Dataset Information

Predicting postoperative opioid use with machine learning and insurance claims in opioid-naive patients.

ABSTRACT:

Background

The clinical impact of postoperative opioid use requires accurate prediction strategies to identify at-risk patients. We utilize preoperative claims data to predict postoperative opioid refill and new persistent use in opioid-naïve patients.

Methods

A retrospective study was conducted on 112,898 opioid-naïve adult postoperative patients from Optum's de-identified Clinformatics® Data Mart database. Potential predictors included sociodemographic data, comorbidities, and prescriptions within one year prior to surgery.

Results

Compared to linear models, non-linear models led to modest improvements in predicting refills - area under the receiver operating characteristics curve (AUROC) 0.68 vs. 0.67 (p < 0.05) - and performed identically in predicting new persistent use - AUROC = 0.66. Undergoing major surgery, opioid prescriptions within 30 days prior to surgery, and abdominal pain were useful in predicting refills; back/joint/head pain were the most important features in predicting new persistent use.

Conclusions

Preoperative patient attributes from insurance claims could potentially be useful in guiding prescription practices for opioid-naïve patients.

SUBMITTER: Hur J

PROVIDER: S-EPMC8373633 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting postoperative opioid use with machine learning and insurance claims in opioid-naïve patients.

Hur Jaewon J Tang Shengpu S Gunaseelan Vidhya V Vu Joceline J Brummett Chad M CM Englesbe Michael M Waljee Jennifer J Wiens Jenna J

American journal of surgery 20210326 3

<h4>Background</h4>The clinical impact of postoperative opioid use requires accurate prediction strategies to identify at-risk patients. We utilize preoperative claims data to predict postoperative opioid refill and new persistent use in opioid-naïve patients.<h4>Methods</h4>A retrospective study was conducted on 112,898 opioid-naïve adult postoperative patients from Optum's de-identified Clinformatics® Data Mart database. Potential predictors included sociodemographic data, comorbidities, and p ...[more]

PMID: 33820654

Similar Datasets

Project description:ImportanceChronic opioid use imposes a substantial burden in terms of morbidity and economic costs. Whether opioid-naive patients undergoing surgery are at increased risk for chronic opioid use is unknown, as are the potential risk factors for chronic opioid use following surgery.ObjectiveTo characterize the risk of chronic opioid use among opioid-naive patients following 1 of 11 surgical procedures compared with nonsurgical patients.Design, setting, and participantsRetrospective analysis of administrative health claims to determine the association between chronic opioid use and surgery among privately insured patients between January 1, 2001, and December 31, 2013. The data concluded 11 surgical procedures (total knee arthroplasty [TKA], total hip arthroplasty, laparoscopic cholecystectomy, open cholecystectomy, laparoscopic appendectomy, open appendectomy, cesarean delivery, functional endoscopic sinus surgery [FESS], cataract surgery, transurethral prostate resection [TURP], and simple mastectomy). Multivariable logistic regression analysis was performed to control for possible confounders, including sex, age, preoperative history of depression, psychosis, drug or alcohol abuse, and preoperatice use of benzodiazepines, antipsychotics, and antidepressants.ExposuresOne of the 11 study surgical procedures.Main outcomes and measuresChronic opioid use, defined as having filled 10 or more prescriptions or more than 120 days' supply of an opioid in the first year after surgery, excluding the first 90 postoperative days. For nonsurgical patients, chronic opioid use was defined as having filled 10 or more prescriptions or more than 120 days' supply following a randomly assigned "surgery date."ResultsThe study included 641 941 opioid-naive surgical patients (169 666 men; mean [SD] age, 44.0 [12.8] years), and 18 011 137 opioid-naive nonsurgical patients (8 849 107 men; mean [SD] age, 42.4 [12.6] years). Among the surgical patients, the incidence of chronic opioid in the first preoperative year ranged from 0.119% for Cesarean delivery (95% CI, 0.104%-0.134%) to 1.41% for TKA (95% CI, 1.29%-1.53%) The baseline incidence of chronic opioid use among the nonsurgical patients was 0.136% (95% CI, 0.134%-0.137%). Except for cataract surgery, laparoscopic appendectomy, FESS, and TURP, all of the surgical procedures were associated with an increased risk of chronic opioid use, with odds ratios ranging from 1.28 (95% CI, 1.12-1.46) for cesarean delivery to 5.10 (95% CI, 4.67-5.58) for TKA. Male sex, age older than 50 years, and preoperative history of drug abuse, alcohol abuse, depression, benzodiazepine use, or antidepressant use were associated with chronic opioid use among surgical patients.Conclusions and relevanceIn opioid-naive patients, many surgical procedures are associated with an increased risk of chronic opioid use in the postoperative period. A certain subset of patients (eg, men, elderly patients) may be particularly vulnerable.

Project description:Background contextAlthough spine procedures have historically been performed inpatient, there has been a recent shift to the outpatient setting for selected cases due to increased patient satisfaction and reduced cost. Effective postoperative pain management while limiting over-prescribing of opioids, which may lead to persistent opioid use, is critical to performing spine surgery in the outpatient setting.PurposeTo assess if there is an increased risk for new, persistent opioid use between inpatient and outpatient spine procedures.Study designRetrospective analysis using national administrative claims database.Patient sampleA total of 390,049 opioid-naïve patients with a perioperative opioid prescription who underwent an inpatient or outpatient spine surgery.Outcome measuresPatients with perioperative opioid prescriptions who filled ≥ 1 opioid prescription between 90- and 180-days following surgery were defined as new, persistent opioid users.MethodsWe utilized a claims database to identify opioid-naïve patients who underwent lumbar or cervical fusion, total disc arthroplasty, or decompression procedures. We constructed a multivariable logistic regression to evaluate the association between inpatient versus outpatient surgery and the development of new, persistent opioid use while adjusting for several patient factors.ResultsA total of 19,205 (11.7%) inpatient and 18,546 (8.2%) outpatient patients developed new, persistent opioid use. Outpatient lumbar and cervical spine surgery patients were significantly less likely to develop new, persistent opioid use following surgery compared to inpatient spine surgery patients (OR = 0.71 [95% confidence interval {CI}: 0.69, 0.73], p < .001). Average morphine milligram equivalents (MMEs) (inpatient = 1,476 MME +/- 22.7, outpatient = 1,072 MME +/- 18.5, p < .001) and average MMEs per day (inpatient = 91.6 MME +/- 0.32, outpatient = 77.7 MME +/- 0.28, p < .001) were lower in the outpatient cohort compared to the inpatient.ConclusionOur results support the shift from inpatient to outpatient spine procedures, as outpatient procedures were not associated with an increased risk for new, persistent opioid use. As more patients become candidates for outpatient spine surgery, predictors of new, persistent opioid use should be considered during risk stratification.Level of evidenceLevel III Prognostic Study.Mini abstractWe utilized a national administrative claims database to identify opioid-naïve patients who underwent common spine procedures. Outpatient lumbar and cervical spine surgery patients were significantly less likely to be new, persistent opioid users following surgery compared to inpatient spine surgery patients. Our results support the shift to outpatient spine procedures.

Project description:BackgroundOpioid use disorder (OUD) is a growing public health crisis, with opioids involved in an overwhelming majority of drug overdose deaths in the United States in recent years. While medications for opioid use disorder (MOUD) effectively reduce overdose mortality, only a minority of patients are able to access MOUD; additionally, those with unstable housing receive MOUD at even lower rates.ObjectiveBecause MOUD access is a multifactorial issue, we leverage machine learning techniques to assess and rank the variables most important in predicting whether any individual receives MOUD. We also seek to explain why persons experiencing homelessness have lower MOUD access and identify potential targets for action.MethodsWe utilize a gradient boosted decision tree algorithm (specifically, XGBoost) to train our model on SAMHSA's Treatment Episode Data Set-Admissions, using anonymized demographic and clinical information for over half a million opioid admissions to treatment facilities across the United States. We use Shapley values to quantify and interpret the predictive power and influencing direction of individual features (i.e., variables).ResultsOur model is effective in predicting access to MOUD with an accuracy of 85.97% and area under the ROC curve of 0.9411. Notably, roughly half of the model's predictive power emerges from facility type (23.34%) and geographic location (18.71%); other influential factors include referral source (6.74%), history of prior treatment (4.41%), and frequency of opioid use (3.44%). We also find that unhoused patients go to facilities that overall have lower MOUD treatment rates; furthermore, relative to housed (i.e., independent living) patients at these facilities, unhoused patients receive MOUD at even lower rates. However, we hypothesize that if unhoused patients instead went to the facilities that housed patients enter at an equal percent (but still received MOUD at the lower unhoused rates), 89.50% of the disparity in MOUD access would be eliminated.ConclusionThis study demonstrates the utility of a model that predicts MOUD access and both ranks the influencing variables and compares their individual positive or negative contribution to access. Furthermore, we examine the lack of MOUD treatment among persons with unstable housing and consider approaches for improving access.

Project description:Widely-prescribed prodrug opioids (e.g., hydrocodone) require conversion by liver enzyme CYP-2D6 to exert their analgesic effects. The most commonly prescribed antidepressant, selective serotonin reuptake inhibitors (SSRIs), inhibits CYP-2D6 activity and therefore may reduce the effectiveness of prodrug opioids. We used a machine learning approach to identify patients prescribed a combination of SSRIs and prodrug opioids postoperatively and to examine the effect of this combination on postoperative pain control. Using EHR data from an academic medical center, we identified patients receiving surgery over a 9-year period. We developed and validated natural language processing (NLP) algorithms to extract depression-related information (diagnosis, SSRI use, symptoms) from structured and unstructured data elements. The primary outcome was the difference between preoperative pain score and postoperative pain at discharge, 3-week and 8-week time points. We developed computational models to predict the increase or decrease in the postoperative pain across the 3 time points by using the patient's EHR data (e.g. medications, vitals, demographics) captured before surgery. We evaluate the generalizability of the model using 10-fold cross-validation method where the holdout test method is repeated 10 times and mean area-under-the-curve (AUC) is considered as evaluation metrics for the prediction performance. We identified 4,306 surgical patients with symptoms of depression. A total of 14.1% were prescribed both an SSRI and a prodrug opioid, 29.4% were prescribed an SSRI and a non-prodrug opioid, 18.6% were prescribed a prodrug opioid but were not on SSRIs, and 37.5% were prescribed a non-prodrug opioid but were not on SSRIs. Our NLP algorithm identified depression with a F1 score of 0.95 against manual annotation of 300 randomly sampled clinical notes. On average, patients receiving prodrug opioids had lower average pain scores (p<0.05), with the exception of the SSRI+ group at 3-weeks postoperative follow-up. However, SSRI+/Prodrug+ had significantly worse pain control at discharge, 3 and 8-week follow-up (p < .01) compared to SSRI+/Prodrug- patients, whereas there was no difference in pain control among the SSRI- patients by prodrug opioid (p>0.05). The machine learning algorithm accurately predicted the increase or decrease of the discharge, 3-week and 8-week follow-up pain scores when compared to the pre-operative pain score using 10-fold cross validation (mean area under the receiver operating characteristic curve 0.87, 0.81, and 0.69, respectively). Preoperative pain, surgery type, and opioid tolerance were the strongest predictors of postoperative pain control. We provide the first direct clinical evidence that the known ability of SSRIs to inhibit prodrug opioid effectiveness is associated with worse pain control among depressed patients. Current prescribing patterns indicate that prescribers may not account for this interaction when choosing an opioid. The study results imply that prescribers might instead choose direct acting opioids (e.g. oxycodone or morphine) in depressed patients on SSRIs.

Project description:ObjectiveIn older patients receiving general anesthesia, postoperative delirium (POD) is the most frequent form of cerebral dysfunction. Early identification of patients at higher risk to develop POD could provide the opportunity to adapt intraoperative and postoperative therapy. We, therefore, propose a machine learning approach to predict the risk of POD in elderly patients, using routine intraoperative electroencephalography (EEG) and clinical data that are readily available in the operating room.MethodsWe conducted a retrospective analysis of the data of a single-center study at the Charité-Universitätsmedizin Berlin, Department of Anesthesiology [ISRCTN 36437985], including 1,277 patients, older than 60 years with planned surgery and general anesthesia. To deal with the class imbalance, we used balanced ensemble methods, specifically Bagging and Random Forests and as a performance measure, the area under the ROC curve (AUC-ROC). We trained our models including basic clinical parameters and intraoperative EEG features in particular classical spectral and burst suppression signatures as well as multi-band covariance matrices, which were classified, taking advantage of the geometry of a Riemannian manifold. The models were validated with 10 repeats of a 10-fold cross-validation.ResultsIncluding EEG data in the classification resulted in a robust and reliable risk evaluation for POD. The clinical parameters alone achieved an AUC-ROC score of 0.75. Including EEG signatures improved the classification when the patients were grouped by anesthetic agents and evaluated separately for each group. The spectral features alone showed an AUC-ROC score of 0.66; the covariance features showed an AUC-ROC score of 0.68. The AUC-ROC scores of EEG features relative to patient data differed by anesthetic group. The best performance was reached, combining both the EEG features and the clinical parameters. Overall, the AUC-ROC score was 0.77, for patients receiving Propofol it was 0.78, for those receiving Sevoflurane it was 0.8 and for those receiving Desflurane 0.73. Applying the trained prediction model to an independent data set of a different clinical study confirmed these results for the combined classification, while the classifier on clinical parameters alone did not generalize.ConclusionA machine learning approach combining intraoperative frontal EEG signatures with clinical parameters could be an easily applicable tool to early identify patients at risk to develop POD.