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

NCT ID: NCT07108660

Last Updated: 2025-08-15

Study Results

Results pending

The study team has not published outcome measurements, participant flow, or safety data for this trial yet. Check back later for updates.

Basic Information

Get a concise snapshot of the trial, including recruitment status, study phase, enrollment targets, and key timeline milestones.

Recruitment Status

RECRUITING

Clinical Phase

NA

Total Enrollment

17800 participants

Study Classification

INTERVENTIONAL

Study Start Date

2025-07-01

Study Completion Date

2027-12-31

Brief Summary

Review the sponsor-provided synopsis that highlights what the study is about and why it is being conducted.

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.

Detailed Description

Dive into the extended narrative that explains the scientific background, objectives, and procedures in greater depth.

Central Line-Associated Bloodstream Infections (CLABSIs) remain a persistent and costly challenge in U.S. hospitals, contributing to increased mortality, prolonged hospital stays, and elevated healthcare costs. In 2022 alone, Providence St. Joseph Health (PSJH) recorded 275 CLABSIs across 430,000 central line days. Despite the implementation of best-practice prevention bundles, these infections continue to occur, prompting the exploration of machine learning (ML) as a tool to predict and mitigate CLABSI risk. While prior studies have demonstrated the predictive potential of ML models-with area under the curve (AUC) values reaching up to 0.87-no randomized trial has yet evaluated the real-world clinical impact of deploying such a model.

The primary objective of this trial is to determine whether the deployment of a machine learning model that predicts possible CLABSI risk, when provided to hospital Infection Preventionists (IPs) with a standardized workflow, can reduce CLABSI rates compared to routine practice. Secondary objectives include assessing the intervention's impact on central line removal within 48 hours of an alert, the rate of positive blood cultures, and various process metrics such as the frequency of IP interventions. Safety outcomes, including pneumothorax and hemorrhage, are also being monitored.

The study is designed as a prospective, open-label, multi-center, cluster-randomized controlled trial conducted across 20 Providence hospitals with the highest CLABSI burden. These hospitals account for approximately 90% of all CLABSI events within the system during 2023 and 2024. Hospitals were paired using Mahalanobis distance based on the hospital's CLABSI count and NHSN Standardized Infection Ratio (SIR) and then randomized into early and late intervention groups. The early group received access to the ML model for four to five months before the late group. Infection Preventionists at early hospitals used a dashboard to identify high-risk patients and deliver targeted education and interventions focused on central line care.

The machine learning model was developed using data from over 62,000 patients and more than 730,000 line-days collected between January 2015 and September 2024. A positive class was defined as a positive blood culture occurring within 24 to 72 hours in a patient with a central line in place for more than 48 hours. From 87 electronic medical record (EMR) data elements, 207 features were engineered for model development. The modeling process employed XGBoost and addressed class imbalance through oversampling, undersampling, and SMOTE techniques. The final model achieved an AUC of 0.93, with a recall of 0.72, precision of 0.66, and an F1 score of 0.68. To ensure fairness, the model underwent a bias analysis using the EEOC's four-fifths rule, confirming consistent performance across race, sex, and ethnicity subgroups.

Each day, the model scored all adult inpatients with central lines in place for more than 48 hours. Predictions were published to a PowerBI dashboard accessible to IPs at intervention hospitals. These IPs reviewed flagged patients, ensured adherence to the CLABSI prevention bundle, and recommended line removal when appropriate. The IPs actions were documented in the EMR. The intervention was supported by training, scripting for clinical conversations, and access to infectious disease physicians for consultation.

The primary outcome of the trial is the CLABSI rate, defined as events per 1,000 central line-days and adjudicated using NHSN criteria. Secondary outcomes include the proportion of lines removed within 48 hours of a model alert, the rate of positive blood cultures, the rate of possible CLABSIs (defined as a positive culture in a patient with a line in place for more than 48 hours), and the total number of central line days per hospital. Additional metrics include the frequency of IP interventions and before-after comparisons of CLABSI rates.

The statistical analysis plan centers on a generalized linear mixed model (GLMM), using either a Poisson or Negative Binomial distribution depending on the presence of overdispersion. The model includes a log of line-days as an offset and incorporates hospital as a random effect to account for clustering. Fixed effects include group assignment and calendar month. Covariates are included to improve precision and control for confounding. Hospital-level covariates include hospital type, medical school affiliation, average length of stay, total bed count, and ICU bed proportion. Patient-level covariates include age, race and ethnicity, primary payer, history of CLABSI, line type, and line location. Sensitivity analyses will explore the additional comorbidities such as immunosuppression, obesity, diabetes, and diarrhea. Inverse Probability of Treatment Weighting (IPTW) will be considered to further adjust for confounding.

Sample size calculations were based on a baseline CLABSI rate of 0.004 events per patient per month, with an intra-cluster correlation (ICC) of 0.05 and a targeted 20% relative risk reduction (RR = 0.8). Under these assumptions, approximately 8,920 patients per arm are required to achieve 80% power at a significance level of 0.01. The study duration was set at five months to accrue the necessary 64 CLABSI events. An interim analysis is planned at 2.5 months, using the O'Brien-Fleming group-sequential design to allow for early stopping due to efficacy or harm. The interim analysis will apply a nominal p-value threshold of 0.0088, while the final analysis will use a threshold of 0.0467 to maintain an overall Type I error rate of 5%.

Conditions

See the medical conditions and disease areas that this research is targeting or investigating.

Central Line Associated Blood Stream Infections (CLABSI)

Study Design

Understand how the trial is structured, including allocation methods, masking strategies, primary purpose, and other design elements.

Allocation Method

RANDOMIZED

Intervention Model

PARALLEL

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.
Primary Study Purpose

HEALTH_SERVICES_RESEARCH

Blinding Strategy

NONE

Study Groups

Review each arm or cohort in the study, along with the interventions and objectives associated with them.

Hospitals receiving "EARLY" access to the prediction model.

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

Group Type EXPERIMENTAL

Infection Preventionist Led Best Practices Reminders

Intervention Type 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 "LATE" access to the prediction model.

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

Group Type NO_INTERVENTION

No interventions assigned to this group

Interventions

Learn about the drugs, procedures, or behavioral strategies being tested and how they are applied within this trial.

Infection Preventionist Led Best Practices Reminders

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.

Intervention Type BEHAVIORAL

Eligibility Criteria

Check the participation requirements, including inclusion and exclusion rules, age limits, and whether healthy volunteers are accepted.

Inclusion Criteria

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

Exclusion Criteria

* Less than 18 years of age
Minimum Eligible Age

18 Years

Eligible Sex

ALL

Accepts Healthy Volunteers

No

Sponsors

Meet the organizations funding or collaborating on the study and learn about their roles.

Providence Health & Services

OTHER

Sponsor Role collaborator

Swedish Medical Center

OTHER

Sponsor Role lead

Responsible Party

Identify the individual or organization who holds primary responsibility for the study information submitted to regulators.

Responsibility Role SPONSOR

Principal Investigators

Learn about the lead researchers overseeing the trial and their institutional affiliations.

Chris Dale, MD, MPH

Role: PRINCIPAL_INVESTIGATOR

Swedish Medical Center

Locations

Explore where the study is taking place and check the recruitment status at each participating site.

Providence Alaska Medical Center

Anchorage, Alaska, United States

Site Status RECRUITING

St. Mary Medical Center

Apple Valley, California, United States

Site Status RECRUITING

Providence Saint Joseph Medical Center

Burbank, California, United States

Site Status RECRUITING

St. Jude Medical Center

Fullerton, California, United States

Site Status RECRUITING

Providence Holy Cross Medical Center

Mission Hills, California, United States

Site Status RECRUITING

Mission Hospital

Mission Viejo, California, United States

Site Status RECRUITING

Queen of the Valley Medical Center

Napa, California, United States

Site Status RECRUITING

St. Joseph Hospital

Orange, California, United States

Site Status RECRUITING

Santa Rosa Memorial Hospital

Santa Rosa, California, United States

Site Status RECRUITING

Providence Cedars-Sinai Tarzana Medical Center

Tarzana, California, United States

Site Status RECRUITING

Providence St. Vincent Medical Center

Portland, Oregon, United States

Site Status RECRUITING

Covenant Medical Center

Lubbock, Texas, United States

Site Status RECRUITING

Swedish Medical Center Edmonds

Edmonds, Washington, United States

Site Status RECRUITING

Providence Regional Medical Center Everett

Everett, Washington, United States

Site Status RECRUITING

Providence St. Peter Hospital

Olympia, Washington, United States

Site Status RECRUITING

Kadlec Regional Medical Center

Richland, Washington, United States

Site Status RECRUITING

Swedish Medical Center Cherry Hill

Seattle, Washington, United States

Site Status RECRUITING

Swedish Medical Center First Hill

Seattle, Washington, United States

Site Status RECRUITING

Providence Sacred Heart Medical Center

Spokane, Washington, United States

Site Status RECRUITING

Countries

Review the countries where the study has at least one active or historical site.

United States

Central Contacts

Reach out to these primary contacts for questions about participation or study logistics.

Chris Dale, MD, MPH

Role: CONTACT

425-747-5822

Evan Sylvester, MPH

Role: CONTACT

425-681-6961

Facility Contacts

Find local site contact details for specific facilities participating in the trial.

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Chris Dale, MD, MPH

Role: primary

425-747-5822

Other Identifiers

Review additional registry numbers or institutional identifiers associated with this trial.

SMS_211225 CLABSI 2025 SMC 250

Identifier Type: OTHER

Identifier Source: secondary_id

STUDY2025000101

Identifier Type: -

Identifier Source: org_study_id

More Related Trials

Additional clinical trials that may be relevant based on similarity analysis.