AI-driven clinical decision support to reduce hospital-acquired blood clots
AI-driven Clinical Decision Support to Reduce Hospital-Acquired Venous Thromboembolism
This project will test whether an automated AI tool that flags hospitalized adults at risk can help clinicians prevent hospital-acquired blood clots at Vanderbilt hospitals.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 2236 (estimated) |
| Sex | All |
| Sponsor | Vanderbilt University Medical Center Academic / other |
| Locations | 1 site (Nashville, Tennessee) |
| Trial ID | NCT06939803 on ClinicalTrials.gov |
What this trial studies
The VTE-AI randomized trial embeds an automated risk model into the electronic health record and randomizes inpatients to receive AI-driven clinical decision support alerts versus usual care. The VTE-AI algorithm computes admission and daily risk scores without clinician input and prompts clinicians to reconsider thromboprophylaxis when no orders exist and there are no contraindications. The primary outcome is the incidence of hospital-acquired venous thromboembolism during the hospital stay across Vanderbilt's urban and rural hospitals. The trial enrolls adult inpatients admitted to Vanderbilt University Medical Center and participating affiliated hospitals with no prespecified exclusions.
Who should consider this trial
Good fit: Ideal candidates are adult inpatients at the listed Vanderbilt hospitals who are not currently receiving thromboprophylaxis and have no contraindication to prophylaxis.
Not a fit: Patients already on appropriate blood-clot prevention, those with contraindications to prophylaxis, or patients admitted outside the Vanderbilt system are unlikely to benefit.
Why it matters
Potential benefit: If successful, the tool could lower the number of hospital-acquired blood clots, reduce complications and deaths, and decrease related healthcare costs.
How similar studies have performed: Previous prognostic models for HA-VTE have shown mixed performance, and while the VTE-AI score was retrospectively validated by the Vanderbilt team, randomized evidence that AI-driven alerts reduce HA-VTE is limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Inpatient admission to Vanderbilt Adult Hospital, Vanderbilt Tullahoma Harton Hospital, Vanderbilt Bedford County Hospital, or Vanderbilt Wilson County Hospital Exclusion Criteria: * None
Where this trial is running
Nashville, Tennessee
- Vanderbilt University Medical Center — Nashville, Tennessee, United States (Recruiting)
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.