Real-time clinician alerts in the ICU
Real-time Evaluation of an Outlier-based Alerting System
This project tests whether real-time alerts about unusual clinician behavior, sent to ICU teams, change bedside care for patients in two UPMC ICUs.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 3000 (estimated) |
| Ages | 18 Years to 100 Years |
| Sex | All |
| Sponsor | University of Pittsburgh Academic / other |
| Locations | 2 sites (Pittsburgh, Pennsylvania and 1 other locations) |
| Trial ID | NCT06996626 on ClinicalTrials.gov |
What this trial studies
An AI model continuously reviews EHR data for ICU patients at UPMC Presbyterian and Montefiore to flag outlier clinician behavior. Alerts are first reviewed by an ICU clinician for clinical relevance and, if potentially relevant, are passed to the treating ICU clinician (pharmacist, physician, or advanced practice provider). The treating clinician may act on the alert or take no action, and the study compares revealed-alert periods to unrevealed-alert controls to measure effects on bedside behavior. Investigators will track how often alerts lead to changes in care and any downstream effects on patient management.
Who should consider this trial
Good fit: Patients admitted to the UPMC Presbyterian or UPMC Montefiore ICUs during the study period are eligible, since all ICU patients at those sites are included.
Not a fit: Patients not admitted to these two UPMC ICUs, or those whose care is unlikely to be influenced by clinician-facing alerts (for example very short stays), are unlikely to directly benefit.
Why it matters
Potential benefit: If successful, the system could prompt safer bedside decisions and reduce preventable errors in ICU care.
How similar studies have performed: Related electronic alert and clinician decision-support systems have shown mixed results, with some safety gains in specific settings but limited evidence for real-time outlier alerts in ICUs.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * All patients in the Presbyterian and Montefiore ICUs Exclusion Criteria: * None
Where this trial is running
Pittsburgh, Pennsylvania and 1 other locations
- UPMC Montefiore — Pittsburgh, Pennsylvania, United States (Not_yet_recruiting)
- UPMC Presbyterian — Pittsburgh, Pennsylvania, United States (Recruiting)
Study contacts
- Principal investigator: David Huang, MD — University of Pittsburgh
- Study coordinator: David Huang, MD
- Email: smoote@pitt.edu
- Phone: 412-624-9459
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.