Home › Trials › NCT07108660

Machine learning alerts to reduce central line bloodstream infections

Prediction and Reduction of Central Line Associated Blood Stream Infections: A Machine Learning Improvement Study

Not applicable Interventional Swedish Medical Center · NCT07108660

This trial will try a machine learning alert system given to hospital infection prevention teams to reduce bloodstream infections in hospitalized adults with central lines.

Quick facts

PhaseNot applicable
Study typeInterventional
Enrollment17800 (estimated)
Ages18 Years and up
SexAll
SponsorSwedish Medical Center Academic / other
Locations19 sites (Anchorage, Alaska and 18 other locations)
Trial IDNCT07108660 on ClinicalTrials.gov

What this trial studies

This is a prospective, open-label, multi-center, cluster-randomized trial across 20 Providence hospitals testing whether a machine learning model that predicts possible CLABSI, when provided to Infection Preventionists with a standardized workflow, reduces CLABSI rates compared with routine practice. The intervention delivers just-in-time risk alerts and prompts IP-led clinical education, reminders of best-practice central-line care, and targeted actions such as line removal within 48 hours of an alert. Secondary outcomes include line removal within 48 hours, rates of positive blood cultures, frequency of IP interventions, and safety events (for example, pneumothorax and hemorrhage). The trial uses electronic health record data for real-time prediction and tracks both process metrics and clinical outcomes.

Who should consider this trial

Good fit: Adults (18 years and older) who are hospitalized with central venous lines at participating Providence hospitals are the patients most likely to be included.

Not a fit: Children under 18, patients without a central line, and patients treated at non-participating hospitals are unlikely to receive benefit from this intervention.

Why it matters

Potential benefit: If successful, this approach could lower central line–associated bloodstream infections, reduce complications and lengths of stay, and decrease healthcare costs.

How similar studies have performed: Prior observational and predictive-model studies have shown good ML accuracy for CLABSI risk (AUCs up to ~0.87), but no randomized trial has yet demonstrated that deploying such models reduces infection rates.

Eligibility criteria

Show full inclusion / exclusion criteria 
Inclusion Criteria:

* The top twenty Providence St. Joseph Health Hospitals by CLABSI burden.

Exclusion Criteria:

* Less than 18 years of age

Where this trial is running

Anchorage, Alaska and 18 other locations

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
View on ClinicalTrials.gov → Find more trials like this →
Conditions Central Line Associated Blood Stream InfectionsInpatientCLABSICentral Line Associates Blood Stream InfectionsInfection PreventionArtificial IntelligenceMachine LearningHealthcare Associated Infection
Last reviewed 2026-06-13 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.