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

Objective: Develop 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 Methods: We 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. Results: Retrospective 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 Conclusion: An 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.