JMIR Publications

ABSTRACT

ABSTRACT Introduction: Although opioid overdose is a leading cause of preventable death in the United States, existing approaches to identify individuals at elevated risk rely on imprecise rule-based criteria that misclassify patients’ risk of this serious health outcome. The Machine‑Learning Prediction and Reducing Overdoses with EHR Nudges (mPROVEN) trial integrates a validated machine‑learning (ML) overdose‑risk model with behavioral‑economics‑informed electronic health record (EHR) nudges to reduce the risk of overdose among elevated-risk patients. Methods and analysis: mPROVEN is a pragmatic cluster randomized controlled trial conducted in primary care practices within a large multi-state integrated health system. Eligible patients are adults (≥18 years) identified by the ML algorithm as having an elevated risk for overdose and seen in an office or telemedicine primary care visit during the study period. Primary care practices serve as the unit of randomization and will be randomized in equal allocation into three arms: (1) Usual Care, (2) Elevated‑Risk Flag only, where clinicians see a non-interruptive EHR flag indicating elevated risk of overdose, and (3) Elevated‑Risk Flag + Nudges, in which active-choice and accountable-justification alerts are embedded within the EHR in addition to the elevated risk flag. The trial will enroll a target cohort of 800 patients for the primary analysis. The intervention period is 4 months (or until the study ends, whichever occurs later). The primary outcome is a 3‑point composite measure of safer opioid prescribing at 4 months, awarding one point each for: active naloxone prescription, average opioid dosage < 50 MME/day, and absence of opioid–benzodiazepine overlap. Secondary outcomes include the composite outcome at 6 months follow-up, each component of the ordinal score, and measures of healthcare utilization (i.e., emergency department or inpatient visits and emergency department or inpatient visits for overdose). Comparisons of outcomes by study arm will follow an intention‑to‑treat approach using linear mixed‑effects models to account for clustering at the clinic level. Ethics and dissemination: The study was approved by the University of Pittsburgh Institutional Review Board (IRB) and is overseen by an independent Data and Safety Monitoring Board. The IRB granted a waiver of patient informed consent because the intervention poses minimal risk and mirrors routine EHR alert workflows. Study findings will be disseminated through peer‑reviewed publications, scientific presentations, and internal health‑system communication and feedback.