Identifying Opioid Use Disorder in the Emergency Department: Multi-System Electronic Health Record–Based Computable Phenotype Derivation and Validation Study

Abstract

BackgroundDeploying accurate computable phenotypes in pragmatic trials requires a trade-off between precise and clinically sensical variable selection. In particular, evaluating the medical encounter to assess a pattern leading to clinically significant impairment or distress indicative of disease is a difficult modeling challenge for the emergency department.ObjectiveThis study aimed to derive and validate an electronic health record–based computable phenotype to identify emergency department patients with opioid use disorder using physician chart review as a reference standard.MethodsA two-algorithm computable phenotype was developed and evaluated using structured clinical data across 13 emergency departments in two large health care systems. Algorithm 1 combined clinician and billing codes. Algorithm 2 used chief complaint structured data suggestive of opioid use disorder. To evaluate the algorithms in both internal and external validation phases, two emergency medicine physicians, with a third acting as adjudicator, reviewed a pragmatic sample of 231 charts: 125 internal validation (75 positive and 50 negative), 106 external validation (56 positive and 50 negative).ResultsCohen kappa, measuring agreement between reviewers, for the internal and external validation cohorts was 0.95 and 0.93, respectively. In the internal validation phase, Algorithm 1 had a positive predictive value (PPV) of 0.96 (95% CI 0.863-0.995) and a negative predictive value (NPV) of 0.98 (95% CI 0.893-0.999), and Algorithm 2 had a PPV of 0.8 (95% CI 0.593-0.932) and an NPV of 1.0 (one-sided 97.5% CI 0.863-1). In the external validation phase, the phenotype had a PPV of 0.95 (95% CI 0.851-0.989) and an NPV of 0.92 (95% CI 0.807-0.978).ConclusionsThis phenotype detected emergency department patients with opioid use disorder with high predictive values and reliability. Its algorithms were transportable across health care systems and have potential value for both clinical and research purposes.

Healthcare utilization patterns among persons who use drugs during the COVID-19 pandemic

“…Regardless of the extent to which the reduction was due to patients delaying care versus the healthcare system being overwhelmed, identifying persons with drug use disorder and connecting them to evidence-based addiction treatment remains a top priority during the COVID-19 pandemic; moreover, given the increased risk of severe COVID-19 complications that this vulnerable population faces, it is important to utilize preestablished treatment initiation algorithms that minimize the risk of COVID-19 transmission, such as those we discuss in the Background section. For example, researchers and providers can continue to work together to develop tools that utilize "real-world" data from electronic health records (EHRs) to aid in the recognition and phenotyping of persons with drug use disorder (Afshar et al, 2019;Chartash et al, 2019;Sanchez-Roige & Palmer, 2019;Sharma et al, 2020), which would allow providers to better identify both new and existing patients. Providers can also continue to develop methods to improve identification and linkage of persons with drug use disorder within their current Table 1 Referrals to treatment, by month.…”

Interrupted Time Series of User‐centered Clinical Decision Support Implementation for Emergency Department–initiated Buprenorphine for Opioid Use Disorder

“…Eligible patients were adult ED patients meeting the criteria of a computable phenotype derived from electronic health record (EHR) data that was developed to capture ED patients likely to have OUD and not actively on medication for OUD (MOUD, i.e., methadone, BUP, or naltrexone). 25 The phenotype is comprised of two algorithms: one based on clinician and billing codes (Algorithm 1) and the other based on structured EHR data of the chief complaint (Algorithm 2). Additionally, the phenotype excludes patients who are admitted to the hospital or pregnant.…”

“…The phenotype has an externally validated positive predictive value of 0.95 and a negative predictive value of 0.92. 25 A waiver of informed consent was obtained given that data were only collected retrospectively and did not involve patient interaction or identifiable information. Regarding clinician subject inclusion criteria, attending ED physicians practicing at the intervention site who cared for the phenotype-positive patients were eligible for inclusion.…”

Two Data-Driven Approaches to Identifying the Spectrum of Problematic Opioid Use: A Pilot Study within a Chronic Pain Cohort

“…Several existing methods have utilized EHR data for OUD prediction [14][15][16][17][18][19][20]. Some models identify OUD cohorts using ICD codes [16][17], but this approach likely underrepresents problematic opioid use [13]. Other models used unstructured clinical notes text [14,15,18,19].…”