Smart EHR alerts and risk scores to prevent opioid overdoses

Machine-Learning Prediction and Reducing Overdoses with EHR Nudges (mPROVEN)

['FUNDING_R01'] · UNIVERSITY OF PITTSBURGH AT PITTSBURGH · NIH-11312598

This project uses computer-based risk scores and short electronic health record alerts to help clinicians reduce opioid overdose risk for patients who may be vulnerable.

Quick facts

Phase['FUNDING_R01']
Study typeNih_funding
SexAll
SponsorUNIVERSITY OF PITTSBURGH AT PITTSBURGH (nih funded)
Locations1 site (PITTSBURGH, UNITED STATES)
Trial IDNIH-11312598 on ClinicalTrials.gov

What this research studies

Researchers will install a machine-learning tool in the electronic health record to flag patients at higher risk of opioid overdose in the next three months. Short, clinician-facing behavioral "nudges" will appear in the EHR to encourage safer prescribing and other risk-reduction actions. The team will pilot and refine the alerts at the University of Pittsburgh/UPMC and then test the approach across clinical units to see if it changes clinician behavior and reduces overdose events. As a patient, you might be affected if your clinician receives an alert about your risk and offers different treatment or safety measures.

Who could benefit from this research

Good fit: Patients receiving care within the UPMC system who have opioid prescriptions, prior overdose history, substance-use risk factors, or other high-risk markers in their medical record are the most likely candidates.

Not a fit: People who do not receive care at participating UPMC clinics or who have low predicted risk based on their records are unlikely to be affected.

Why it matters

Potential benefit: If successful, this could lower overdose rates by focusing prevention on patients most likely to benefit and prompting safer clinician decisions.

How similar studies have performed: Previous work validated the machine-learning overdose risk model and showed that EHR behavioral nudges can change clinician prescribing, but combining these approaches at scale in a large health system is relatively new.

Where this research is happening

PITTSBURGH, UNITED STATES

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.

View on NIH RePORTER →

Conditions: Cancers

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.