Chronic opioid use is associated with early biologic discontinuation in inflammatory bowel disease

Applying Machine Learning Models Derived From Administrative Claims Data to Predict Medication Nonadherence in Patients Self-Administering Biologic Medications for Inflammatory Bowel Disease

Background

Adherence to self-administered biologic therapies is important to induce remission and prevent adverse clinical outcomes in Inflammatory bowel disease (IBD). This study aimed to use administrative claims data and machine learning methods to predict nonadherence in an academic medical center test population.

Methods

A model-training dataset of beneficiaries with IBD and the first unique dispense of a self-administered biologic between June 30, 2016 and June 30, 2019 was extracted from the Commercial Claims and Encounters and Medicare Supplemental Administrative Claims Database. Known correlates of medication nonadherence were identified in the dataset. Nonadherence to biologic therapies was defined as a proportion of days covered ratio <80% at 1 year. A similar dataset was obtained from a tertiary academic medical center's electronic medical record data for use in model testing. A total of 48 machine learning models were trained and assessed utilizing the area under the receiver operating characteristic curve as the primary measure of predictive validity.

Results

The training dataset included 6998 beneficiaries (n = 2680 nonadherent, 38.3%) while the testing dataset included 285 patients (n = 134 nonadherent, 47.0%). When applied to test data, the highest performing models had an area under the receiver operating characteristic curve of 0.55, indicating poor predictive performance. The majority of models trained had low sensitivity and high specificity.

Conclusions

Administrative claims-trained models were unable to predict biologic medication nonadherence in patients with IBD. Future research may benefit from datasets with enriched demographic and clinical data in training predictive models.

Opioid use and associated factors in 1676 patients with inflammatory bowel disease: a multicentre quality improvement project

Objective

Despite its association with poorer outcomes, opioid use in inflammatory bowel disease (IBD) is not well characterised in the UK. We aimed to examine the extent of opioid use, the associated factors and the use of mitigation techniques such as pain-service review and opioid weaning plans among individuals with IBD.

Methods

Data were collected from consecutive patients attending IBD outpatient appointments at 12 UK hospitals. A predefined questionnaire was used to collect data including patient demographics, IBD history, opioid use in the past year (>2 weeks) and opioid-use mitigation techniques. Additionally, consecutive IBD-related hospital stays leading up to July 2019 were reviewed with data collected regarding opioid use at admission, discharge and follow-up as well as details of the admission indication.

Results

In 1352 outpatients, 12% had used opioids within the past 12 months. Over half of these individuals were taking opioids for non-IBD pain and less than half had undergone an attempted opioid wean.In 324 hospitalised patients, 27% were prescribed opioids at discharge from hospital. At 12 months postdischarge, 11% were using opioids. Factors associated with opioid use in both cohorts included female sex, Crohn's disease and previous surgery.

Conclusions

1 in 10 patients with IBD attending outpatient appointments were opioid exposed in the past year while a quarter of inpatients were discharged with opioids, and 11% continued to use opioids 12 months after discharge. IBD services should aim to identify patients exposed to opioids, reduce exposure where possible and facilitate access to alternative pain management approaches.