Ignite Creation Date:
2025-12-25 @ 2:07 AM
Ignite Modification Date:
2025-12-26 @ 4:17 AM
Study NCT ID:
NCT07108660
Status:
RECRUITING
Last Update Posted:
2025-08-15
First Post:
2025-07-17
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Machine Learning Prediction of Possible Central Line Associated Blood Stream Infections and Rate of Reduction
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D003428', 'term': 'Cross Infection'}], 'ancestors': [{'id': 'D007239', 'term': 'Infections'}, {'id': 'D007049', 'term': 'Iatrogenic Disease'}, {'id': 'D020969', 'term': 'Disease Attributes'}, {'id': 'D010335', 'term': 'Pathologic Processes'}, {'id': 'D013568', 'term': 'Pathological Conditions, Signs and Symptoms'}]}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'RANDOMIZED', 'maskingInfo': {'masking': 'NONE'}, 'primaryPurpose': 'HEALTH_SERVICES_RESEARCH', 'interventionModel': 'PARALLEL', 'interventionModelDescription': '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.'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 17800}}, 'statusModule': {'overallStatus': 'RECRUITING', 'startDateStruct': {'date': '2025-07-01', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-08', 'completionDateStruct': {'date': '2027-12', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2025-08-12', 'studyFirstSubmitDate': '2025-07-17', 'studyFirstSubmitQcDate': '2025-08-05', 'lastUpdatePostDateStruct': {'date': '2025-08-15', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2025-08-07', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2025-11', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'CLABSI Rate', 'timeFrame': 'Day 1 of Hospitalization thru Discharge', 'description': 'Rate of CLABSIs (CLABSI Event Per Central Line Days)'}], 'secondaryOutcomes': [{'measure': 'CLABSI Rate expressed as SIR', 'timeFrame': 'Day 1 of Hospitalization thru Discharge', 'description': 'Overall CLABSI rate expressed in Standardized Incident Ratio (SIR), using the National Healthcare Safety Network (NSHN) methodology'}, {'measure': 'Possible CLABSI Rate', 'timeFrame': 'Day 1 of Hospitalization thru Discharge', 'description': 'Possible CLABSI rate, where "possible CLABSI" is defined as positive blood culture in the patient who has had a central line in place for greater than 48 hours.'}, {'measure': 'Central Line Days', 'timeFrame': 'Day 1 of Hospitalization thru Discharge', 'description': 'Number of Central Line Days'}, {'measure': 'Infection preventionist documentation of patient review', 'timeFrame': 'Day 1 of Hospitalization thru Discharge', 'description': 'A process measure of model implementation, the frequency of infection preventionist intervention documentation after prediction model firing.'}, {'measure': 'Central line removal within 48 hours of model alert', 'timeFrame': 'Day 1 of Hospitalization thru Discharge', 'description': 'Central line removal within 48 hours of model firing for possible CLABSI risk.'}, {'measure': 'Facility Before and After', 'timeFrame': 'From trial start until 5 months after trial end.', 'description': 'Before-after change in CLABSI or possible CLABSI for all 20 hospitals based on before-after analysis by go-live date'}, {'measure': 'Safety outcomes after model prediction', 'timeFrame': 'Day 1 of Hospitalization thru Discharge', 'description': 'Structured assessment of possible patient harm, as assessed by the human-reviewed results of an large language model note text search for pneumothorax, arterial puncture or deep venous thrombosis in the 10 days following model prediction'}]}, 'oversightModule': {'oversightHasDmc': True, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['Inpatient', 'CLABSI', 'Central Line Associates Blood Stream Infections', 'Infection Prevention', 'Artificial Intelligence', 'Machine Learning', 'Healthcare Associated Infection', 'HAI'], 'conditions': ['Central Line Associated Blood Stream Infections (CLABSI)']}, 'descriptionModule': {'briefSummary': '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.\n\nThe objective is to determine whether providing this model to Infection Preventionists will decrease the CLABSI rates versus routine clinical practice.', 'detailedDescription': "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.\n\nThe 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.\n\nThe 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.\n\nThe 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.\n\nEach 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.\n\nThe 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.\n\nThe 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.\n\nSample 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%."}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* The top twenty Providence St. Joseph Health Hospitals by CLABSI burden.\n\nExclusion Criteria:\n\n* Less than 18 years of age'}, 'identificationModule': {'nctId': 'NCT07108660', 'acronym': 'CLABSI AI', 'briefTitle': 'Machine Learning Prediction of Possible Central Line Associated Blood Stream Infections and Rate of Reduction', 'organization': {'class': 'OTHER', 'fullName': 'Swedish Medical Center'}, 'officialTitle': 'Prediction and Reduction of Central Line Associated Blood Stream Infections: A Machine Learning Improvement Study', 'orgStudyIdInfo': {'id': 'STUDY2025000101'}, 'secondaryIdInfos': [{'id': 'SMS_211225 CLABSI 2025 SMC 250', 'type': 'OTHER', 'domain': 'Swedish Medical Center'}]}, 'armsInterventionsModule': {'armGroups': [{'type': 'EXPERIMENTAL', 'label': 'Hospitals receiving "EARLY" access to the prediction model.', 'description': 'During the study period, the "EARLY" hospitals receive access to the Possible CLABSI ML model.', 'interventionNames': ['Behavioral: Infection Preventionist Led Best Practices Reminders']}, {'type': 'NO_INTERVENTION', 'label': 'Hospitals receiving "LATE" access to the prediction model.', 'description': 'During the comparison period, the "LATE" hospitals do not receive access to the Possible CLABSI ML model.'}], 'interventions': [{'name': 'Infection Preventionist Led Best Practices Reminders', 'type': 'BEHAVIORAL', 'description': "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.", 'armGroupLabels': ['Hospitals receiving "EARLY" access to the prediction model.']}]}, 'contactsLocationsModule': {'locations': [{'zip': '99508', 'city': 'Anchorage', 'state': 'Alaska', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Providence Alaska Medical Center', 'geoPoint': {'lat': 61.21806, 'lon': -149.90028}}, {'zip': '92307', 'city': 'Apple Valley', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'St. Mary Medical Center', 'geoPoint': {'lat': 34.50083, 'lon': -117.18588}}, {'zip': '91505', 'city': 'Burbank', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Providence Saint Joseph Medical Center', 'geoPoint': {'lat': 34.18084, 'lon': -118.30897}}, {'zip': '92835', 'city': 'Fullerton', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'St. Jude Medical Center', 'geoPoint': {'lat': 33.87029, 'lon': -117.92534}}, {'zip': '91345', 'city': 'Mission Hills', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Providence Holy Cross Medical Center', 'geoPoint': {'lat': 34.68609, 'lon': -120.43683}}, {'zip': '92691', 'city': 'Mission Viejo', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Mission Hospital', 'geoPoint': {'lat': 33.60002, 'lon': -117.672}}, {'zip': '94558', 'city': 'Napa', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Queen of the Valley Medical Center', 'geoPoint': {'lat': 38.29714, 'lon': -122.28553}}, {'zip': '92868', 'city': 'Orange', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'St. Joseph Hospital', 'geoPoint': {'lat': 33.78779, 'lon': -117.85311}}, {'zip': '95405', 'city': 'Santa Rosa', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Santa Rosa Memorial Hospital', 'geoPoint': {'lat': 38.44047, 'lon': -122.71443}}, {'zip': '91356', 'city': 'Tarzana', 'state': 'California', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Providence Cedars-Sinai Tarzana Medical Center', 'geoPoint': {'lat': 34.17334, 'lon': -118.55397}}, {'zip': '97225', 'city': 'Portland', 'state': 'Oregon', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Providence St. Vincent Medical Center', 'geoPoint': {'lat': 45.52345, 'lon': -122.67621}}, {'zip': '79416', 'city': 'Lubbock', 'state': 'Texas', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Covenant Medical Center', 'geoPoint': {'lat': 33.57786, 'lon': -101.85517}}, {'zip': '98026', 'city': 'Edmonds', 'state': 'Washington', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Swedish Medical Center Edmonds', 'geoPoint': {'lat': 47.81065, 'lon': -122.37736}}, {'zip': '98201', 'city': 'Everett', 'state': 'Washington', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Providence Regional Medical Center Everett', 'geoPoint': {'lat': 47.97898, 'lon': -122.20208}}, {'zip': '98506', 'city': 'Olympia', 'state': 'Washington', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Providence St. Peter Hospital', 'geoPoint': {'lat': 47.04491, 'lon': -122.90169}}, {'zip': '99352', 'city': 'Richland', 'state': 'Washington', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Kadlec Regional Medical Center', 'geoPoint': {'lat': 46.28569, 'lon': -119.28446}}, {'zip': '98122', 'city': 'Seattle', 'state': 'Washington', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Swedish Medical Center Cherry Hill', 'geoPoint': {'lat': 47.60621, 'lon': -122.33207}}, {'zip': '98122', 'city': 'Seattle', 'state': 'Washington', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Swedish Medical Center First Hill', 'geoPoint': {'lat': 47.60621, 'lon': -122.33207}}, {'zip': '99204', 'city': 'Spokane', 'state': 'Washington', 'status': 'RECRUITING', 'country': 'United States', 'contacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}], 'facility': 'Providence Sacred Heart Medical Center', 'geoPoint': {'lat': 47.65966, 'lon': -117.42908}}], 'centralContacts': [{'name': 'Chris Dale, MD, MPH', 'role': 'CONTACT', 'email': 'christopher.dale@swedish.org', 'phone': '425-747-5822'}, {'name': 'Evan Sylvester, MPH', 'role': 'CONTACT', 'email': 'evan.sylvester@providence.org', 'phone': '425-681-6961'}], 'overallOfficials': [{'name': 'Chris Dale, MD, MPH', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'Swedish Medical Center'}]}, 'ipdSharingStatementModule': {'infoTypes': ['STUDY_PROTOCOL', 'SAP', 'ANALYTIC_CODE'], 'timeFrame': 'Five years from conclusion of study.', 'ipdSharing': 'YES', 'description': "The investigators are happy to share non-PHI data, as deemed permissible by the investigator's institutional research and legal teams.", 'accessCriteria': 'Contact the Principal Investigator'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Swedish Medical Center', 'class': 'OTHER'}, 'collaborators': [{'name': 'Providence Health & Services', 'class': 'OTHER'}], 'responsibleParty': {'type': 'SPONSOR'}}}}