Implementation of an Opioid Use Disorder (OUD) Machine-Learning Phenotype in Real-Time for the ADAPT Project

ObjectiveDevelop and deploy a real-time, EHR-integrated machine learning phenotype to identify emergency department (ED) patients with opioid use disorder (OUD) for prospective clinical trial screening and buprenorphine initiation. Materials and MethodsWe conducted a multi-phase study across three EDs in a single United States health system from 2014 to 2025. Using visit-level data available at or before triage, we trained a random-forest classifier to estimate OUD risk and embedded scoring in the EHR to trigger point-of-care alerts for trial eligibility review. A computable silver-standard label supported retrospective development; a clinician gold-standard reference was established via structured, DSM-5-aligned chart review. Performance was summarized with ROC-/PR-AUC, calibration, and threshold-based classification metrics; prospective validation used a stratified random sample of flagged and unflagged encounters. ResultsRetrospective discrimination compared to the silver standard was high (ROC-AUC 0.99, 95% CI 0.98-0.99; PR-AUC 0.92, 95% CI 0.90-0.94), and calibration plots informed operating-point selection for real-time use. In prospective gold-standard validation (n=218), the positive predictive value was 98.28%, and the negative predictive value was 95.68% at the prespecified threshold. Discussion and ConclusionAn EHR-embedded, machine-learning phenotype can accurately and feasibly identify ED patients with OUD in real time, streamlining clinical trial enrollment and treatment initiation. Ongoing work will report operational metrics (e.g., alert volume and latency), monitor performance drift and equity across subgroups, and evaluate downstream clinical and trial outcomes. Author SummaryIn this study, we wanted to find a better way to identify people visiting the emergency department who may be living with opioid use problems. These patients are often hard to recognize quickly, even though timely support, including offering effective medications, can greatly improve their health and safety. Traditional approaches rely heavily on clinicians noticing certain patterns in real time, which can be challenging during busy emergency care. To address this gap, we examined over a decade of information from a large health system and developed a clinical decision support tool that reviews routine information collected at the start of an emergency visit. The tool gives clinicians a simple, real-time signal when a patient may benefit from additional evaluation or treatment. Our early experience shows that this approach can help teams identify patients more consistently and connect them to care more quickly. We hope this work will make it easier for hospitals to support people affected by opioid use and to run clinical studies that improve future treatment options.