Central Line-Associated Bloodstream Infection (CLABSI)VA-AI-CLABSINCT07918352
Evaluation of an AI-Assisted Tool for CLABSI Surveillance at VA Medical Centers
A study testing Generative AI tool for CLABSI surveillance in people with Central Line-Associated Bloodstream Infection (CLABSI) and Bacteremia, run by University of Maryland, Baltimore.
Trial summary
Infection prevention and control programs at US hospitals perform surveillance to detect and publicly report hospital-onset central line-associated bloodstream infections (CLABSI) using standards set by CDC's National Healthcare Safety Network (NHSN). Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Central Line-Associated Bloodstream Infection (CLABSI), Bacteremia, Bloodstream Infections
- What is being tested?
- Generative AI tool for CLABSI surveillance
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 30 participants
- Where
- No sites listed yet
- Study dates
- 16 Nov 2026to 31 Dec 2027
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- VA medical center that provides short- or long-term acute care
- CLABSI surveillance is performed by a local infection prevention team who agree to complete all study assessments
Who cannot join
- 1. VA medical center planned for conversion to the Cerner electronic health record within the anticipated study period
Trial locations and contacts
No sites are listed yet. Contact the study team or a site near you to ask about taking part.
About this study
Official title: VA National AI Initiative (NAII) Evaluation of an AI-Assisted CLABSI Surveillance Tool: A Prospective Cluster-Randomized Trial
Infection prevention and control programs at US hospitals perform surveillance to detect and publicly report hospital-onset central line-associated bloodstream infections (CLABSI) using standards set by CDC's National Healthcare Safety Network (NHSN). Because this process requires time-consuming review of the medical record by dedicated infection preventionists, VA has developed a generative artificial intelligence (AI) tool that applies the NHSN CLABSI standard to clinical data from the medical record. In this quality improvement initiative, we will evaluate the tool as it is implemented operationally across a cohort of VA medical centers in 3 randomized waves. The purpose of this evaluation is (1) to determine whether the tool reduces the time required for CLABSI surveillance, (2) to assess the objectivity and trustworthiness of the tool from the perspective of infection preventionists, and (3) to detect patient safety events.
Read the detailed description
This study is being conducted from a VA operational perspective as quality improvement. This will proceed regardless of research approvals. This was submitted to the University of Maryland / Baltimore VA joint IRB/VA Research \& Development committees and determined to be non-human subjects research.
- Conditions
- Central Line-Associated Bloodstream Infection (CLABSI), Bacteremia, Bloodstream Infections
- Being tested
- Generative AI tool for CLABSI surveillance
- Keywords
- artificial intelligence, generative AI, infection surveillance, infection prevention, health care-associated infection, quality improvement, Veterans Affairs
- Medical subject headings
- Bacteremia, Sepsis, Cross Infection
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Generative AI tool for CLABSI surveillanceOther
The intervention involves implementation of a generative artificial intelligence (AI) tool that operationalizes the CDC National Healthcare Safety Network definition for central line-associated bloodstream infections (CLABSI) to support CLABSI surveillance. The tool reviews the medical record to confirm the presence and duration of a central line, identify competing or secondary sources of infection, exclude commensal organisms and bloodstream infections due to mucosal barrier injury, and provide supporting quotations from the medical record.
| Study group | Role | What they receive |
|---|---|---|
| Post-implementation of an AI for CLABSI surveillance | Experimental | Infection preventionists (reviewers) at participating VA medical centers will use the generative artificial intelligence (AI) tool while reviewing cases of bacteremia to adjudicate the presence of a central line-associated bloodstream infection (CLABSI). The tool operationalizes the CDC's National Healthcare Safety Network definition of CLABSI as discrete steps. Reviewers will be allowed to flexibly implement the tool within their workflow, will not be restricted from performing independent review of the medical record to clarify tool output when necessary, and will retain final authority regarding all CLABSI determinations for event reporting. Receives: Other: Generative AI tool for CLABSI surveillance |
| Standard CLABSI surveillance | No intervention | Infection preventionists at participating VA medical centers will use their pre-intervention approach to surveillance for central line-associated bloodstream infections (CLABSI), which involves manual review of the medical record and reporting per the CDC National Healthcare Safety Network CLABSI definition. |
What is being measured
The primary outcome is the main question the study is designed to answer.
Time per bacteremia case review
Time in elapsed minutes captured automatically by start and end time of the per-case review form. Assessed at time of completion of the bacteremia case review.
Measured: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.
Secondary outcomes (5)
Difficulty of bacteremia case review
Measured using the Single Ease Question, a validated single-item 7-level scale.
Measured: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.
Objectivity of case review
Measured using a question on the case review form ("How objective is the case to review? (1=not at all objective to 7=very objective)").
Measured: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.
Reviewer confidence in case review
Measured using a question on the case review form ("How confident are you with your review of this case? (1=not confident to 7=very confident)").
Measured: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.
Infection preventionist-identified safety problems
Reported using a binary question (yes/no) on the monthly survey administered to all sites during the post-implementation period.
Measured: Assessed monthly during each facility's 6-month post-implementation period
Infection preventionist-identified direct patient harm
Reported using a binary question (yes/no) on the monthly survey administered to all sites during the post-implementation period.
Measured: Assessed monthly during each facility's 6-month post-implementation period
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted5 Nov 2026
- Study start16 Nov 2026 (estimated)
- Primary completion30 Sep 2027 (estimated)
- Study completion31 Dec 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Central Line-Associated Bloodstream Infection (CLABSI)Studies of the same condition, open and under way.
- More trials run by University of Maryland, BaltimoreThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Crossover
- Model description
- This study will be a multicenter trial evaluating the implementation of a quality improvement intervention using a pragmatic stepped-wedge cluster-randomized design. At baseline, all participating VA medical centers will begin in the control condition. After a 1-month period of baseline data collection, three randomized clusters of medical centers will cross over into the intervention condition in successive steps with a 6-week interval between steps. Post-implementation data collection for each cluster will continue for 6 months.
- Masking
- None (open label)
- Enrolment
- 30 participants (estimated)
Sponsor and investigators
- Lead sponsor
- University of Maryland, Baltimore
- Sponsor type
- University, hospital or other
- Collaborators
- VA Maryland Health Care System, US Department of Veterans Affairs
- Responsible party
- Principal investigator, Daniel Morgan, VA Maryland Health Care System
- Investigators
- Daniel J Morgan, MD, MS, Principal investigator, University of Maryland, Baltimore
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07918352
- Sponsor's protocol ID
- HP-00120271
- Acronym
- VA-AI-CLABSI
- Status last verified
- Nov 2026
- First submitted
- 24 Oct 2026
- Last updated
- 5 Nov 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Study at a glance
From the registry record, last updated by the sponsor on 5 Nov 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- VA National AI Initiative (NAII) Evaluation of an AI-Assisted CLABSI Surveillance Tool: A Prospective Cluster-Randomized Trial
- ClinicalTrials.gov ID
- NCT07918352
- Acronym / sponsor ID
- VA-AI-CLABSI / HP-00120271
- Conditions
- Central Line-Associated Bloodstream Infection (CLABSI), Bacteremia, Bloodstream Infections
- Keywords
- artificial intelligence, generative AI, infection surveillance, infection prevention, health care-associated infection, quality improvement, Veterans Affairs
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 30 participants (estimated)
- Lead sponsor
- University of Maryland, BaltimoreUniversity, hospital or other
- Collaborators
- VA Maryland Health Care System, US Department of Veterans Affairs
- Study start
- 16 Nov 2026 (estimated)
- Primary completion
- 30 Sep 2027 (estimated)
- Study completion
- 31 Dec 2027 (estimated)
- First posted
- 5 Nov 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
Infection prevention and control programs at US hospitals perform surveillance to detect and publicly report hospital-onset central line-associated bloodstream infections (CLABSI) using standards set by CDC's National Healthcare Safety Network (NHSN). Because this process requires time-consuming review of the medical record by dedicated infection preventionists, VA has developed a generative artificial intelligence (AI) tool that applies the NHSN CLABSI standard to clinical data from the medical record. In this quality improvement initiative, we will evaluate the tool as it is implemented operationally across a cohort of VA medical centers in 3 randomized waves. The purpose of this evaluation is (1) to determine whether the tool reduces the time required for CLABSI surveillance, (2) to assess the objectivity and trustworthiness of the tool from the perspective of infection preventionists, and (3) to detect patient safety events.
Detailed description
This study is being conducted from a VA operational perspective as quality improvement. This will proceed regardless of research approvals. This was submitted to the University of Maryland / Baltimore VA joint IRB/VA Research \& Development committees and determined to be non-human subjects research.
Study design
- Primary purpose
- Health services research
- Allocation
- Randomised
- Intervention model
- Crossover
- Masking
- None (open label)
- Number of arms
- 2
- Model description
- This study will be a multicenter trial evaluating the implementation of a quality improvement intervention using a pragmatic stepped-wedge cluster-randomized design. At baseline, all participating VA medical centers will begin in the control condition. After a 1-month period of baseline data collection, three randomized clusters of medical centers will cross over into the intervention condition in successive steps with a 6-week interval between steps. Post-implementation data collection for each cluster will continue for 6 months.
| Arm | Type | Receives |
|---|---|---|
| Post-implementation of an AI for CLABSI surveillance | Experimental | Other: Generative AI tool for CLABSI surveillanceInfection preventionists (reviewers) at participating VA medical centers will use the generative artificial intelligence (AI) tool while reviewing cases of bacteremia to adjudicate the presence of a central line-associated bloodstream infection (CLABSI). The tool operationalizes the CDC's National Healthcare Safety Network definition of CLABSI as discrete steps. Reviewers will be allowed to flexibly implement the tool within their workflow, will not be restricted from performing independent review of the medical record to clarify tool output when necessary, and will retain final authority regarding all CLABSI determinations for event reporting. |
| Standard CLABSI surveillance | No intervention | –Infection preventionists at participating VA medical centers will use their pre-intervention approach to surveillance for central line-associated bloodstream infections (CLABSI), which involves manual review of the medical record and reporting per the CDC National Healthcare Safety Network CLABSI definition. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (2 listed)
- VA medical center that provides short- or long-term acute care
- CLABSI surveillance is performed by a local infection prevention team who agree to complete all study assessments
Key exclusion criteria (1 listed)
- 1. VA medical center planned for conversion to the Cerner electronic health record within the anticipated study period
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Generative AI tool for CLABSI surveillanceThe intervention involves implementation of a generative artificial intelligence (AI) tool that operationalizes the CDC National Healthcare Safety Network definition for central line-associated bloodstream infections (CLABSI) to support CLABSI surveillance. The tool reviews the medical record to confirm the presence and duration of a central line, identify competing or secondary sources of infection, exclude commensal organisms and bloodstream infections due to mucosal barrier injury, and provide supporting quotations from the medical record. | Other | Post-implementation of an AI for CLABSI surveillance |
Primary outcome
Time per bacteremia case review
Time frame: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.
Time in elapsed minutes captured automatically by start and end time of the per-case review form. Assessed at time of completion of the bacteremia case review.
5 secondary outcomes
Difficulty of bacteremia case review
Time frame: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.
Objectivity of case review
Time frame: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.
Reviewer confidence in case review
Time frame: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.
Infection preventionist-identified safety problems
Time frame: Assessed monthly during each facility's 6-month post-implementation period
Infection preventionist-identified direct patient harm
Time frame: Assessed monthly during each facility's 6-month post-implementation period
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 5 Nov 2026.
- Individual participant dataSharing planned: No
Related trials for Central Line-Associated Bloodstream Infection (CLABSI)
Active, not recruiting
Compassionate-Use of 4% T-EDTA Lock Solution for Central Venous Lines of Pediatric PN Patients
Central Line Complication, Central Line-associated Bloodstream Infection (CLABSI)
RecruitingPhase 3
Comparing The Safety And Efficacy Of DEFENCATH® In Reducing Central-Line Bloodstream Infections (CLABSIs) In Adults And Adolescent Participants Receiving Total Parenteral Nutrition Through A Central Venous Catheter (CVC)
Central Line Associated Blood Stream Infections (CLABSI)
Not yet recruitingObservational study
Central Line-Associated Bloodstream Infection QI Project
Central Line-associated Bloodstream Infection (CLABSI)
Not yet recruiting
Neonatal Catheter Lock for Infection Prevention
CLABSI - Central Line Associated Bloodstream Infection, CRBSI - Catheter Related Bloodstream Infection
Recruiting
Impact of Infusion Line Change Frequency on Infectious Complications Related to Central Venous Catheters in the ICU - A Randomized Controlled Trial
Intensive Care (ICU), Central Venous Catheter Related Infections
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Daniel J Morgan, MD, MS principal investigator
University of Maryland, Baltimore
Questions about this trial
What is this clinical trial studying?
A study testing Generative AI tool for CLABSI surveillance in people with Central Line-Associated Bloodstream Infection (CLABSI) and Bacteremia, run by University of Maryland, Baltimore.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 2 inclusion and 1 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 5 Nov 2026. Status can change between updates, so confirm with the study contact before making plans.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Daniel J Morgan, MD, MS (410-706-0066, dmorgan@som.umaryland.edu), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Time per bacteremia case review (time frame: At completion of each bacteremia case review performed during the study period beginning 1 month prior to implementation until 6 months post-implementation.). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 5 Nov 2026.