Machine Learning Prediction of Possible Central Line Associated Blood Stream Infections and Rate of Reduction

NCT07108660 | Recruiting DMC

• 2 other identifiers: STUDY2025000101SMS_211225 CLABSI 2025 SMC 250
• Study Type: interventional
• Target: 17,800
• Locations: 1 country
• Sites: 19

Brief Summary

Prospective, multi-center, cluster-randomized trial of a hospital Infection Preventionist (IP)-led quality improvement study to provide clinical teams with just-in-time clinical education and reinforcement of existing best practices recommendations based on the output of a possible Central Line Associated Blood Stream Infection (CLABSI) Machine Learning (ML) prediction model. The objective is to determine whether providing this model to Infection Preventionists will decrease the CLABSI rates versus routine clinical practice.

Conditions

Central Line Associated Blood Stream Infections (CLABSI)

Keywords

Inpatient; CLABSI; Central Line Associates Blood Stream Infections; Infection Prevention; Artificial Intelligence; Machine Learning; Healthcare Associated Infection; HAI

Outcome Measures

Primary Outcomes (1)

• CLABSI Rate

  Rate of CLABSIs (CLABSI Event Per Central Line Days)

  Day 1 of Hospitalization thru Discharge

Secondary Outcomes (7)

• CLABSI Rate expressed as SIR

  Day 1 of Hospitalization thru Discharge

• Possible CLABSI Rate

  Day 1 of Hospitalization thru Discharge

• Central Line Days

  Day 1 of Hospitalization thru Discharge

• Infection preventionist documentation of patient review

  Day 1 of Hospitalization thru Discharge

• Central line removal within 48 hours of model alert

  Day 1 of Hospitalization thru Discharge

Study Arms (2)

Hospitals receiving "EARLY" access to the prediction model.

EXPERIMENTAL

During the study period, the "EARLY" hospitals receive access to the Possible CLABSI ML model.

Behavioral: Infection Preventionist Led Best Practices Reminders

Hospitals receiving "LATE" access to the prediction model.

NO INTERVENTION

During the comparison period, the "LATE" hospitals do not receive access to the Possible CLABSI ML model.

Interventions

Infection Preventionist Led Best Practices Reminders BEHAVIORAL

Infection preventionists at each study hospital review a dashboard on a daily basis that contains predictions for the infection preventionist's hospital. If a patient is predicted to have a possible CLABSI by the ML model, the infection preventionist reviews the case and recommends next steps to the care team based on Providence's CLABSI prevention best-practices bundle, which include reviewing the line for necessity and recommending alternate IV access when appropriate. If line-removal isn't possible, the infection preventionist collaborates with the direct care team to ensure that the line maintenance best practices are observed, including maintaining a clean, dry and intact dressing and using daily chlorhexidine baths.

Hospitals receiving "EARLY" access to the prediction model.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

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

You may not qualify if:

• Less than 18 years of age

Sponsors & Collaborators

• Swedish Medical Center: lead
• Providence Health & Services: collaborator

Study Sites (19)

Providence Alaska Medical Center

Anchorage, Alaska, 99508, United States

RECRUITING

St. Mary Medical Center

Apple Valley, California, 92307, United States

RECRUITING

Providence Saint Joseph Medical Center

Burbank, California, 91505, United States

RECRUITING

St. Jude Medical Center

Fullerton, California, 92835, United States

RECRUITING

Providence Holy Cross Medical Center

Mission Hills, California, 91345, United States

RECRUITING

Mission Hospital

Mission Viejo, California, 92691, United States

RECRUITING

Queen of the Valley Medical Center

Napa, California, 94558, United States

RECRUITING

St. Joseph Hospital

Orange, California, 92868, United States

RECRUITING

Santa Rosa Memorial Hospital

Santa Rosa, California, 95405, United States

RECRUITING

Providence Cedars-Sinai Tarzana Medical Center

Tarzana, California, 91356, United States

RECRUITING

Providence St. Vincent Medical Center

Portland, Oregon, 97225, United States

RECRUITING

Covenant Medical Center

Lubbock, Texas, 79416, United States

RECRUITING

Swedish Medical Center Edmonds

Edmonds, Washington, 98026, United States

RECRUITING

Providence Regional Medical Center Everett

Everett, Washington, 98201, United States

RECRUITING

Providence St. Peter Hospital

Olympia, Washington, 98506, United States

RECRUITING

Kadlec Regional Medical Center

Richland, Washington, 99352, United States

RECRUITING

Swedish Medical Center Cherry Hill

Seattle, Washington, 98122, United States

RECRUITING

Swedish Medical Center First Hill

Seattle, Washington, 98122, United States

RECRUITING

Providence Sacred Heart Medical Center

Spokane, Washington, 99204, United States

RECRUITING

MeSH Terms

Conditions

Cross Infection

Condition Hierarchy (Ancestors)

Infections; Iatrogenic Disease; Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Chris Dale, MD, MPH

  Swedish Medical Center

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Chris Dale, MD, MPH

CONTACT

425-747-5822; christopher.dale@swedish.org

Evan Sylvester, MPH

CONTACT

425-681-6961; evan.sylvester@providence.org

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: This is a prospective, multi-center, cluster-randomized controlled trial evaluating whether a machine learning (ML) model predicting central line-associated bloodstream infection (CLABSI) risk can reduce CLABSI rates when integrated into infection prevention workflows. Twenty hospitals with the highest CLABSI burden in the Providence system were matched into 10 pairs using Mahalanobis distance based on infection count and standardized infection ratio (SIR). Within each pair, one hospital was randomized to early intervention (immediate access to the ML model) and the other to late intervention (access after a 4-month delay). The ML model identifies high-risk patients with central lines in place for \>48 hours, and infection preventionists use this information to guide best-practice interventions.

Study Record Dates

• First Submitted: July 17, 2025
• First Posted: August 7, 2025
• Study Start: July 1, 2025
• Primary Completion: November 1, 2025
• Study Completion (Estimated): December 1, 2027
• Last Updated: August 15, 2025

Record last verified: 2025-08

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ANALYTIC CODE
• Time Frame: Five years from conclusion of study.
• Access Criteria: Contact the Principal Investigator

Locations

US (19)