Nociception level index: do intra-operative values allow the prediction of acute postoperative pain?

Deep learning models for the prediction of acute postoperative pain in PACU for video-assisted thoracoscopic surgery

BACKGROUND

Postoperative pain is a prevalent symptom experienced by patients undergoing surgical procedures. This study aims to develop deep learning algorithms for predicting acute postoperative pain using both essential patient details and real-time vital sign data during surgery.

METHODS

Through a retrospective observational approach, we utilized Graph Attention Networks (GAT) and graph Transformer Networks (GTN) deep learning algorithms to construct the DoseFormer model while incorporating an attention mechanism. This model employed patient information and intraoperative vital signs obtained during Video-assisted thoracoscopic surgery (VATS) surgery to anticipate postoperative pain. By categorizing the static and dynamic data, the DoseFormer model performed binary classification to predict the likelihood of postoperative acute pain.

RESULTS

A total of 1758 patients were initially included, with 1552 patients after data cleaning. These patients were then divided into training set (n = 931) and testing set (n = 621). In the testing set, the DoseFormer model exhibited significantly higher AUROC (0.98) compared to classical machine learning algorithms. Furthermore, the DoseFormer model displayed a significantly higher F1 value (0.85) in comparison to other classical machine learning algorithms. Notably, the attending anesthesiologists' F1 values (attending: 0.49, fellow: 0.43, Resident: 0.16) were significantly lower than those of the DoseFormer model in predicting acute postoperative pain.

CONCLUSIONS

Deep learning model can predict postoperative acute pain events based on patients' basic information and intraoperative vital signs.

Progress in the validation of nociception monitoring in guiding intraoperative analgesic therapy

PURPOSE OF REVIEW

This article summarizes the current level of validation for several nociception monitors using a categorized validation process to facilitate the comparison of performance.

RECENT FINDINGS

Nociception monitors improve the detection of a shift in the nociception and antinociception balance during anesthesia, guiding perioperative analgesic therapy. A clear overview and comparison of the validation process for these monitors is missing.

RESULTS

Within a 2-year time-frame, we identified validation studies for four monitors [analgesia nociception index (ANI), nociception level monitor (NOL), surgical pleth index (SPI), and pupillometry]. We categorized these studies in one out of six mandatory validation steps: developmental studies, clinical validation studies, pharmacological validation studies, clinical utility studies, outcome improvement studies and economical evaluation studies. The current level of validation for most monitors is mainly focused on the first three categories, whereas ANI, NOL, and SPI advanced most in the availability of clinical utility studies and provide confirmation of a clinical outcome improvement. Analysis of economical value for public health effects is not yet publicly available for the studied monitors.

SUMMARY

This review proposes a stepwise structure for validation of new monitoring technology, which facilitates comparison between the level of validation of different devices and identifies the need for future research questions.

Depth of Anesthesia and Nociception Monitoring: Current State and Vision For 2050

Anesthesia objectives have evolved into combining hypnosis, amnesia, analgesia, paralysis, and suppression of the sympathetic autonomic nervous system. Technological improvements have led to new monitoring strategies, aimed at translating a qualitative physiological state into quantitative metrics, but the optimal strategies for depth of anesthesia (DoA) and analgesia monitoring continue to stimulate debate. Historically, DoA monitoring used patient's movement as a surrogate of awareness. Pharmacokinetic models and metrics, including minimum alveolar concentration for inhaled anesthetics and target-controlled infusion models for intravenous anesthesia, provided further insights to clinicians, but electroencephalography and its derivatives (processed EEG; pEEG) offer the potential for personalization of anesthesia care. Current studies appear to affirm that pEEG monitoring decreases the quantity of anesthetics administered, diminishes postanesthesia care unit duration, and may reduce the occurrence of postoperative delirium (notwithstanding the difficulties of defining this condition). Major trials are underway to further elucidate the impact on postoperative cognitive dysfunction. In this manuscript, we discuss the Bispectral (BIS) index, Narcotrend monitor, Patient State Index, entropy-based monitoring, and Neurosense monitor, as well as middle latency evoked auditory potential, before exploring how these technologies could evolve in the upcoming years. In contrast to developments in pEEG monitors, nociception monitors remain by comparison underdeveloped and underutilized. Just as with anesthetic agents, excessive analgesia can lead to harmful side effects, whereas inadequate analgesia is associated with increased stress response, poorer hemodynamic conditions and coagulation, metabolic, and immune system dysregulation. Broadly, 3 distinct monitoring strategies have emerged: motor reflex, central nervous system, and autonomic nervous system monitoring. Generally, nociceptive monitors outperform basic clinical vital sign monitoring in reducing perioperative opioid use. This manuscript describes pupillometry, surgical pleth index, analgesia nociception index, and nociception level index, and suggest how future developments could impact their use. The final section of this review explores the profound implications of future monitoring technologies on anesthesiology practice and envisages 3 transformative scenarios: helping in creation of an optimal analgesic drug, the advent of bidirectional neuron-microelectronic interfaces, and the synergistic combination of hypnosis and virtual reality.

[New Approaches in Perioperative Algesimetry]

The measurement of anaesthetic depth and muscle relaxation have been routine procedures during general anaesthesia for years. Quantification of intraoperative nociception, on the other hand, is still largely impossible. Various methods have been tested and commercialised for more than 10 years. However, a real breakthrough has not yet been achieved and the routine application of all methods available so far is not without problems. This article explains methodological similarities, but also points to specific aspects of various commercial solutions for perioperative algesimetry.

Validation of three nociception indices to predict immediate postoperative pain before emergence from general anaesthesia: a prospective double-blind, observational study

BACKGROUND

Nociception monitoring devices are designed to estimate nociception during general anaesthesia. We evaluated the predictive accuracy of heart rate and three nociception indices to predict postoperative pain before emergence from general anaesthesia.

METHODS

In patients undergoing trauma or orthopaedic surgery, HR, Surgical Pleth Index® (SPI), Pupillary Pain Index® (PPI), and Nociception Level® (NOL) were simultaneously recorded for 5 min after the end of surgery but before return of consciousness. After admission to the recovery room, pain scores were assessed regularly for 2 h. HR, SPI, PPI, and NOL were analysed for their predictive accuracy of postoperative pain and opioid consumption with assessment of area under the receiver operating characteristic (AUC) curves, Spearman rank-correlation coefficient, and regression modelling.

RESULTS

Data for 60 subjects were analysed. The AUC (95% confidence interval [95% CI]) of the predictive accuracy for moderate-to-severe postoperative pain differed between nociception indices (HR=0.46 [0.29-0.64], P=0.671; SPI=0.46 [0.31-0.61], P=0.621; PPI=0.52 [0.36-0.68], P=0.770; NOL=0.66 [0.51-0.81], P=0.038). In a multivariable logistic regression model, a higher predictive accuracy was found for a multivariable predictor combining NOL values with ASA physical status and information about use of regional anaesthesia (AUC=0.83 [0.72-0.94], P<0.001).

CONCLUSIONS

Heart rate, Surgical Pleth Index, Pupillary Pain Index, and Nociception Level measured before emergence from general anaesthesia do not yet have sufficient diagnostic accuracy for prediction of postoperative pain.

CLINICAL TRIAL REGISTRATION

NCT05063227.

Nociception Level Index-Guided Intraoperative Analgesia for Improved Postoperative Recovery: A Randomized Trial

BACKGROUND

Nociception is the physiological response to nociceptive stimuli, normally experienced as pain. During general anesthesia, patients experience and respond to nociceptive stimuli by increasing blood pressure and heart rate if not controlled by preemptive analgesia. The PMD-200 system from Medasense (Ramat Gan, Israel) evaluates the balance between nociceptive stimuli and analgesia during general anesthesia and generates the nociception level (NOL) index from a single finger probe. NOL is a unitless index ranging from 0 to 100, with values exceeding 25 indicating that nociception exceeds analgesia. We aimed to demonstrate that titrating intraoperative opioid administration to keep NOL <25 optimizes intraoperative opioid dosing. Specifically, we tested the hypothesis that pain scores during the initial 60 minutes of recovery are lower in patients managed with NOL-guided fentanyl than in patients given fentanyl per clinical routine.

METHODS

We conducted a randomized, single-center trial of patients having major abdominal open and laparoscopic surgeries. Patients were randomly assigned 1:1 to intraoperative NOL-guided fentanyl administration or fentanyl given per clinical routine. The primary outcome was pain score (0-10 verbal response scale) at 10-minute intervals during the initial 60 minutes of recovery. Our secondary outcome was a measure of adequate analgesia, defined as a pain score <5, assessed separately at each interval.

RESULTS

With a planned maximum sample size of 144, the study was stopped for futility after enrolling 72 patients from November 2020 to October 2021. Thirty-five patients were assigned to NOL-guided analgesic dosing and 37 to routine care. Patients in the NOL group spent significantly less time with a NOL index >25 (median reduction [95% confidence interval {CI}] of 14 [4-25] minutes) were given nearly twice as much intraoperative fentanyl (median [quartiles] 500 [330, 780] vs 300 [200, 330] µg), and required about half as much morphine in the recovery period (3.3 [0, 8] vs 7.7 [0, 13] mg). However, in the primary outcome analysis, NOL did not reduce pain scores in the first 60 minutes after awakening, assessed in a linear mixed effects model with mean (standard error [SE]) of 4.12 (0.59) for NOL and 4.04 (0.58) for routine care, and estimated difference in means of 0.08 (-1.43, 1.58), P = .895.

CONCLUSIONS

More intraoperative fentanyl was given in NOL-guided patients, but NOL guidance did not reduce initial postoperative pain scores.

Prediction of acute postoperative pain based on intraoperative nociception level (NOL) index values: the impact of machine learning-based analysis

The relationship between intraoperative nociception and acute postoperative pain is still not well established. The nociception level (NOL) Index (Medasense, Ramat Gan, Israel) uses a multiparametric approach to provide a 0-100 nociception score. The objective of the ancillary analysis of the NOLGYN study was to evaluate the ability of a machine-learning aglorithm to predict moderate to severe acute postoperative pain based on intraoperative NOL values. Our study uses the data from the NOLGYN study, a randomized controlled trial that evaluated the impact of NOL-guided intraoperative administration of fentanyl on overall fentanyl consumption compared to standard of care. Seventy patients (ASA class I-III, aged 18-75 years) scheduled for gynecological laparoscopic surgery were enrolled. Variables included baseline demographics, NOL reaction to incision or intubation, median NOL during surgery, NOL time-weighted average (TWA) above or under manufacturers' recommended thresholds (10-25), and percentage of surgical time spent with NOL > 25 or < 10. We evaluated different machine learning algorithms to predict postoperative pain. Performance was assessed using cross-validated area under the ROC curve (CV-AUC). Of the 66 patients analyzed, 42 (63.6%) experienced moderate to severe pain. NOL post-intubation (42.8 (31.8-50.6) vs. 34.8 (25.6-41.3), p = 0.05), median NOL during surgery (13 (11-15) vs. 11 (8-13), p = 0.027), percentage of surgical time spent with NOL > 25 (23% (18-18) vs. 20% (15-24), p = 0.036), NOL TWA < 10 (2.54 (2.1-3.0) vs. 2.86 (2.48-3.62), p = 0.044) and percentage of surgical time spent with NOL < 10 (41% (36-47) vs. 47% (40-55), p = 0.022) were associated with moderate to severe PACU pain. Corresponding ROC AUC for the prediction of moderate to severe PACU pain were 0.65 [0.51-0.79], 0.66 [0.52-0.81], 0.66 [0.52-0.79], 0.65 [0.51-0.79] and 0.67 [0.53-0.81]. Penalized logistic regression achieved the best performance with a 0.753 (0.718-0.788) CV-AUC. Our results, even if limited by the small number of patients, suggest that acute postoperative pain is better predicted by a multivariate machine-learning algorithm rather than individual intraoperative nociception variables. Further larger multicentric trials are highly recommended to better understand the relationship between intraoperative nociception and acute postoperative pain.Trial registration Registered on ClinicalTrials.gov in October 2018 (NCT03776838).

Evaluation of Nociception during Pediatric Surgery: A Topical Review

The association between intraoperative nociception and increased patient's morbidity is well established. However, hemodynamic parameters, such as heart rate and blood pressure, may result in an inadequate monitor of nociception during surgery. Over the last two decades, different devices have been marketed to "reliably" detect intraoperative nociception. Since the direct measure of nociception is impractical during surgery, these monitors measures nociception surrogates such as sympathetic and parasympathetic nervous systems responses (heart rate variability, pupillometry, skin conductance), electroencephalographic changes, and muscular reflex arc. Each monitor carries its own advantages and disadvantages. The manuscript aims to give an overview of the most up-to-date information available in the literature on current nociceptor monitors available in clinical practice, with particular focus on their applications in pediatrics.

Different perspectives for monitoring nociception during general anesthesia

Safe anesthesia is achieved using objective methods that estimate the patient’s state during different phases of surgery. A patient’s state under anesthesia is characterized by three major aspects, which are linked to the main effects produced by each of the families of anesthetic agents administered: hypnosis, analgesia, and muscular relaxation.

While quantification techniques designed to assess muscular relaxation under neuromuscular blocking agents have a relatively long history with a high degree of standardization and understanding (e.g., the train-of-four), the knowledge and techniques used to the depth of hypnosis assessment suffer from a lesser degree in both standardization and interpretation due to brain complexity.

The problem of standardization and interpretation in the analgesia and nociception assessment increases since it involves more systems, the central nervous system, and the autonomic nervous system.

This helps to explain why there are multiple a priori valid approaches to develop nociception monitoring from different interpretations and physiological bases of noxious stimuli processing. Thus, in this review, the current monitoring technologies clinically available for estimating a patient’s nociception under general anesthesia are described.

[Nociception monitoring : Method for intraoperative opioid control?]

The intraoperative dosing of opioids is a challenge in routine anesthesia as the potential effects of intraoperative overdosing and underdosing are not completely understood. In recent years an increasing number of monitors were approved, which were developed for the detection of intraoperative nociception and therefore should enable a better control of opioid titration. The nociception monitoring devices use either continuous hemodynamic, galvanic or thermal biosignals reflecting the balance between parasympathetic and sympathetic activity, measure the pupil dilatation reflex or the nociceptive flexor reflex as a reflexive response to application of standardized nociceptive stimulation. This review article presents the currently available nociception monitors. Most of these monitoring devices detect nociceptive stimulations with higher sensitivity and specificity than changes in heart rate, blood pressure or sedation depth monitoring devices. There are only few studies on the effect of opioid titration guided by nociception monitoring and the possible postoperative benefits of these devices. All nociception monitoring techniques are subject to specific limitations either due to perioperative confounders (e.g. hypovolemia) or special accompanying medical conditions (e.g. muscle relaxation). There is an ongoing discussion about the clinical relevance of nociceptive stimulation in general anesthesia and the effect on patient outcome. Initial results for individual monitor systems show a reduction in opioid consumption and in postoperative pain level. Nevertheless, current evidence does not enable the routine use of nociception monitoring devices to be recommended as a clear beneficial effect on long-term outcome has not yet been proven.