descent algorithm. Our empirical results demonstrate that LossS outperforms the other two by providing narrower prediction intervals. For 50%, 75%, 85%, and 95% prediction interval coverage probability, LossS provides average interval widths that are 22.4%, 7.9%, 16.7%, and 9.1% narrower than those of LossL, and 19.3%, 21.1%, 23.6%, and 26.9% narrower than those of bootstrap. As LossS outperforms, we assessed its performance in three different model-building approaches: (1) a generalized approach using a single model for the entire population, (2) a personalized approach with separate models for each individual, and (3) a hybrid approach with models for clusters of individuals. Results demonstrate that the hybrid model-building approach provides the best performance.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

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.

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

ABSTRACT

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

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

Introduction

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

Method

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

Results and discussion

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

Empirical comparison of deep learning models for fNIRS pain decoding

Introduction

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

Methods

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

Results

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

Discussion

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

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

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

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

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

Development and validation of machine learning based prediction model for postoperative pain risk after extraction of impacted mandibular third molars

Background

Predicting postoperative pain risk in patients with impacted mandibular third molar extractions is helpful in guiding clinical decision-making, enhancing perioperative pain management, and improving the patients' medical experience. This study aims to develop a prediction model based on machine learning algorithms to identify patients at high risk of postoperative pain after tooth extraction.

Methods

We conducted a prospective cohort study. Outpatients with impacted mandibular third molars were recruited and the outcome was defined as the NRS (Numerical Rating Scale) score of peak postoperative pain within 24 h after the operation ≥7, which is considered a high risk of postoperative pain. We compared the models built using nine different machine learning algorithms and conducted internal and time-series external validations to evaluate the model's predictive performances in terms of the area under the curve (AUC), accuracy, sensitivity, specificity, and F1-value.

Results

A total of 185 patients and 202 cases of impacted mandibular third molar data were included in this study. Five modeling variables were screened out using least absolute selection and shrinkage operator regression, including physician qualification, patient self-reported maximum pain sensitivity, OHI-S-CI, BMI, and systolic blood pressure. The overall performance of the random forest model was evaluated. The AUC, sensitivity, and specificity of the prediction model built using the random forest method were 0.879 (0.861-0.891), 0.857, and 0.846, respectively, for the training set and 0.724 (0.673-0.732), 0.667, and 0.600, respectively, for the time series validation set.

Conclusions

This study developed a machine learning-based postoperative pain risk prediction model for impacted mandibular third molar extraction, which is promising for providing a theoretical basis for better pain management to reduce postoperative pain after third molar extraction.

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

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

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

ABSTRACT

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

Parametric Modeling and Deep Learning for Enhancing Pain Assessment in Postanesthesia

OBJECTIVE

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

METHODS

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

RESULTS

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

CONCLUSION

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

SIGNIFICANCE

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

Automatic Variable Selection Algorithms in Prognostic Factor Research in Neck Pain

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

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.

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

OBJECTIVES

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

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

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

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

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

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

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

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

OBJECTIVES

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

DESIGN

Exploratory, cross-sectional design.

SETTING AND PARTICIPANTS

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

METHODS

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

MAIN OUTCOME MEASURES

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

RESULTS

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

CONCLUSIONS

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

Altered habenular connectivity in chronic low back pain: An fMRI and machine learning study

The habenula has been implicated in the pathogenesis of pain and analgesia, while evidence concerning its function in chronic low back pain (cLBP) is sparse. This study aims to investigate the resting-state functional connectivity (rsFC) and effective connectivity of the habenula in 52 patients with cLBP and 52 healthy controls (HCs) and assess the feasibility of distinguishing cLBP from HCs based on connectivity by machine learning methods. Our results indicated significantly enhanced rsFC of the habenula-left superior frontal cortex (SFC), habenula-right thalamus, and habenula-bilateral insular pathways as well as decreased rsFC of the habenula-pons pathway in cLBP patients compared to HCs. Dynamic causal modelling revealed significantly enhanced effective connectivity from the right thalamus to right habenula in cLBP patients compared with HCs. RsFC of the habenula-SFC was positively correlated with pain intensities and Hamilton Depression scores in the cLBP group. RsFC of the habenula-right insula was negatively correlated with pain duration in the cLBP group. Additionally, the combination of the rsFC of the habenula-SFC, habenula-thalamus, and habenula-pons pathways could reliably distinguish cLBP patients from HCs with an accuracy of 75.9% by support vector machine, which was validated in an independent cohort (N = 68, accuracy = 68.8%, p = .001). Linear regression and random forest could also distinguish cLBP and HCs in the independent cohort (accuracy = 73.9 and 55.9%, respectively). Overall, these findings provide evidence that cLBP may be associated with abnormal rsFC and effective connectivity of the habenula, and highlight the promise of machine learning in chronic pain discrimination.

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

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

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

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

Artificial Intelligence in Musculoskeletal Conditions

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

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

CONTEXT

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

OBJECTIVES

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

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

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

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

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

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

OBJECTIVE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

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

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

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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

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

BACKGROUND

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

RESEARCH QUESTION

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

METHODS

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

RESULTS

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

SIGNIFICANCE

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

Improving Pain Assessment Using Vital Signs and Pain Medication for Patients With Sickle Cell Disease: Retrospective Study

BACKGROUND

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

OBJECTIVE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

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

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

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

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

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

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

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

BACKGROUND

Persistent postsurgical neuropathic pain (PPSNP) can occur after intraoperative damage to somatosensory nerves, with a prevalence of 29-57% in breast cancer surgery. Proteomics is an active research field in neuropathic pain and the first results support its utility for establishing diagnoses or finding therapy strategies.

METHODS

57 women (30 non-PPSNP/27 PPSNP) who had experienced a surgeon-verified intercostobrachial nerve injury during breast cancer surgery, were examined for patterns in 74 serum proteomic markers that allowed discrimination between subgroups with or without PPSNP. Serum samples were obtained both before and after surgery.

RESULTS

Unsupervised data analyses, including principal component analysis and self-organizing maps of artificial neurons, revealed patterns that supported a data structure consistent with pain-related subgroup (non-PPSPN vs. PPSNP) separation. Subsequent supervised machine learning-based analyses revealed 19 proteins (CD244, SIRT2, CCL28, CXCL9, CCL20, CCL3, IL.10RA, MCP.1, TRAIL, CCL25, IL10, uPA, CCL4, DNER, STAMPB, CCL23, CST5, CCL11, FGF.23) that were informative for subgroup separation. In cross-validated training and testing of six different machine-learned algorithms, subgroup assignment was significantly better than chance, whereas this was not possible when training the algorithms with randomly permuted data or with the protein markers not selected. In particular, sirtuin 2 emerged as a key protein, presenting both before and after breast cancer treatments in the PPSNP compared with the non-PPSNP subgroup.

CONCLUSIONS

The identified proteins play important roles in immune processes such as cell migration, chemotaxis, and cytokine-signaling. They also have considerable overlap with currently known targets of approved or investigational drugs. Taken together, several lines of unsupervised and supervised analyses pointed to structures in serum proteomics data, obtained before and after breast cancer surgery, that relate to neuroinflammatory processes associated with the development of neuropathic pain after an intraoperative nerve lesion.