Machine learning approach to predict postoperative opioid requirements in ambulatory surgery patients

Machine learning: implications and applications for ambulatory anesthesia

PURPOSE OF REVIEW

This review explores the timely and relevant applications of machine learning in ambulatory anesthesia, focusing on its potential to optimize operational efficiency, personalize risk assessment, and enhance patient care.

RECENT FINDINGS

Machine learning models have demonstrated the ability to accurately forecast case durations, Post-Anesthesia Care Unit (PACU) lengths of stay, and risk of hospital transfers based on preoperative patient and procedural factors. These models can inform case scheduling, resource allocation, and preoperative evaluation. Additionally, machine learning can standardize assessments, predict outcomes, improve handoff communication, and enrich patient education.

SUMMARY

Machine learning has the potential to revolutionize ambulatory anesthesia practice by optimizing efficiency, personalizing care, and improving quality and safety. However, limitations such as algorithmic opacity, data biases, reproducibility issues, and adoption barriers must be addressed through transparent, participatory design principles and ongoing validation to ensure responsible innovation and incremental adoption.

Predicting Postoperative Pain and Opioid Use with Machine Learning Applied to Longitudinal Electronic Health Record and Wearable Data

BACKGROUND

 Managing acute postoperative pain and minimizing chronic opioid use are crucial for patient recovery and long-term well-being.

OBJECTIVES

 This study explored using preoperative electronic health record (EHR) and wearable device data for machine-learning models that predict postoperative acute pain and chronic opioid use.

METHODS

 The study cohort consisted of approximately 347 All of Us Research Program participants who underwent one of eight surgical procedures and shared EHR and wearable device data. We developed four machine learning models and used the Shapley additive explanations (SHAP) technique to identify the most relevant predictors of acute pain and chronic opioid use.

RESULTS

 The stacking ensemble model achieved the highest accuracy in predicting acute pain (0.68) and chronic opioid use (0.89). The area under the curve score for severe pain versus other pain was highest (0.88) when predicting acute postoperative pain. Values of logistic regression, random forest, extreme gradient boosting, and stacking ensemble ranged from 0.74 to 0.90 when predicting postoperative chronic opioid use. Variables from wearable devices played a prominent role in predicting both outcomes.

CONCLUSION

 SHAP detection of individual risk factors for severe pain can help health care providers tailor pain management plans. Accurate prediction of postoperative chronic opioid use before surgery can help mitigate the risk for the outcomes we studied. Prediction can also reduce the chances of opioid overuse and dependence. Such mitigation can promote safer and more effective pain control for patients during their recovery.

Public Health Informatics and the Perioperative Physician: Looking to the Future

The role of informatics in public health has increased over the past few decades, and the coronavirus disease 2019 (COVID-19) pandemic has underscored the critical importance of aggregated, multicenter, high-quality, near-real-time data to inform decision-making by physicians, hospital systems, and governments. Given the impact of the pandemic on perioperative and critical care services (eg, elective procedure delays; information sharing related to interventions in critically ill patients; regional bed-management under crisis conditions), anesthesiologists must recognize and advocate for improved informatic frameworks in their local environments. Most anesthesiologists receive little formal training in public health informatics (PHI) during clinical residency or through continuing medical education. The COVID-19 pandemic demonstrated that this knowledge gap represents a missed opportunity for our specialty to participate in informatics-related, public health-oriented clinical care and policy decision-making. This article briefly outlines the background of PHI, its relevance to perioperative care, and conceives intersections with PHI that could evolve over the next quarter century.

The association of intraoperative opioid dose with postanesthesia care unit outcomes in children: a retrospective study

PURPOSE

In children, the relationship between the dose of intraoperative opioid and postoperative outcomes is unclear. We examined the relationship between intraoperative opioid dose and postanesthesia care unit (PACU) pain scores and opioid and antiemetic administrations.

METHODS

We performed a single-institution retrospective cohort study. Patients who were aged < 19 yr, had an American Society of Anesthesiologists Physical Status of I-III, were undergoing one of 11 procedures under general anesthesia and without regional anesthesia, and who were admitted to the PACU were included. Patients were analyzed by quartiles of total intraoperative opioid dose using multivariable regression, adjusting for confounders including procedure. An exploratory analysis of opioid-free anesthetics was also performed.

RESULTS

Three thousand, seven hundred and thirty-three cases were included, and the mean age of included patients was 8.3 yr. After adjustment, there were no significant differences between the lowest and higher quartiles for first conscious pain score, mean pain score, PACU opioid dose, or PACU length of stay; in addition, estimated differences were small. Patients in higher quartiles were estimated to be more likely to receive antiemetics, significantly so for those in the second quartile. Patients in the lowest quartile received significantly more intraoperative nonopioid analgesics. In the exploratory analysis, no significant difference in PACU pain scores was found in cases without intraoperative opioids.

CONCLUSIONS

Children who received lower doses of intraoperative opioids did not have worse PACU pain outcomes but required fewer antiemetics and received greater numbers of nonopioid analgesics intraoperatively. These findings suggest that lower doses of intraoperative opioids may be administered to children as long as other analgesics are used.

Machine Learning Algorithms Predict Long-Term Postoperative Opioid Misuse: A Systematic Review

INTRODUCTION

A steadily rising opioid pandemic has left the US suffering significant social, economic, and health crises. Machine learning (ML) domains have been utilized to predict prolonged postoperative opioid (PPO) use. This systematic review aims to compile all up-to-date studies addressing such algorithms' use in clinical practice.

METHODS

We searched PubMed/MEDLINE, EMBASE, CINAHL, and Web of Science using the keywords "machine learning," "opioid," and "prediction." The results were limited to human studies with full-text availability in English. We included all peer-reviewed journal articles that addressed an ML model to predict PPO use by adult patients.

RESULTS

Fifteen studies were included with a sample size ranging from 381 to 112898, primarily orthopedic-surgery-related. Most authors define a prolonged misuse of opioids if it extends beyond 90 days postoperatively. Input variables ranged from 9 to 23 and were primarily preoperative. Most studies developed and tested at least two algorithms and then enhanced the best-performing model for use retrospectively on electronic medical records. The best-performing models were decision-tree-based boosting algorithms in 5 studies with AUC ranging from .81 to .66 and Brier scores ranging from .073 to .13, followed second by logistic regression classifiers in 5 studies. The topmost contributing variable was preoperative opioid use, followed by depression and antidepressant use, age, and use of instrumentation.

CONCLUSIONS

ML algorithms have demonstrated promising potential as a decision-supportive tool in predicting prolonged opioid use in post-surgical patients. Further validation studies would allow for their confident incorporation into daily clinical practice.

Use of Artificial Intelligence in the Advancement of Breast Surgery and Implications for Breast Reconstruction: A Narrative Review

BACKGROUND

Breast reconstruction is a pivotal part of the recuperation process following a mastectomy and aims to restore both the physical aesthetic and emotional well-being of breast cancer survivors. In recent years, artificial intelligence (AI) has emerged as a revolutionary technology across numerous medical disciplines. This narrative review of the current literature and evidence analysis explores the role of AI in the domain of breast reconstruction, outlining its potential to refine surgical procedures, enhance outcomes, and streamline decision making.

METHODS

A systematic search on Medline (via PubMed), Cochrane Library, Web of Science, Google Scholar, Clinical Trials, and Embase databases from January 1901 to June 2023 was conducted.

RESULTS

By meticulously evaluating a selection of recent studies and engaging with inherent challenges and prospective trajectories, this review spotlights the promising role AI plays in advancing the techniques of breast reconstruction. However, issues concerning data quality, privacy, and ethical considerations pose hurdles to the seamless integration of AI in the medical field.

CONCLUSION

The future research agenda comprises dataset standardization, AI algorithm refinement, and the implementation of prospective clinical trials and fosters cross-disciplinary partnerships. The fusion of AI with other emergent technologies like augmented reality and 3D printing could further propel progress in breast surgery.

Predictive models for fentanyl dose requirement and postoperative pain using clinical and genetic factors in patients undergoing major breast surgery

ABSTRACT

Fentanyl exhibits interindividual variability in its dose requirement due to various nongenetic and genetic factors such as single nucleotide polymorphisms (SNPs). This study aims to develop and cross-validate robust predictive models for postoperative fentanyl analgesic requirement and other related outcomes in patients undergoing major breast surgery. Data regarding genotypes of 10 candidate SNPs, cold pain test (CPT) scores, pupillary response to fentanyl (PRF), and other common clinical characteristics were recorded from 257 patients undergoing major breast surgery. Predictive models for 24-hour fentanyl requirement, 24-hour pain scores, and time for first analgesic (TFA) in the postoperative period were developed using 4 different algorithms: generalised linear regression model, linear support vector machine learning (SVM-Linear), random forest (RF), and Bayesian regularised neural network. The variant genotype of OPRM1 (rs1799971) and higher CPT scores were associated with higher 24-hour postoperative fentanyl consumption, whereas higher PRF and history of hypertension were associated with lower fentanyl requirement. The variant allele of COMT (rs4680) and higher CPT scores were associated with 24-hour postoperative pain scores. The variant genotype of CTSG (rs2070697), higher intraoperative fentanyl use, and higher CPT scores were associated with significantly lower TFA. The predictive models for 24-hour postoperative fentanyl requirement, pain scores, and TFA had R-squared values of 0.313 (SVM-Linear), 0.434 (SVM-Linear), and 0.532 (RF), respectively. We have developed and cross-validated predictive models for 24-hour postoperative fentanyl requirement, 24-hour postoperative pain scores, and TFA with satisfactory performance characteristics and incorporated them in a novel web application.

A Neural Network Model Using Pain Score Patterns to Predict the Need for Outpatient Opioid Refills Following Ambulatory Surgery: Algorithm Development and Validation

BACKGROUND

Expansion of clinical guidance tools is crucial to identify patients at risk of requiring an opioid refill after outpatient surgery.

OBJECTIVE

The objective of this study was to develop machine learning algorithms incorporating pain and opioid features to predict the need for outpatient opioid refills following ambulatory surgery.

METHODS

Neural networks, regression, random forest, and a support vector machine were used to evaluate the data set. For each model, oversampling and undersampling techniques were implemented to balance the data set. Hyperparameter tuning based on k-fold cross-validation was performed, and feature importance was ranked based on a Shapley Additive Explanations (SHAP) explainer model. To assess performance, we calculated the average area under the receiver operating characteristics curve (AUC), F1-score, sensitivity, and specificity for each model.

RESULTS

There were 1333 patients, of whom 144 (10.8%) refilled their opioid prescription within 2 weeks after outpatient surgery. The average AUC calculated from k-fold cross-validation was 0.71 for the neural network model. When the model was validated on the test set, the AUC was 0.75. The features with the highest impact on model output were performance of a regional nerve block, postanesthesia care unit maximum pain score, postanesthesia care unit median pain score, active smoking history, and total perioperative opioid consumption.

CONCLUSIONS

Applying machine learning algorithms allows providers to better predict outcomes that require specialized health care resources such as transitional pain clinics. This model can aid as a clinical decision support for early identification of at-risk patients who may benefit from transitional pain clinic care perioperatively in ambulatory surgery.

Evaluation of machine learning models as decision aids for anesthesiologists

Machine Learning (ML) models have been developed to predict perioperative clinical parameters. The objective of this study was to determine if ML models can serve as decision aids to improve anesthesiologists' prediction of peak intraoperative glucose values and postoperative opioid requirements. A web-based tool was used to present actual surgical case and patient information to 10 practicing anesthesiologists. They were asked to predict peak glucose levels and post-operative opioid requirements for 100 surgical patients with and without presenting ML model estimations of peak glucose and opioid requirements. The accuracies of the anesthesiologists' estimates with and without ML estimates as reference were compared. A questionnaire was also sent to the participating anesthesiologists to obtain their feedback on ML decision support. The accuracy of peak glucose level estimates by the anesthesiologists increased from 79.0 ± 13.7% without ML assistance to 84.7 ± 11.5% (< 0.001) when ML estimates were provided as reference. The accuracy of opioid requirement estimates increased from 18% without ML assistance to 42% (p < 0.001) when ML estimates were provided as reference. When ML estimates were provided, predictions of peak glucose improved for 8 out of the 10 anesthesiologists, while predictions of opioid requirements improved for 7 of the 10 anesthesiologists. Feedback questionnaire responses revealed that the anesthesiologist primarily used the ML estimates as reference to modify their clinical judgement. ML models can improve anesthesiologists' estimation of clinical parameters. ML predictions primarily served as reference information that modified an anesthesiologist's clinical estimate.

Patient Factors Associated with High Opioid Consumption after Common Surgical Procedures Following State-Mandated Opioid Prescription Regulations

BACKGROUND

State regulations have decreased prescribed opioids with more than 25% of patients abstaining from opioids. Despite this, 2 distinct populations of patients exist who consume "high" or "low" amounts of opioids. The aim of this study was to identify factors associated with postoperative opioid use after common surgical procedures and develop an opioid risk score.

STUDY DESIGN

Patients undergoing 35 surgical procedures from 7 surgical specialties were identified at a 620-bed tertiary care academic center and surveyed 1 week after discharge regarding opioid use and adequacy of analgesia. Electronic medical record data were used to characterize postdischarge opioids, complications, demographics, medical history, and social factors. High opioid use was defined as >75th percentile morphine milligram equivalents for each procedure. An opioid risk score was calculated from factors associated with opioid use identified by backward multivariate logistic regression analysis.

RESULTS

A total of 1,185 patients were enrolled between September 2017 and February 2019. Bivariate analyses revealed patient factors associated with opioid use including earlier substance use (p < 0.001), depression (p = 0.003), anxiety (p < 0.001), asthma (p = 0.006), obesity (p = 0.03), migraine (p = 0.004), opioid use in the 7 days before surgery (p < 0.001), and 31 Clinical Classifications Software Refined classifications (p < 0.05). Significant multivariates included: insurance (p = 0.005), employment status (p = 0.005), earlier opioid use (odds ratio [OR] 2.38 [95% CI 1.21 to 4.68], p = 0.01), coronary artery disease (OR 0.38 [95% CI 0.16 to 0.86], p = 0.02), acute pulmonary embolism (OR 9.81 [95% CI 3.01 to 32.04], p < 0.001), benign breast conditions (OR 3.42 [95% CI 1.76 to 6.64], p < 0.001), opioid-related disorders (OR 6.67 [95% CI 1.87 to 23.75], p = 0.003), mental and substance use disorders (OR 3.80 [95% CI 1.47 to 9.83], p = 0.006), headache (OR 1.82 [95% CI 1.24 to 2.67], p = 0.002), and previous cesarean section (OR 5.10 [95% CI 1.33 to 19.56], p = 0.02). An opioid risk score base was developed with an area under the curve of 0.696 for the prediction of high opioid use.

CONCLUSIONS

Preoperative patient characteristics associated with high opioid use postoperatively were identified and an opioid risk score was derived. Identification of patients with a higher need for opioids presents an opportunity for improved preoperative interventions, the use of nonopioid analgesic therapies, and alternative therapies.

Preventing Pediatric Chronic Postsurgical Pain: Time for Increased Rigor

Chronic postsurgical pain (CPSP) results from a cascade of events in the peripheral and central nervous systems following surgery. Several clinical predictors, including the prior pain state, premorbid psychological state (e.g., anxiety, catastrophizing), intraoperative surgical load (establishment of peripheral and central sensitization), and acute postoperative pain management, may contribute to the patient’s risk of developing CPSP. However, research on the neurobiological and biobehavioral mechanisms contributing to pediatric CPSP and effective preemptive/treatment strategies are still lacking. Here we evaluate the perisurgical process by identifying key problems and propose potential solutions for the pre-, intra-, and postoperative pain states to both prevent and manage the transition of acute to chronic pain. We propose an eight-step process involving preemptive and preventative analgesia, behavioral interventions, and the use of biomarkers (brain-based, inflammatory, or genetic) to facilitate timely evaluation and treatment of premorbid psychological factors, ongoing surgical pain, and postoperative pain to provide an overall improved outcome. By achieving this, we can begin to establish personalized precision medicine for children and adolescents presenting to surgery and subsequent treatment selection.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Big Data in Studying Acute Pain and Regional Anesthesia

The digital transformation of healthcare is advancing, leading to an increasing availability of clinical data for research. Perioperative big data initiatives were established to monitor treatment quality and benchmark outcomes. However, big data analyses have long exceeded the status of pure quality surveillance instruments. Large retrospective studies nowadays often represent the first approach to new questions in clinical research and pave the way for more expensive and resource intensive prospective trials. As a consequence, the utilization of big data in acute pain and regional anesthesia research has considerably increased over the last decade. Multicentric clinical registries and administrative databases (e.g., healthcare claims databases) have collected millions of cases until today, on which basis several important research questions were approached. In acute pain research, big data was used to assess postoperative pain outcomes, opioid utilization, and the efficiency of multimodal pain management strategies. In regional anesthesia, adverse events and potential benefits of regional anesthesia on postoperative morbidity and mortality were evaluated. This article provides a narrative review on the growing importance of big data for research in acute postoperative pain and regional anesthesia.