Machine learning approach to predicting persistent opioid use following lower extremity joint arthroplasty

Abstract

BackgroundThe objective of this study is to develop predictive models for persistent opioid use following lower extremity joint arthroplasty and determine if ensemble learning and an oversampling technique may improve model performance.MethodsWe compared various predictive models to identify at-risk patients for persistent postoperative opioid use using various preoperative, intraoperative, and postoperative data, including surgical procedure, patient demographics/characteristics, past surgical history, opioid use history, comorbidities, lifestyle habits, anesthesia details, and postoperative hospital course. Six classification models were evaluated: logistic regression, random forest classifier, simple-feedforward neural network, balanced random forest classifier, balanced bagging classifier, and support vector classifier. Performance with Synthetic Minority Oversampling Technique (SMOTE) was also evaluated. Repeated stratified k-fold cross-validation was implemented to calculate F1-scores and area under the receiver operating characteristics curve (AUC).ResultsThere were 1042 patients undergoing elective knee or hip arthroplasty in which 242 (23.2%) reported persistent opioid use. Without SMOTE, the logistic regression model has an F1 score of 0.47 and an AUC of 0.79. All ensemble methods performed better, with the balanced bagging classifier having an F1 score of 0.80 and an AUC of 0.94. SMOTE improved performance of all models based on F1 score. Specifically, performance of the balanced bagging classifier improved to an F1 score of 0.84 and an AUC of 0.96. The features with the highest importance in the balanced bagging model were postoperative day 1 opioid use, body mass index, age, preoperative opioid use, prescribed opioids at discharge, and hospital length of stay.ConclusionsEnsemble learning can dramatically improve predictive models for persistent opioid use. Accurate and early identification of high-risk patients can play a role in clinical decision making and early optimization with personalized interventions.

Preoperative Predictors of Prolonged Opioid Use in the 6 Months Following Total Knee Arthroplasty

“…Previously published predictive models for extended postoperative opioid use-all based on retrospective data-show an average AUC of 0.76 for preoperative opioid use. [62][63][64][65][66][67][68][69][70][71][72][73] Our prospective models show that at 6 weeks post-TKA, preoperative opioid use is a less accurate predictor (AUC = 0.64) than prior retrospective models indicate, highlighting the importance of psychosocial and pain-related predictors at this time point. In contrast, at 6-month follow-up, preoperative opioid use is an even better prospective predictor than prior work would suggest (AUC = 0.90), and the addition of the above phenotypic characteristics improves it even further.…”

Leveraging a Natural Language Processing Model (Transformers) on Electronic Medical Record Notes to Classify Persistent Opioid Use After Surgery

“…To this end, LLMs can be used to classify patients with persistent opioid use and can aid (1) in clinical decision support 9 ; and (2) as a critical step in developing accurate opioid prediction models. 10 Using NLP is a scalable solution for improving classification accuracy within large datasets, as the EHR reaches the status of “Big Data.”…”

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

“…The data included age (years), sex (male vs female), body mass index (kg/m 2 ), English-speaking, comorbidities, regional nerve block performance, general anesthesia, intraoperative ketamine, intraoperative total intravenous anesthesia, opioid consumption, and pain scores (11-point numeric rating scale [NRS] from 0 to 10). These features were included, as they were determined to be relevant to postoperative opioid use based on clinical judgement and previous research [ 14 , 15 ]. Opioid consumption, defined as total opioids consumed intraoperatively and in the PACU, was measured in intravenous morphine equivalents (MEQ).…”

“…Studies have shown surgical procedure as an independent risk factor for prolonged opioid use [4,19,20]. Other risk factors include preoperative opioids, tobacco use, gender, and mood disorders [21][22][23][24][25][26]. Although efforts are in place to standardize postoperative opioid prescriptions per surgical procedure [27], there continues to be a wide variety in the amount and duration of opioids prescribed and often in excess [1,[28][29][30][31]].…”