PICTURE Pediatric: AI early-warning to spot kids likely to worsen
Pilot Randomized Controlled Trial of PICTURE-Pediatric
This pilot tests an AI-based early warning system that gives real-time risk scores and alerts to care teams for pediatric patients on general wards and ED boarders to see if the workflow and interface achieve high compliance.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 375 (estimated) |
| Ages | 30 Days to 25 Years |
| Sex | All |
| Sponsor | University of Michigan Academic / other |
| Locations | 1 site (Ann Arbor, Michigan) |
| Trial ID | NCT07304050 on ClinicalTrials.gov |
What this trial studies
PICTURE Pediatric uses routine EHR data (vitals, labs, monitored values) every 15 minutes to generate a deterioration risk score that has outperformed PEWS in prior work. In this interventional pilot, clinical teams will see PICTURE scores and alerts during one workflow arm while the control arm has scores hidden, and scores for red-risk patients will be included in handoff notes and inform morning rounds. The protocol does not mandate clinical actions based on alerts; care teams make decisions using their clinical judgment. The primary hypothesis is that the combined model, workflow, and interface will reach at least 80% compliance among clinicians, and clinician usability and acceptability will be measured via questionnaires.
Who should consider this trial
Good fit: Pediatric patients aged ≥30 days to ≤25 years who are on general care wards at Mott Children's Hospital or boarding in the ED but admitted to a pediatric floor medical team are the intended population.
Not a fit: Patients already in the ICU, those outside the specified age range, or patients located outside the enrolled wards/ED locations are not expected to be affected by this implementation.
Why it matters
Potential benefit: If successful, the system could help teams identify deteriorating children earlier, potentially reducing PICU transfers, morbidity, and hospital length of stay while improving bed flow.
How similar studies have performed: Prior work indicates the PICTURE Pediatric algorithm outperforms PEWS and similar scores for predicting deterioration, but real-world clinical implementation and workflow usability remain relatively novel and are the focus of this pilot.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria - Patients:
* Age ≥30 days and ≤25 years
* Be on the general care wards of Mott Children's Hospital or boarding in the Emergency Department (ED), but admitted to a pediatric floor medical team. These will be enforced by these criteria:
1. Patient class: not emergency b. Patient level of care: not Intensive Care unit (ICU) c. Patient locations (per protocol)
Exclusion Criteria - Patients:
* Patients that do not meet the inclusion criteria
Where this trial is running
Ann Arbor, Michigan
- University of Michigan — Ann Arbor, Michigan, United States (Recruiting)
Study contacts
- Principal investigator: Rodney Daniels — University of Michigan
- Study coordinator: Jay Semerad
- Email: jsemerad@umich.edu
- Phone: 734-647-4751
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.