Prediction of postoperative opioid analgesia using clinical-experimental parameters and electroencephalography

Moving towards the use of artificial intelligence in pain management

BACKGROUND AND OBJECTIVE

While the development of artificial intelligence (AI) technologies in medicine has been significant, their application to acute and chronic pain management has not been well characterized. This systematic review aims to provide an overview of the current state of AI in acute and chronic pain management.

DATABASES AND DATA TREATMENT

This review was registered with PROSPERO (ID# CRD42022307017), the international registry for systematic reviews. The search strategy was prepared by a librarian and run in four electronic databases (Embase, Medline, Central, and Web of Science). Collected articles were screened by two reviewers. Included studies described the use of AI for acute and chronic pain management.

RESULTS

From the 17,601 records identified in the initial search, 197 were included in this review. Identified applications of AI were described for treatment planning as well as treatment delivery. Described uses include prediction of pain, forecasting of individualized responses to treatment, treatment regimen tailoring, image-guidance for procedural interventions and self-management tools. Multiple domains of AI were used including machine learning, computer vision, fuzzy logic, natural language processing and expert systems.

CONCLUSION

There is growing literature regarding applications of AI for pain management, and their clinical use holds potential for improving patient outcomes. However, multiple barriers to their clinical integration remain including lack validation of such applications in diverse patient populations, missing infrastructure to support these tools and limited provider understanding of AI.

SIGNIFICANCE

This review characterizes current applications of AI for pain management and discusses barriers to their clinical integration. Our findings support continuing efforts directed towards establishing comprehensive systems that integrate AI throughout the patient care continuum.

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.

Impact of genetic variants on fentanyl metabolism in major breast surgery patients: a candidate gene association study

AIM

The study aimed to examine the association of two selected candidate SNPs rs2242480 (CYP3A4) and rs1045642 (ABCB1) with metabolic ratio of plasma norfentanyl to fentanyl concentrations in patients undergoing major breast surgeries.

METHODS

The retrospective cross-sectional study was done in 257 female patients. DNA extraction, genotyping of selected SNPs, and drug levels measurement were employed.

RESULTS

A total of 257 female patients were recruited with no loss to follow up. There was no significant association between the two mentioned SNPs and the metabolic ratio (p value > 0.05). As an exploratory analysis, there was a moderately significant negative correlation between metabolic ratio and pupillary constriction to fentanyl (r = -0.27; p < 0.001). There was also a weak but significant positive correlation between metabolic ratio and time for first analgesia in the postoperative period (r = 0.17; p = 0.01).

CONCLUSION

There was no significant association with the selected candidate SNPs in CYP3A4 and ABCB1 genes and metabolic ratio of norfentanyl to fentanyl in South Indian patients undergoing major breast surgery.

Enhanced labor pain monitoring using machine learning and ECG waveform analysis for uterine contraction-induced pain

OBJECTIVES

This study aims to develop an innovative approach for monitoring and assessing labor pain through ECG waveform analysis, utilizing machine learning techniques to monitor pain resulting from uterine contractions.

METHODS

The study was conducted at National Taiwan University Hospital between January and July 2020. We collected a dataset of 6010 ECG samples from women preparing for natural spontaneous delivery (NSD). The ECG data was used to develop an ECG waveform-based Nociception Monitoring Index (NoM). The dataset was divided into training (80%) and validation (20%) sets. Multiple machine learning models, including LightGBM, XGBoost, SnapLogisticRegression, and SnapDecisionTree, were developed and evaluated. Hyperparameter optimization was performed using grid search and five-fold cross-validation to enhance model performance.

RESULTS

The LightGBM model demonstrated superior performance with an AUC of 0.96 and an accuracy of 90%, making it the optimal model for monitoring labor pain based on ECG data. Other models, such as XGBoost and SnapLogisticRegression, also showed strong performance, with AUC values ranging from 0.88 to 0.95.

CONCLUSIONS

This study demonstrates that the integration of machine learning algorithms with ECG data significantly enhances the accuracy and reliability of labor pain monitoring. Specifically, the LightGBM model exhibits exceptional precision and robustness in continuous pain monitoring during labor, with potential applicability extending to broader healthcare settings.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT04461704.

Artificial Intelligence in Anesthetic Care: A Survey of Physician Anesthesiologists

BACKGROUND

This study explored physician anesthesiologists' knowledge, exposure, and perceptions of artificial intelligence (AI) and their associations with attitudes and expectations regarding its use in clinical practice. The findings highlight the importance of understanding anesthesiologists' perspectives for the successful integration of AI into anesthesiology, as AI has the potential to revolutionize the field.

METHODS

A cross-sectional survey of 27,056 US physician anesthesiologists was conducted to assess their knowledge, perceptions, and expectations regarding the use of AI in clinical practice. The primary outcome measured was attitude toward the use of AI in clinical practice, with scores of 4 or 5 on a 5-point Likert scale indicating positive attitudes. The anticipated impact of AI on various aspects of professional work was measured using a 3-point Likert scale. Logistic regression was used to explore the relationship between participant responses and attitudes toward the use of AI in clinical practice.

RESULTS

A 2021 survey of 27,056 US physician anesthesiologists received 1086 responses (4% response rate). Most respondents were male (71%), active clinicians (93%) under 45 (34%). A majority of anesthesiologists (61%) had some knowledge of AI and 48% had a positive attitude toward using AI in clinical practice. While most respondents believed that AI can improve health care efficiency (79%), timeliness (75%), and effectiveness (69%), they are concerned that its integration in anesthesiology could lead to a decreased demand for anesthesiologists (45%) and decreased earnings (45%). Within a decade, respondents expected AI would outperform them in predicting adverse perioperative events (83%), formulating pain management plans (67%), and conducting airway exams (45%). The absence of algorithmic transparency (60%), an ambiguous environment regarding malpractice (47%), and the possibility of medical errors (47%) were cited as significant barriers to the use of AI in clinical practice. Respondents indicated that their motivation to use AI in clinical practice stemmed from its potential to enhance patient outcomes (81%), lower health care expenditures (54%), reduce bias (55%), and boost productivity (53%). Variables associated with positive attitudes toward AI use in clinical practice included male gender (odds ratio [OR], 1.7; P < .001), 20+ years of experience (OR, 1.8; P < .01), higher AI knowledge (OR, 2.3; P = .01), and greater AI openness (OR, 10.6; P < .01). Anxiety about future earnings was associated with negative attitudes toward AI use in clinical practice (OR, 0.54; P < .01).

CONCLUSIONS

Understanding anesthesiologists' perspectives on AI is essential for the effective integration of AI into anesthesiology, as AI has the potential to revolutionize the field.

Correlation between spinal cord stimulation analgesia and cortical dynamics in pain management

AIM

Spinal cord stimulation (SCS) is an effective method to treat neuropathic pain. It is necessary to identify the responders of SCS analgesia before implantation. The aim of this study is to investigate the relationship between the cortical dynamics and SCS analgesia responders in pain management.

METHODS

Resting-state EEG recording was performed in patients who underwent short-term implantation of spinal cord stimulation for pain therapy. We then did spectral analysis to capture the pattern of cortical oscillation between neuromodulation therapy analgesia responders and nonresponders.

RESULTS

About 58.3% (14 out of 24) of participants were considered as analgesia responders, with average visual analogue scores reduction of 4.8 ± 1.0 after surgery, and 2.1 ± 0.7 for the nonresponder subgroup, respectively. The alpha oscillation was significantly enhanced in responder cohort compared with nonresponders. We also observed an increasing spectral power of gamma band in responders. Furthermore, the attenuation of pain severity was significantly correlated with the global alpha oscillation activity (r = 0.60, P = 0.002). Likely, positive and significant correlation was found between the pain relief and gamma activity (r = 0.58, P = 0.003).

CONCLUSIONS

Distinct pattern of neural oscillation is associated with the analgesic effect of spinal cord stimulation in pain management, enhancement of cortical alpha and gamma oscillation may be a predictor of analgesia responders.

Machine learning and EEG can classify passive viewing of discrete categories of visual stimuli but not the observation of pain

Previous studies have demonstrated the potential of machine learning (ML) in classifying physical pain from non-pain states using electroencephalographic (EEG) data. However, the application of ML to EEG data to categorise the observation of pain versus non-pain images of human facial expressions or scenes depicting pain being inflicted has not been explored. The present study aimed to address this by training Random Forest (RF) models on cortical event-related potentials (ERPs) recorded while participants passively viewed faces displaying either pain or neutral expressions, as well as action scenes depicting pain or matched non-pain (neutral) scenarios. Ninety-one participants were recruited across three samples, which included a model development group (n = 40) and a cross-subject validation group (n = 51). Additionally, 25 participants from the model development group completed a second experimental session, providing a within-subject temporal validation sample. The analysis of ERPs revealed an enhanced N170 component in response to faces compared to action scenes. Moreover, an increased late positive potential (LPP) was observed during the viewing of pain scenes compared to neutral scenes. Additionally, an enhanced P3 response was found when participants viewed faces displaying pain expressions compared to neutral expressions. Subsequently, three RF models were developed to classify images into faces and scenes, neutral and pain scenes, and neutral and pain expressions. The RF model achieved classification accuracies of 75%, 64%, and 69% for cross-validation, cross-subject, and within-subject classifications, respectively, along with reasonably calibrated predictions for the classification of face versus scene images. However, the RF model was unable to classify pain versus neutral stimuli above chance levels when presented with subsequent tasks involving images from either category. These results expand upon previous findings by externally validating the use of ML in classifying ERPs related to different categories of visual images, namely faces and scenes. The results also indicate the limitations of ML in distinguishing pain and non-pain connotations using ERP responses to the passive viewing of visually similar images.

Impact of Genetic Variants on Postoperative Pain and Fentanyl Dose Requirement in Patients Undergoing Major Breast Surgery: A Candidate Gene Association Study

BACKGROUND

Postoperative analgesia is crucial for the early and effective recovery of patients undergoing surgery. Although postoperative multimodal analgesia is widely practiced, opioids such as fentanyl are still one of the best analgesics. The analgesic response of fentanyl varies widely among individuals, probably due to genetic and nongenetic factors. Among genetic factors, single nucleotide polymorphisms (SNPs) may influence its analgesic response by altering the structure or function of genes involved in nociceptive, fentanyl pharmacodynamic, and pharmacokinetic pathways. Thus, it is necessary to comprehensively ascertain if the SNPs present in the aforementioned pathways are associated with interindividual differences in fentanyl requirement. In this study, we evaluated the association between 10 candidate SNPs in 9 genes and 24-hour postoperative fentanyl dose (primary outcome) and also with postoperative pain scores and time for first analgesia (secondary outcomes).

METHODS

A total of 257 South Indian women, aged 18-70 years, with American Society of Anesthesiologists (ASA) physical status I-III, undergoing major breast surgery under general anesthesia, were included in the study. Patients were genotyped for candidate SNPs using real-time polymerase chain reaction. All patients received a standardized intravenous fentanyl infusion through a patient-controlled analgesic (PCA) pump, and the 24-hour postoperative fentanyl dose requirement was measured using PCA.

RESULTS

The median 24-hour postoperative fentanyl requirement was higher in rs1799971 carriers (G/G versus A/A + A/G-620 μg [500-700] vs 460 μg [400-580]) with a geometric mean (GM) ratio of 1.91 (95% confidence interval [CI], 1.071-1.327). The median 24-hour pain scores were higher in rs4680 carriers (A/G + A/A versus G/G-34 [30-38] vs 31 [30-38]) with a GM ratio of 1.059 (95% CI, 1.018-1.101) and were lower in rs1045642 carriers (A/A + A/G versus G/G-34 [30-38] vs 30 [30-34]) with a GM ratio of 0.936 (95% CI, 0.889-0.987). The median time for first analgesic was lower in rs734784 carriers [C/C versus T/T + C/T-240 minutes (180-270) vs 240 minutes (210-270)] with a GM ratio of 0.902 (95% CI, 0.837-0.972). Five of 9 clinical factors, namely, history of diabetes, hypertension, hypothyroidism, anesthesia duration, and intraoperative fentanyl requirement were associated with different outcomes individually ( P < .05) and were used to adjust the respective associations.

CONCLUSIONS

The SNP opioid receptor mu-1 ( OPRM1 ) (rs1799971) was associated with higher postoperative fentanyl requirement in South Indian patients undergoing major breast surgery. Twenty-four hour postoperative pain scores were higher in catechol-O-methyl transferase ( COMT ) (rs4680) carriers and lower in ATP binding cassette subfamily B member 1 ( ABCB1 ) (rs1045642) carriers, whereas time for first analgesic was lower in potassium channel subunit 1 ( KCNS1 ) (rs734784) carriers. However, these exploratory findings must be confirmed in a larger study.

In search of a composite biomarker for chronic pain by way of EEG and machine learning: where do we currently stand?

Machine learning is becoming an increasingly common component of routine data analyses in clinical research. The past decade in pain research has witnessed great advances in human neuroimaging and machine learning. With each finding, the pain research community takes one step closer to uncovering fundamental mechanisms underlying chronic pain and at the same time proposing neurophysiological biomarkers. However, it remains challenging to fully understand chronic pain due to its multidimensional representations within the brain. By utilizing cost-effective and non-invasive imaging techniques such as electroencephalography (EEG) and analyzing the resulting data with advanced analytic methods, we have the opportunity to better understand and identify specific neural mechanisms associated with the processing and perception of chronic pain. This narrative literature review summarizes studies from the last decade describing the utility of EEG as a potential biomarker for chronic pain by synergizing clinical and computational perspectives.

Resting-state electroencephalography and magnetoencephalography as biomarkers of chronic pain: a systematic review

ABSTRACT

Reliable and objective biomarkers promise to improve the assessment and treatment of chronic pain. Resting-state electroencephalography (EEG) is broadly available, easy to use, and cost efficient and, therefore, appealing as a potential biomarker of chronic pain. However, results of EEG studies are heterogeneous. Therefore, we conducted a systematic review (PROSPERO CRD42021272622) of quantitative resting-state EEG and magnetoencephalography (MEG) studies in adult patients with different types of chronic pain. We excluded populations with severe psychiatric or neurologic comorbidity. Risk of bias was assessed using a modified Newcastle-Ottawa Scale. Semiquantitative data synthesis was conducted using modified albatross plots. We included 76 studies after searching MEDLINE, Web of Science Core Collection, Cochrane Central Register of Controlled Trials, and EMBASE. For cross-sectional studies that can serve to develop diagnostic biomarkers, we found higher theta and beta power in patients with chronic pain than in healthy participants. For longitudinal studies, which can yield monitoring and/or predictive biomarkers, we found no clear associations of pain relief with M/EEG measures. Similarly, descriptive studies that can yield diagnostic or monitoring biomarkers showed no clear correlations of pain intensity with M/EEG measures. Risk of bias was high in many studies and domains. Together, this systematic review synthesizes evidence on how resting-state M/EEG might serve as a diagnostic biomarker of chronic pain. Beyond, this review might help to guide future M/EEG studies on the development of pain biomarkers.

A systematic review of neurophysiological sensing for the assessment of acute pain

Pain is a complex and personal experience that presents diverse measurement challenges. Different sensing technologies can be used as a surrogate measure of pain to overcome these challenges. The objective of this review is to summarise and synthesise the published literature to: (a) identify relevant non-invasive physiological sensing technologies that can be used for the assessment of human pain, (b) describe the analytical tools used in artificial intelligence (AI) to decode pain data collected from sensing technologies, and (c) describe the main implications in the application of these technologies. A literature search was conducted in July 2022 to query PubMed, Web of Sciences, and Scopus. Papers published between January 2013 and July 2022 are considered. Forty-eight studies are included in this literature review. Two main sensing technologies (neurological and physiological) are identified in the literature. The sensing technologies and their modality (unimodal or multimodal) are presented. The literature provided numerous examples of how different analytical tools in AI have been applied to decode pain. This review identifies different non-invasive sensing technologies, their analytical tools, and the implications for their use. There are significant opportunities to leverage multimodal sensing and deep learning to improve accuracy of pain monitoring systems. This review also identifies the need for analyses and datasets that explore the inclusion of neural and physiological information together. Finally, challenges and opportunities for designing better systems for pain assessment are also presented.

Electroencephalography functional connectivity-A biomarker for painful polyneuropathy

BACKGROUND AND PURPOSE

Advanced analysis of electroencephalography (EEG) data has become an essential tool in brain research. Based solely on resting state EEG signals, a data-driven, predictive and explanatory approach is presented to discriminate painful from non-painful diabetic polyneuropathy (DPN) patients.

METHODS

Three minutes long, 64 electrode resting-state recordings were obtained from 180 DPN patients. The analysis consisted of a mixture of traditional, explanatory and machine learning analyses. First, the 10 functional bivariate connections best differentiating between painful and non-painful patients in each EEG band were identified and the relevant receiver operating characteristic was calculated. Later, those connections were correlated with selected clinical parameters.

RESULTS

Predictive analysis indicated that theta and beta bands contain most of the information required for discrimination between painful and non-painful polyneuropathy patients, with area under the receiver operating characteristic curve values of 0.93 for theta and 0.89 for beta bands. Assessing statistical differences between the average magnitude of functional connectivity values and clinical pain parameters revealed that painful DPN patients had significantly higher cortical functional connectivity than non-painful ones (p = 0.008 for theta and p = 0.001 for alpha bands). Moreover, intra-band analysis of individual significant functional connections revealed a positive correlation with average reported pain in the previous 3 months in all frequency bands.

CONCLUSIONS

Resting state EEG functional connectivity can serve as a highly accurate biomarker for the presence or absence of pain in DPN patients. This highlights the importance of the brain, in addition to the peripheral lesions, in generating the clinical pain picture. This tool can probably be extended to other pain syndromes.

Efficacy and Applications of Artificial Intelligence and Machine Learning Analyses in Total Joint Arthroplasty: A Call for Improved Reporting

BACKGROUND

There has been a considerable increase in total joint arthroplasty (TJA) research using machine learning (ML). Therefore, the purposes of this study were to synthesize the applications and efficacies of ML reported in the TJA literature, and to assess the methodological quality of these studies.

METHODS

PubMed, OVID/MEDLINE, and Cochrane libraries were queried in January 2021 for articles regarding the use of ML in TJA. Study demographics, topic, primary and secondary outcomes, ML model development and testing, and model presentation and validation were recorded. The TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) guidelines were used to assess the methodological quality.

RESULTS

Fifty-five studies were identified: 31 investigated clinical outcomes and resource utilization; 11, activity and motion surveillance; 10, imaging detection; and 3, natural language processing. For studies reporting the area under the receiver operating characteristic curve (AUC), the median AUC (and range) was 0.80 (0.60 to 0.97) among 26 clinical outcome studies, 0.99 (0.83 to 1.00) among 6 imaging-based studies, and 0.88 (0.76 to 0.98) among 3 activity and motion surveillance studies. Twelve studies compared ML to logistic regression, with 9 (75%) reporting that ML was superior. The average number of TRIPOD guidelines met was 11.5 (range: 5 to 18), with 38 (69%) meeting greater than half of the criteria. Presentation and explanation of the full model for individual predictions and assessments of model calibration were poorly reported (<30%).

CONCLUSIONS

The performance of ML models was good to excellent when applied to a wide variety of clinically relevant outcomes in TJA. However, reporting of certain key methodological and model presentation criteria was inadequate. Despite the recent surge in TJA literature utilizing ML, the lack of consistent adherence to reporting guidelines needs to be addressed to bridge the gap between model development and clinical implementation.

Postoperative breakthrough pain in paediatric cardiac surgery not reduced by increased morphine concentrations

BACKGROUND

Morphine is commonly used for postoperative analgesia in children. Here we studied the pharmacodynamics of morphine in children after cardiac surgery receiving protocolized morphine.

METHODS

Data on morphine rescue requirements guided by validated pain scores in children (n = 35, 3-36 months) after cardiac surgery receiving morphine as loading dose (100 μg kg^-1) with continuous infusion (40 μg kg^-1 h^-1) from a previous study on morphine pharmacokinetics were analysed using repeated time-to-event (RTTE) modelling.

RESULTS

During the postoperative period (38 h (IQR 23-46)), 130 morphine rescue events (4 (IQR 1-5) per patient) mainly occurred in the first 24 h (107/130) at a median morphine concentration of 29.5 ng ml^-1 (range 7-180 ng ml^-1). In the RTTE model, the hazard of rescue morphine decreased over time (half-life 18 h; P < 0.001), while the hazard for rescue morphine (21.9% at 29.5 ng ml^-1) increased at higher morphine concentrations (P < 0.001).

CONCLUSIONS

In this study on protocolized morphine analgesia in children, rescue morphine was required at a wide range of morphine concentrations and further increase of the morphine concentration did not lead to a decrease in hazard. Future studies should focus on a multimodal approach using other opioids or other analgesics to treat breakthrough pain in children.

IMPACT

In children receiving continuous morphine infusion, administration of rescue morphine is an indicator for insufficient effect or an event. Morphine rescue events were identified at a wide range of morphine concentrations upon a standardized pain protocol consisting of continuous morphine infusion and morphine as rescue boluses. The expected number of rescue morphine events was found to increase at higher morphine concentrations. Instead of exploring more aggressive morphine dosing, future research should focus on a multimodal approach to treat breakthrough pain in children.

Quantifying the pharmacodynamics of morphine in the treatment of postoperative pain in preverbal children

While the pharmacokinetics of morphine in children have been studied extensively, little is known about the pharmacodynamics of morphine in this population. Here, we quantified the concentration‐effect relationship of morphine for postoperative pain in preverbal children between 0 and 3 years of age. For this, we applied item response theory modeling in the pharmacokinetic/pharmacodynamic analysis of COMFORT‐Behavior (COMFORT‐B) scale data from 2 previous clinical studies. In the model, we identified a sigmoid maximal efficacy model for the effect of morphine and found that in 26% of children, increasing morphine concentrations were not associated with lower pain scores (nonresponders to morphine up‐titration). In responders to morphine up‐titration, the COMFORT‐B score slowly decreases with increasing morphine concentrations at morphine concentrations >20 ng/mL. In nonresponding children, no decrease in COMFORT‐B score is expected. In general, lower baseline COMFORT‐B scores (2.1 points on average) in younger children (postnatal age <10.3 days) were found. Based on the model, we conclude that the percentage of children at a desirable COMFORT‐B score is maximized at a morphine concentration between 5 and 30 ng/mL for children aged <10 days, and between 5 and 40 ng/mL for children >10 days. These findings support a dosing regimen previously suggested by Krekels et al, which would put >95% of patients within this morphine target concentration range at steady state. Our modeling approach provides a promising platform for pharmacodynamic research of analgesics and sedatives in children.

Novel Analgesic Index for Postoperative Pain Assessment Based on a Photoplethysmographic Spectrogram and Convolutional Neural Network: Observational Study

BACKGROUND

Although commercially available analgesic indices based on biosignal processing have been used to quantify nociception during general anesthesia, their performance is low in conscious patients. Therefore, there is a need to develop a new analgesic index with improved performance to quantify postoperative pain in conscious patients.

OBJECTIVE

This study aimed to develop a new analgesic index using photoplethysmogram (PPG) spectrograms and a convolutional neural network (CNN) to objectively assess pain in conscious patients.

METHODS

PPGs were obtained from a group of surgical patients for 6 minutes both in the absence (preoperatively) and in the presence (postoperatively) of pain. Then, the PPG data of the latter 5 minutes were used for analysis. Based on the PPGs and a CNN, we developed a spectrogram-CNN index for pain assessment. The area under the curve (AUC) of the receiver-operating characteristic curve was measured to evaluate the performance of the 2 indices.

RESULTS

PPGs from 100 patients were used to develop the spectrogram-CNN index. When there was pain, the mean (95% CI) spectrogram-CNN index value increased significantly-baseline: 28.5 (24.2-30.7) versus recovery area: 65.7 (60.5-68.3); P<.01. The AUC and balanced accuracy were 0.76 and 71.4%, respectively. The spectrogram-CNN index cutoff value for detecting pain was 48, with a sensitivity of 68.3% and specificity of 73.8%.

CONCLUSIONS

Although there were limitations to the study design, we confirmed that the spectrogram-CNN index can efficiently detect postoperative pain in conscious patients. Further studies are required to assess the spectrogram-CNN index's feasibility and prevent overfitting to various populations, including patients under general anesthesia.

TRIAL REGISTRATION

Clinical Research Information Service KCT0002080; https://cris.nih.go.kr/cris/search/search_result_st01.jsp?seq=6638.

The effectiveness of an oral opioid rescue medication algorithm for postoperative pain management compared to PCIA : A cohort analysis

Background

Standard protocols or algorithms are considered essential to ensure adequate analgesia. Germany has widely adopted postoperative protocols for pain management including oral opioids for rescue medication, but the effectiveness of such protocols has only been evaluated longitudinally in a before and after setting. The aim of this cohort analysis was to compare the effectiveness of an oral opioid rescue medication algorithm for postoperative management of pain to the gold standard of patient-controlled intravenous analgesia (PCIA).

Material and methods

This study compared cohorts of patients of two prospective observational studies undergoing elective total hip replacement. After surgery patients received piritramide to achieve a pain score of ≤3 on the numeric rating scale (NRS 0–10). A protocol was started consisting of oral long-acting oxycodone and ibuprofen (basic analgesia). Cohort 1 (C1, 126 patients) additionally received an oral opioid rescue medication (hydromorphone) when reporting pain >3 on the NRS. Cohort 2 (C2, 88 patients) was provided with an opioid by PCIA (piritramide) for opioid rescue medication. Primary endpoints were pain intensity at rest, during movement, and maximum pain intensity within the first 24 h postoperative. Secondary endpoints were opioid consumption, functional outcome and patient satisfaction with pain management.

Results

Pain during movement and maximum pain intensity were higher in C1 compared to C2: pain on movement median 1st–3rd quartile: 6 (3.75–8) vs. 5 (3–7), p = 0.023; maximum pain intensity: 7 (5–9) vs. 5 (3–8), p = 0.008. There were no differences in pain intensity at rest or between women and men in either group. The mean opioid consumption in all patients (combined PACU, baseline, and rescue medication; mean ± SD mg ME) was 126.6 ± 51.8 mg oral ME (median 120 (87.47–154.25) mg ME). Total opioid consumption was lower in C1 than C2 (117 ± 46 mg vs 140 ± 56 mg, p = 0.002) due to differences in rescue opioids (C1: 57 ± 37 mg ME, C2: 73 ± 43 mg ME, p = 0.006, Z = −2.730). Basic analgesia opioid use was comparable (C1: 54 ± 31 mg ME, C2: 60 ± 36 mg ME, p = 0.288, Z = −1.063). There were no differences in respect to the addition of non-opioids and reported quality of mobilization, sleep, frequency of nausea and vomiting, or general satisfaction with pain management.

Conclusion

In this study PCIA provided a better reduction of pain intensity, when compared to a standardized protocol with oral opioid rescue medication. This effect was associated with increased opioid consumption. There were no differences in frequencies of opioid side effects. This study was a retrospective analysis of two cohorts of a major project. As with all retrospective studies, our analysis has several limitations to consider. Data can only represent the observation of clinical practice. It cannot reflect the quality of a statement of a randomized controlled trial. Observational studies do not permit conclusions on causal relationships.

Artificial Intelligence in Anesthesiology: Current Techniques, Clinical Applications, and Limitations

Artificial intelligence has been advancing in fields including anesthesiology. This scoping review of the intersection of artificial intelligence and anesthesia research identified and summarized six themes of applications of artificial intelligence in anesthesiology: (1) depth of anesthesia monitoring, (2) control of anesthesia, (3) event and risk prediction, (4) ultrasound guidance, (5) pain management, and (6) operating room logistics. Based on papers identified in the review, several topics within artificial intelligence were described and summarized: (1) machine learning (including supervised, unsupervised, and reinforcement learning), (2) techniques in artificial intelligence (e.g., classical machine learning, neural networks and deep learning, Bayesian methods), and (3) major applied fields in artificial intelligence.The implications of artificial intelligence for the practicing anesthesiologist are discussed as are its limitations and the role of clinicians in further developing artificial intelligence for use in clinical care. Artificial intelligence has the potential to impact the practice of anesthesiology in aspects ranging from perioperative support to critical care delivery to outpatient pain management.

Beyond the Randomized Clinical Trial: Innovative Data Science to Close the Pediatric Evidence Gap

Despite the application of advanced statistical and pharmacometric approaches to pediatric trial data, a large pediatric evidence gap still remains. Here, we discuss how to collect more data from children by using real-world data from electronic health records, mobile applications, wearables, and social media. The large datasets collected with these approaches enable and may demand the use of artificial intelligence and machine learning to allow the data to be analyzed for decision making. Applications of this approach are presented, which include the prediction of future clinical complications, medical image analysis, identification of new pediatric end points and biomarkers, the prediction of treatment nonresponders, and the prediction of placebo-responders for trial enrichment. Finally, we discuss how to bring machine learning from science to pediatric clinical practice. We conclude that advantage should be taken of the current opportunities offered by innovations in data science and machine learning to close the pediatric evidence gap.

Sensor Technologies to Manage the Physiological Traits of Chronic Pain: A Review

Non-oncologic chronic pain is a common high-morbidity impairment worldwide and acknowledged as a condition with significant incidence on quality of life. Pain intensity is largely perceived as a subjective experience, what makes challenging its objective measurement. However, the physiological traces of pain make possible its correlation with vital signs, such as heart rate variability, skin conductance, electromyogram, etc., or health performance metrics derived from daily activity monitoring or facial expressions, which can be acquired with diverse sensor technologies and multisensory approaches. As the assessment and management of pain are essential issues for a wide range of clinical disorders and treatments, this paper reviews different sensor-based approaches applied to the objective evaluation of non-oncological chronic pain. The space of available technologies and resources aimed at pain assessment represent a diversified set of alternatives that can be exploited to address the multidimensional nature of pain.

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

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

Analgesic consumption trajectories in 8975 patients 1 year after fast-track total hip or knee arthroplasty

BACKGROUND

Persistent or increased long-term opioid consumption has previously been described following total hip- (THA) and knee arthroplasty (TKA). However, detailed information on postoperative analgesic consumption trajectories and risk factors associated with continued need of analgesics in fast-track THA and TKA is sparse.

METHODS

This is a descriptive multicentre study in primary unilateral fast-track THA or TKA with prospective data on patient characteristics and information on reimbursement entitled dispensed prescriptions of paracetamol, non-steroidal anti-inflammatory drugs, opioids, anticonvulsants and antidepressants 1 month preoperatively and 1 year postoperatively. Patients were stratified according to preoperative opioid use. Postoperative analgesic consumption trajectories were stratified as increased, decreased or no use compared to the preoperative period.

RESULTS

Of 8975 patients (4849 THA/4126 TKA), 33.9% had relevant reimbursed prescriptions 9-12 months postoperatively. Of 2136 (23.8%) patients with preoperative opioid use, 3.4% had unchanged opioid consumption at 9-12 months postoperatively. However, increased opioid consumption after 9-12 months occurred in 17.6 (TKA) and 10.2% (THA) compared to 9.9 and 6.3% in opioid-naive TKA and THA patients, respectively. Increased NSAID and paracetamol use was seen in 11.5 and 12.4% of all patients. Preoperative analgesic use (any), TKA, psychiatric disorder, tobacco abuse, cardiac disease and use of walking aids were associated with increased opioid consumption.

CONCLUSION

Continued and increased opioid and other analgesic use occur in a clinically significant proportion of fast-track TKA and THA patients 9-12 months postoperatively, suggesting treatment failure and need for early intervention. Preoperative risk assessment may allow identification of patients in risk of increased postoperative opioid consumption.

SIGNIFICANCE

We found a considerable fraction of patients with continued or increased opioid consumption 9-12 months after fast-track THA and TKA. Increase in opioid consumption was more frequent in preoperative opioid users than opioid-naive patients, but a pattern of increased analgesic consumption was present across all analgesics. Our data demonstrate a need for increased focus on long-term analgesic strategies and postoperative follow-up after THA and TKA, especially in preoperative opioid users.

Exploration of the Pathophysiology of Chronic Pain Using Quantitative EEG Source Localization

Chronic pain affects more than 35% of the US adult population representing a major public health imperative. Currently, there are no objective means for identifying the presence of pain, nor for quantifying pain severity. Through a better understanding of the pathophysiology of pain, objective indicators of pain might be forthcoming. Brain mechanisms mediating the painful state were imaged in this study, using source localization of the EEG. In a population of 77 chronic pain patients, significant overactivation of the "Pain Matrix" or pain network, was found in brain regions including, the anterior cingulate, anterior and posterior insula, parietal lobule, thalamus, S1, and dorsolateral prefrontal cortex (DLPFC), consistent with those reported with conventional functional imaging, and extended to include the mid and posterior cingulate, suggesting that the increased temporal resolution of electrophysiological measures may allow a more precise identification of the pain network. Significant differences between those who self-report high and low pain were reported for some of the regions of interest (ROIs), maximally on left hemisphere in the DLPFC, suggesting encoding of pain intensity occurs in a subset of pain network ROIs. Furthermore, a preliminary multivariate logistic regression analysis was used to select quantitative-EEG features which demonstrated a highly significant predictive relationship of self-reported pain scores. Findings support the potential to derive a quantitative measure of the severity of pain using information extracted from a multivariate descriptor of the abnormal overactivation. Furthermore, the frequency specific (theta/low alpha band) overactivation in the regions reported, while not providing direct evidence, are consistent with a model of thalamocortical dysrhythmia as the potential mechanism of the neuropathic painful condition.

Prediction of opioid dose in cancer pain patients using genetic profiling: not yet an option with support vector machine learning

OBJECTIVE

Use of opioids for pain management has increased over the past decade; however, inadequate analgesic response is common. Genetic variability may be related to opioid efficacy, but due to the many possible combinations and variables, statistical computations may be difficult. This study investigated whether data processing with support vector machine learning could predict required opioid dose in cancer pain patients, using genetic profiling. Eighteen single nucleotide polymorphisms (SNPs) within the µ and δ opioid receptor genes and the catechol-O-methyltransferase gene were selected for analysis.

RESULTS

Data from 1237 cancer pain patients were included in the analysis. Support vector machine learning did not find any associations between the assessed SNPs and opioid dose in cancer pain patients, and hence, did not provide additional information regarding prediction of required opioid dose using genetic profiling.